user
string | videos
list | gt
int64 | predict
string | pred_order
list | top1_correct
bool | gt_pos
int64 | latency_ms
float64 | index
int64 | request_messages
list |
|---|---|---|---|---|---|---|---|---|---|
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_eVTMUEYhwDE.mp4",
"activitynet/videos/v_NpBZn7OHUKo.mp4",
"activitynet/videos/v_uqiMw7tQ1Cc.mp4",
"activitynet/videos/v_gIhVeU8xbrs.mp4",
"activitynet/videos/v_1epGZvRN3Fw.mp4"
] | 3
|
<answer>1</answer>
|
[
1
] | false
| 0
| 25,768.688315
| 0
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A weight lifting tutorial is given. The coach helps the guy in red with the proper body placement and lifting technique.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_eVTMUEYhwDE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_NpBZn7OHUKo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uqiMw7tQ1Cc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_gIhVeU8xbrs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1epGZvRN3Fw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_HktZZPJMU8s.mp4",
"activitynet/videos/v_1imA9vLRd3k.mkv",
"activitynet/videos/v_LmioUbGNv04.mp4",
"activitynet/videos/v_bXdq2zI1Ms0.mp4",
"activitynet/videos/v_6LLDsbc8XMM.mp4"
] | 4
|
<answer>3</answer>
|
[
3
] | false
| 0
| 33,041.859635
| 1
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen speaking to the camera and pans out into more men standing behind him. The first man then begins performing martial arts moves while speaking to he camera. He continues moving around and looking to the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HktZZPJMU8s.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1imA9vLRd3k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LmioUbGNv04.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bXdq2zI1Ms0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_6LLDsbc8XMM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_FsS_NCZEfaI.mp4",
"activitynet/videos/v_FX4inHmWQtE.mp4",
"activitynet/videos/v_sxQbiXWFdKs.mp4",
"activitynet/videos/v_3TNDCTlLlGk.mkv",
"activitynet/videos/v_sG3JpMuXFnU.mp4"
] | 1
|
<answer>2</answer>
|
[
2
] | false
| 0
| 38,336.422621
| 2
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Several shots of boats are shown riding around as well as people riding on the boats and speaking to one another. Several shots are then shown of people sitting on the water as well as life under the water. The camera pans around old cars under water as well as people in the area.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FX4inHmWQtE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sxQbiXWFdKs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3TNDCTlLlGk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sG3JpMuXFnU.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Rho3u46ZIEE.mp4",
"activitynet/videos/v_KzZlSbM16aY.mp4",
"activitynet/videos/v_K6Tm5xHkJ5c.mp4",
"activitynet/videos/v_t1-GV2bAL4I.mp4",
"activitynet/videos/v_91XkPU8A5hs.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 22,048.000755
| 3
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen speaking to the camera while holding an accordion and and moving her hands around. She demonstrates how to play the instrument while still speaking to the camera and moving all around.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Rho3u46ZIEE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_KzZlSbM16aY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_K6Tm5xHkJ5c.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_t1-GV2bAL4I.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_91XkPU8A5hs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_msiX-xky6Ac.mp4",
"activitynet/videos/v_Ty0BvWyYPVA.mp4",
"activitynet/videos/v_pgff9mC5y3s.mp4",
"activitynet/videos/v_4Lu8ECLHvK4.mp4",
"activitynet/videos/v_f6j6lb0AaxM.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 18,662.458615
| 4
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"There are some people including small children near a soccer field. A small boy is playing by himself a he stands on a large square tile. A man dressed in a blue shirt come running towards him and points out his finger, indicating to the boy to go there. The boy gets off the tile and walks to another tile. Then another little boy wearing a gray shirt comes to that tile and begins playing. The other little boy moves away to another tile. There are some man playing with small children on the lawn. The little boy comes running towards some children and his father follows him.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_msiX-xky6Ac.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Ty0BvWyYPVA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_pgff9mC5y3s.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4Lu8ECLHvK4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_f6j6lb0AaxM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_iA2Q4t-o58w.mp4",
"activitynet/videos/v_dJ0kxnyVzFI.mp4",
"activitynet/videos/v_bG7hnpAeja0.mp4",
"activitynet/videos/v_HWV_ccmZVPA.mp4",
"activitynet/videos/v_fG0nn2IVdDM.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 16,536.044198
| 5
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are dancing having fun at a party. A race starts and people are running. Cheerleaders are standing on the side of the road. People are dancing on the grass.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iA2Q4t-o58w.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_dJ0kxnyVzFI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bG7hnpAeja0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HWV_ccmZVPA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fG0nn2IVdDM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_i1PpX1IOcIs.mp4",
"activitynet/videos/v_GGSY1Qvo990.mp4",
"activitynet/videos/v_j9QPrMZuegY.mp4",
"activitynet/videos/v_PJysE5c1WDs.mp4",
"activitynet/videos/v_aDaazrgvjJg.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 9,994.998532
| 6
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A female weight lifter bends at the knees. She lifts a barbell to her chest. She then lifts it over her head before dropping it heavily to the ground.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_i1PpX1IOcIs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GGSY1Qvo990.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_j9QPrMZuegY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_PJysE5c1WDs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_aDaazrgvjJg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A large kid playground slide is shown. Several people slide down, a woman and her little girl."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_yj2WJBqmEHk.mp4",
"activitynet/videos/v__uKKSGTNJAY.mp4",
"activitynet/videos/v_5I0K3y27EUM.mp4",
"activitynet/videos/v_JTrwGfPJNzU.mp4",
"activitynet/videos/v_hghdjiQlYko.mp4"
] | 4
|
<answer>1</answer>
|
[
1
] | false
| 0
| 10,312.377371
| 8
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A large kid playground slide is shown. Several people slide down, a woman and her little girl.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yj2WJBqmEHk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_JTrwGfPJNzU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_hghdjiQlYko.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_qaB0igbuKuQ.mp4",
"activitynet/videos/v_tfPm9xAZ5z0.mp4",
"activitynet/videos/v_xOmfJGR5fBw.mp4",
"activitynet/videos/v_frePM0YGtQE.mp4",
"activitynet/videos/v_U36rsW_WhUA.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 20,151.516695
| 7
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy puts a black cat on the kitchen floor. The guy reaches for a scissor and sits next to the cat. The guy carries the cat. The guy uses the scissor to cut the cat's claws. The guy puts the clippings in his palm. The guy pets the cat and puts the cat on the floor. The guy gets up and trashes the clippings. The owner and pet exit the kitchen.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qaB0igbuKuQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tfPm9xAZ5z0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_xOmfJGR5fBw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_frePM0YGtQE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_U36rsW_WhUA.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_s1YjWVUu6pM.mp4",
"activitynet/videos/v_YZvdzvM-124.mp4",
"activitynet/videos/v_lfllVwgOWBk.mp4",
"activitynet/videos/v_gOniW-yEZ0k.mp4",
"activitynet/videos/v_5BbHu0WQZqw.mp4"
] | 4
|
<answer>1</answer>
|
[
1
] | false
| 0
| 15,749.863021
| 9
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen kneeling down next to a man. Another person is seen kneeling nearby. The man pans closely around the man.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_s1YjWVUu6pM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_YZvdzvM-124.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lfllVwgOWBk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_gOniW-yEZ0k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5BbHu0WQZqw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_rwxSphRRIL8.mp4",
"activitynet/videos/v_kbe4iowYMqM.mp4",
"activitynet/videos/v_3j2d27w3x5Q.mp4",
"activitynet/videos/v_RKDjetk5Kko.mp4",
"activitynet/videos/v_Po8gmt7hVTY.mkv"
] | 5
|
<answer>1</answer>
|
[
1
] | false
| 0
| 18,145.284797
| 12
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A chef is talking inside a kitchen as he fills a pan with frying oil and water. He boils pasta noodles in a pot. He then tastes the noodles when they are done.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_rwxSphRRIL8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kbe4iowYMqM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3j2d27w3x5Q.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_RKDjetk5Kko.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Po8gmt7hVTY.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_smh90DBXsBg.mp4",
"activitynet/videos/v_HtkuvF7VbSQ.mp4",
"activitynet/videos/v_aPEqCGdCsp0.mp4",
"activitynet/videos/v_qm8sJxsZ5VY.mp4",
"activitynet/videos/v_j05b3qqgRxw.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 26,017.51495
| 11
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is sitting in a chair getting a tattoo. He stands up and yells at the man tattooing. A woman in a pink shirt is sitting in front of him. He walks out the door of the shop and walks down the street.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_smh90DBXsBg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HtkuvF7VbSQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_aPEqCGdCsp0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qm8sJxsZ5VY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_j05b3qqgRxw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_6czh95dpwAA.mp4",
"activitynet/videos/v_yACg55C3IlM.mkv",
"activitynet/videos/v_iSH43hQoxio.mp4",
"activitynet/videos/v_Lwy92HbuZII.mkv",
"activitynet/videos/v_XoFikALe8Q0.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 16,336.017989
| 13
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two girls are outside in bathing suits cleaning the front of a green vehicle. One of the girl then walks away and goes to get something from a man cleaning the motorcycle. They continue to wash the vehicle and then the girls walks over and grabs the water hose. She comes back to rinse the vehicle and then holds it up to the girl's head and washes her hair.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_6czh95dpwAA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yACg55C3IlM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iSH43hQoxio.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Lwy92HbuZII.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_XoFikALe8Q0.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_zGTqXydTuQs.mp4",
"activitynet/videos/v_ijgLl3PHHE0.mp4",
"activitynet/videos/v_W30cufYc_ZI.mp4",
"activitynet/videos/v_cHYZPYLwvks.mp4",
"activitynet/videos/v_FsS_NCZEfaI.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 58,379.563186
| 10
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Three scuba divers are seen moving along the water with one giving a thumbs up to the camera and the camera panning all around the ocean. Several shots are shown of the divers taking pictures under the water as well as taking off their mask and waving to the camera. In the end the divers come to the surface.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zGTqXydTuQs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ijgLl3PHHE0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_W30cufYc_ZI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cHYZPYLwvks.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS_NCZEfaI.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_iHO42zwYsu0.mp4",
"activitynet/videos/v_CjPN7fw0B48.mp4",
"activitynet/videos/v_E9R1H8xRIW8.mp4",
"activitynet/videos/v_z1tV0-C3IBw.mp4",
"activitynet/videos/v_CJWSed5v4jE.mkv"
] | 3
|
<answer>1</answer>
|
[
1
] | false
| 0
| 32,191.08578
| 14
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen pushing a lawn mower across a lawn to cut the grass. The man continues moving the machine all along the yard while the camera captures his movements.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iHO42zwYsu0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CjPN7fw0B48.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_E9R1H8xRIW8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z1tV0-C3IBw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CJWSed5v4jE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_UqU_mAjgknQ.mp4",
"activitynet/videos/v_-wXbBZDSIa8.mp4",
"activitynet/videos/v_eFbZ0_TJLE0.mkv",
"activitynet/videos/v_5qsXmDi8d74.mp4",
"activitynet/videos/v_0zjA3KPnLK8.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 14,964.81331
| 16
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A wrestler is seen walking out in front of an audience and sitting on the floor. Two men are then seen walking out onto a pit with one throwing dirt and kneeling down. The men begin fighting with one pushing another out and leads into several more clips of the men wrestling.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UqU_mAjgknQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_-wXbBZDSIa8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_eFbZ0_TJLE0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5qsXmDi8d74.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_0zjA3KPnLK8.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_ByF8Pg3xXNA.mp4",
"activitynet/videos/v_4OeZViscNp4.mp4",
"activitynet/videos/v_k3oPZS_Id3M.mp4",
"activitynet/videos/v_V1SEaTS9hos.mp4",
"activitynet/videos/v_9RAW6QibWRs.mp4"
] | 4
|
<answer>5</answer>
|
[
5
] | false
| 0
| 30,399.536214
| 15
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen sitting in front of a bucket holding clothes in his hands. Another person is seen sitting next to him sticking his hand in a bucket. The men continue washing clothes next to one another while dipping them into a bucket.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ByF8Pg3xXNA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4OeZViscNp4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_k3oPZS_Id3M.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_V1SEaTS9hos.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_WzDnorAzWVU.mp4",
"activitynet/videos/v_sEGceBU8icE.mp4",
"activitynet/videos/v_nB90Q8sTBgE.mp4",
"activitynet/videos/v_ng14GLT_hHQ.mp4",
"activitynet/videos/v_1UgjxeAPq_A.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 20,734.282649
| 17
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling on the kitchen floor. He is using a bucket of paints and a canvas. He uses the paints to create an image on the canvas.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WzDnorAzWVU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sEGceBU8icE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nB90Q8sTBgE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ng14GLT_hHQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1UgjxeAPq_A.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_cROJALtLB1k.mp4",
"activitynet/videos/v_nGABbRHJ2Ug.mp4",
"activitynet/videos/v__MR8G1jwM4o.mp4",
"activitynet/videos/v_f4CSejhkTd8.mp4",
"activitynet/videos/v_E50qKeeMbgU.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 13,990.917447
| 19
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A girl is seen standing near a piece of exercise equipment talking a man. She continues speaking to him and has him watch her while she steps on the machine. She rides the bike moving back and fourth speaking to the man and switches places with the man.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cROJALtLB1k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nGABbRHJ2Ug.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__MR8G1jwM4o.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_f4CSejhkTd8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_E50qKeeMbgU.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_wPYr19iFxhw.mp4",
"activitynet/videos/v_CfDdbeAk8LE.mp4",
"activitynet/videos/v_XQaaA2UZYh8.mp4",
"activitynet/videos/v_7JXae2so5-E.mp4",
"activitynet/videos/v_GcE-0A4Titg.mp4"
] | 1
|
<answer>1</answer>
|
[
1
] | true
| 1
| 14,183.498107
| 18
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The camera is showing an arc welder in a shop. A man approaches the arc welder and begins using it to weld some metal bars. The man shows the metal bar to the camera. The man sets the bar down and begins welding it again.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_wPYr19iFxhw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CfDdbeAk8LE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_XQaaA2UZYh8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7JXae2so5-E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GcE-0A4Titg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_arnKDX_ToxE.mp4",
"activitynet/videos/v_8-QcL1k5n6k.mp4",
"activitynet/videos/v_D0pVkTEYQg8.mp4",
"activitynet/videos/v_tnt6Wpv_kHc.mp4",
"activitynet/videos/v_c4ctwOucndQ.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 11,617.518422
| 20
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy exercises on a stationary bike. The guy has his hand on the handles. The guy lets go of the handles and puts his hands to his side.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_arnKDX_ToxE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_8-QcL1k5n6k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tnt6Wpv_kHc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_c4ctwOucndQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_4OCbTYrThtc.mkv",
"activitynet/videos/v_Fdzw3niNDYY.mp4",
"activitynet/videos/v_tjEMbP2SODQ.mp4",
"activitynet/videos/v_LUDZ7e0RdEE.mp4",
"activitynet/videos/v_2icoQWmbocU.mp4"
] | 2
|
<answer>4</answer>
|
[
4
] | false
| 0
| 14,144.183129
| 22
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is looking at a red vase. A woman takes her shirt off. The two begin fighting with swords.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4OCbTYrThtc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Fdzw3niNDYY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tjEMbP2SODQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LUDZ7e0RdEE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2icoQWmbocU.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_od1jHUzgrAU.mp4",
"activitynet/videos/v_uyGxlvak-Bg.mkv",
"activitynet/videos/v_dFVX_2UQ2WY.mp4",
"activitynet/videos/v_y9kk0ptXevk.mp4",
"activitynet/videos/v_k85EQoiLckw.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 26,904.119644
| 21
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see an opening title screen. A pair of red boots sit on a table. A lady talks and pours soap in a glass then wipes the boots with the soap. The lady talks and shows a bottle of olive oil. We see the closing title screen.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_od1jHUzgrAU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uyGxlvak-Bg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_dFVX_2UQ2WY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_y9kk0ptXevk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_k85EQoiLckw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_3K_8CdJS9lE.mp4",
"activitynet/videos/v_ymJTN8aKZEw.mp4",
"activitynet/videos/v_rgAALWYnRrg.mp4",
"activitynet/videos/v_Wgh8e4V8hBc.mp4",
"activitynet/videos/v_iiqaJGokpEw.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 13,164.366759
| 24
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man spin a girl who is blindfold and holds a bat to hit a piñata. Then, the girl swing the bat in the air, and in the second try she hits the piñata and break it. Candies fall from the piñata.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3K_8CdJS9lE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ymJTN8aKZEw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_rgAALWYnRrg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Wgh8e4V8hBc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iiqaJGokpEw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_5JVHUcOW0GE.mp4",
"activitynet/videos/v_jikOPvJPU-c.mp4",
"activitynet/videos/v_ZTHsS5lQyvQ.mp4",
"activitynet/videos/v_z0tiCqKa4cs.mp4",
"activitynet/videos/v_EwYgRPVDQWQ.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 25,144.143257
| 23
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A lady in short hair, wearing an orange top is standing by the kitchen counter, on the counter there are black pan, mayo, foil, plate, bread, knife. She spread the mayo on the bread, put cheese, on the black cutting board, beside the knife is a tomato, she put the tomato on the bread, put the cheese in the plastic bag, shows the sandwich, placed the other side of the bread on top of the sandwich. She moved to the stove, the black pan is on the stove, she put the butter using a bread knife, covered the kettle with foil, placed the bread on the pan and press it using the kettle with foil, she stood beside the stove while she waits, then turn over the bread, press the kettle with foil on it. She placed the bread on the plate, cut it and half, she is sitting on the green chair and started eating her sandwich.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5JVHUcOW0GE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_jikOPvJPU-c.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZTHsS5lQyvQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z0tiCqKa4cs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EwYgRPVDQWQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Br1Ty6PCrv8.mp4",
"activitynet/videos/v_5I0K3y27EUM.mp4",
"activitynet/videos/v_q2KR3lzTrq4.mkv",
"activitynet/videos/v__uKKSGTNJAY.mp4",
"activitynet/videos/v_2SYTRqm4Ym4.mp4"
] | 3
|
<answer>2</answer>
|
[
2
] | false
| 0
| 12,559.004449
| 26
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A mother helps slide a boy in a playground. The boy walk away from the slide while the mother follow him, then the mother help slice the boy again. After, the boy walks away on the grass, while mother sits on a bench.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Br1Ty6PCrv8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5I0K3y27EUM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_q2KR3lzTrq4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__uKKSGTNJAY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2SYTRqm4Ym4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_DVXOr56dlKg.mp4",
"activitynet/videos/v_5UlxCwq-LOs.mp4",
"activitynet/videos/v_Rokj1EIAHHk.mp4",
"activitynet/videos/v_FsS8cQbfKTQ.mp4",
"activitynet/videos/v_fJ4xMCc5SKk.mp4"
] | 5
|
<answer>4</answer>
|
[
4
] | false
| 0
| 20,835.868023
| 25
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man begins running down a track and doing several flips and tricks while many watch on the sides. He high fives another man and the same jumps are seen again in slow motion.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_DVXOr56dlKg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5UlxCwq-LOs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Rokj1EIAHHk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FsS8cQbfKTQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fJ4xMCc5SKk.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_AXw2bkQyRPo.mp4",
"activitynet/videos/v_V4U5SaPDL0E.mp4",
"activitynet/videos/v_tY6UFSLtIoE.mp4",
"activitynet/videos/v_CRzaKuaCXr8.mp4",
"activitynet/videos/v_2imjxY43yYM.mkv"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 12,228.129585
| 28
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see people dancing and light flashing in a club. The camera is tilted on its's side. A man spins a lady over and over. A man stops in front of the camera and shows the back of his shirt before turning to talk to the camera. The man spins the lady over and over and over.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_AXw2bkQyRPo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_V4U5SaPDL0E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tY6UFSLtIoE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CRzaKuaCXr8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2imjxY43yYM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_1rf7t4sYtIA.mp4",
"activitynet/videos/v_oCicjtc1t9Y.mp4",
"activitynet/videos/v_EvJqfGXb5Fo.mp4",
"activitynet/videos/v_ll91M5topgU.mp4",
"activitynet/videos/v_90vop6PS2Y0.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 17,250.848063
| 27
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A boy pushes a rake while riding a scooter down the driveway. It pushes the leaves in the driveway out to the road. He continues the pattern until the driveway is clean of debris.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1rf7t4sYtIA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_oCicjtc1t9Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EvJqfGXb5Fo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ll91M5topgU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_90vop6PS2Y0.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_fCLnOf-YjEI.mp4",
"activitynet/videos/v_olBh9KMAHMQ.mp4",
"activitynet/videos/v_bb9AIdvKkZU.mp4",
"activitynet/videos/v_i1CVl-0-gJE.mp4",
"activitynet/videos/v_a1WhnMcTbrY.mp4"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 12,747.726318
| 29
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A guy hold a shovel over his shoulder while recording himself. the camera then spins in a circle. the guy now scoops up some snow in the shovel picks it up then dumps it a couple of times. the guy use the shovel to clean the snow of the top of his bushes. finally the guy tosses his last snow he scooped up.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fCLnOf-YjEI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_olBh9KMAHMQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bb9AIdvKkZU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_i1CVl-0-gJE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_a1WhnMcTbrY.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_9PY28-zQhm4.mp4",
"activitynet/videos/v_FNAt8Pew0HA.mp4",
"activitynet/videos/v_57buK1yvKPk.mp4",
"activitynet/videos/v_ux3h_qEusvw.mp4",
"activitynet/videos/v_lgu-DBDWlEs.mp4"
] | 3
|
<answer>2</answer>
|
[
2
] | false
| 0
| 13,339.34845
| 31
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A young girl is seen standing before a counter peeling potatoes with a peeler. The girl continues peeling while speaking to the camera and waving the potato all around her. The girl continues peeling while looking over and speaking to the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9PY28-zQhm4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FNAt8Pew0HA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_57buK1yvKPk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ux3h_qEusvw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lgu-DBDWlEs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_e_0bMJEFiN8.mp4",
"activitynet/videos/v_x44fn0snUvw.mp4",
"activitynet/videos/v_sS-KyhAzeUY.mkv",
"activitynet/videos/v_EwjDShmfFHM.mp4",
"activitynet/videos/v_4Sf9C_vtYIs.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 19,485.768545
| 30
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person extends their hands out towards the faucet. They turn on the faucet and wet their hands. The person pumps soap into their hands. The person scrubs their hands thoroughly with the soap. They extend the hand washing to their wrists. They turn on the faucet and rinse their hands and wrists. They extend their palms out in front of the faucet.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_e_0bMJEFiN8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_x44fn0snUvw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sS-KyhAzeUY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EwjDShmfFHM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4Sf9C_vtYIs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_G77y1JRjZDU.mp4",
"activitynet/videos/v_L2FgftH2VD8.mp4",
"activitynet/videos/v_optJ47P_5Ys.mp4",
"activitynet/videos/v_gl_0jjJBUkc.mp4",
"activitynet/videos/v_9RAW6QibWRs.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 11,884.311192
| 33
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen pumping water out of a machine while another wheel kneels down in front and washes clothes. The people speak back and fourth to one another while the camera pans around and watches them work.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_G77y1JRjZDU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_L2FgftH2VD8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_optJ47P_5Ys.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_gl_0jjJBUkc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9RAW6QibWRs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_z3xkE5Ox-2A.mp4",
"activitynet/videos/v_YcjLd_XBK5Y.mp4",
"activitynet/videos/v_ZVIi4lPU6h0.mp4",
"activitynet/videos/v_1y2aqd5HQlU.mp4",
"activitynet/videos/v_tJ2xOG_EWOg.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 27,754.430307
| 32
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man shows to carve a pumpkin using a sharp tool. Then, the man carves a devil face in the pumpkin. Then, the woman puts a light inside the pumpkin and continues improving the carved pumpkin.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z3xkE5Ox-2A.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_YcjLd_XBK5Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVIi4lPU6h0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1y2aqd5HQlU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tJ2xOG_EWOg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_9XmzbuByY_E.mp4",
"activitynet/videos/v_RHtpBRwZ9hM.mp4",
"activitynet/videos/v_Oa26_SgrY8w.mp4",
"activitynet/videos/v_VAG6ECk5WYo.mp4",
"activitynet/videos/v_D2TQ_RR2Q50.mp4"
] | 2
|
<answer>4</answer>
|
[
4
] | false
| 0
| 16,463.658806
| 34
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are sitting behind a desk talking. They start playing a game of curling. Two girls in purple are standing on the ice.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9XmzbuByY_E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_RHtpBRwZ9hM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Oa26_SgrY8w.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_VAG6ECk5WYo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_D2TQ_RR2Q50.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_kCb2Km85Yn4.mp4",
"activitynet/videos/v_wkSm7bUCgGQ.mp4",
"activitynet/videos/v_GyBIC-DBoss.mp4",
"activitynet/videos/v_zpBZ7HMNO34.mp4",
"activitynet/videos/v_zYQ-WdosIwI.mp4"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 27,831.313648
| 35
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen standing on a pink may while speaking to the camera. The woman then gets on knees and sits backwards. She looks forward while sitting up and does this several times while speaking to the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kCb2Km85Yn4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_wkSm7bUCgGQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GyBIC-DBoss.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zpBZ7HMNO34.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zYQ-WdosIwI.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_7NG6UrY2Foo.mp4",
"activitynet/videos/v_E88Sr9H3Wi8.mp4",
"activitynet/videos/v_yjazHd6a5SQ.mkv",
"activitynet/videos/v_b1QkoG9hxk8.mp4",
"activitynet/videos/v_PxGggNnMGtQ.mkv"
] | 1
|
<answer>1</answer>
|
[
1
] | true
| 1
| 20,508.594909
| 36
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man comes onto the screen and announces that he will show the viewers how to make a drink. He fills a cup with ice and pours all the ingredients into the glass. He takes a spoon and stirs it up. He takes out another glass and pours the drink into the new glass and places a straw into the drink.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7NG6UrY2Foo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_E88Sr9H3Wi8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yjazHd6a5SQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_b1QkoG9hxk8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_PxGggNnMGtQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_STAvUAslEYM.mp4",
"activitynet/videos/v_oD0RWEO8D1g.mp4",
"activitynet/videos/v_JQavlg895jU.mp4",
"activitynet/videos/v_AC9mml3mqps.mp4",
"activitynet/videos/v_mjbzWcSeiwQ.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 23,321.882361
| 37
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A screen is shown playing video above a stage and leads into performers skating out on ice as well as hockey players behind them. The players all line up on the ice with one waving a flag and then begin skating around.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_STAvUAslEYM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_oD0RWEO8D1g.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_JQavlg895jU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_AC9mml3mqps.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_mjbzWcSeiwQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_ZYwfvPJv4Rk.mp4",
"activitynet/videos/v_puK4NxGKNdQ.mp4",
"activitynet/videos/v_uJ_QCxMDfag.mp4",
"activitynet/videos/v_86hyAYM5d3E.mp4",
"activitynet/videos/v_GR6Ul2pD8_Y.mp4"
] | 2
|
<answer>1</answer>
|
[
1
] | false
| 0
| 16,589.025418
| 39
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen riding into frame on a lawn mower and looking at the camera. The man speaks to the camera until two more mowers appear and he begins riding around. He gives the camera a thumbs up while still riding around and stops to look at the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZYwfvPJv4Rk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_puK4NxGKNdQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uJ_QCxMDfag.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_86hyAYM5d3E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GR6Ul2pD8_Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_A0XGYLim9IU.mp4",
"activitynet/videos/v_w7IeqGuuA7Q.mp4",
"activitynet/videos/v_6VT2jBflMAM.mp4",
"activitynet/videos/v_yVp99wxlW90.mp4",
"activitynet/videos/v_vGcH8N8sJlM.mp4"
] | 5
|
<answer>4</answer>
|
[
4
] | false
| 0
| 17,798.959397
| 40
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Four males,three teenagers and a young boy are outside in a back yard playing croquet. As the boys take turns,only one ball goes through the arch as the other ones go in the grass and over the trees. When the ball comes back,two of the boys begin to play fight with their croquet. Suddenly,another boy has a large dodge ball like item that he hits and but then it hits the peg it is the actual ball. After,the real ball is hit from various locations,such as the clubhouse and trampoline until the end where their names are shown and credits are rolled.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_A0XGYLim9IU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_w7IeqGuuA7Q.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_6VT2jBflMAM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yVp99wxlW90.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vGcH8N8sJlM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_qHRCGBIiNFg.mp4",
"activitynet/videos/v_hUynCsek8I0.mp4",
"activitynet/videos/v_TX8FGTL1flw.mp4",
"activitynet/videos/v_FEqLmpNzxdg.mp4",
"activitynet/videos/v_J8mSgO4r-kQ.mp4"
] | 1
|
<answer>4</answer>
|
[
4
] | false
| 0
| 32,363.200881
| 38
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is bending over a hole in the ice, while another is trying to pull out his pole as he has caught something. He eventually pulls a large trout fish from the hole, holding it up for the camera. The men high five in celebration.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qHRCGBIiNFg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_hUynCsek8I0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_TX8FGTL1flw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FEqLmpNzxdg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_J8mSgO4r-kQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_qiRrR2Nj2SQ.mp4",
"activitynet/videos/v_D0pVkTEYQg8.mp4",
"activitynet/videos/v_qhnWJ4G5JMA.mp4",
"activitynet/videos/v_zb6WUBWwXfk.mp4",
"activitynet/videos/v_Ck-9AHZNkq4.mp4"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 12,519.178792
| 41
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Students pedal stationary bikes in a classroom. A boy looks at a smart phone while pedaling a stationary bike, and other boys continue biking. A boy lowers his cap to cover his eyes. A girl pedals a bike while looking her smart phone.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qiRrR2Nj2SQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_D0pVkTEYQg8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qhnWJ4G5JMA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zb6WUBWwXfk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Ck-9AHZNkq4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_q6sLCLnTuik.mp4",
"activitynet/videos/v_vmUbGiOyUbU.mp4",
"activitynet/videos/v_uDmEOkAXTfo.mp4",
"activitynet/videos/v_WqnnGmL-lmU.mp4",
"activitynet/videos/v_sMITf5WBIxM.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 17,040.870529
| 42
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Clips are shown of a woman cutting a woman's hair while another speaks to the camera and he begins washing the hair. The man continues to cut and style the womans hair as he speaks to the camera with the host. He shows several different ways to style the hair and ends with the woman looking pleased.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_q6sLCLnTuik.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vmUbGiOyUbU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uDmEOkAXTfo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WqnnGmL-lmU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sMITf5WBIxM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_pLVCuSq560Y.mp4",
"activitynet/videos/v_8fZbv6OUEm8.mp4",
"activitynet/videos/v_Uc1_7BXtXZs.mp4",
"activitynet/videos/v_4_wfCFTnExI.mp4",
"activitynet/videos/v_bfk3xsTt0XA.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 15,124.295168
| 43
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are playing with a ball in the sand on the beach. A man dives for the ball and falls into the sand. The ball is shown on the sand.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_pLVCuSq560Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_8fZbv6OUEm8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Uc1_7BXtXZs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4_wfCFTnExI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bfk3xsTt0XA.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_y1IjkACdnfs.mp4",
"activitynet/videos/v_ZeBrPKBGb_k.mp4",
"activitynet/videos/v_aTQaYDmcMDY.mp4",
"activitynet/videos/v_ennVaOEePHk.mp4",
"activitynet/videos/v_ZVNRQ_MPZAs.mkv"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 36,037.562201
| 45
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are riding motocross bikes in the dirt and going off jumps. A man waves a white flag over the course.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_y1IjkACdnfs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZeBrPKBGb_k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_aTQaYDmcMDY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ennVaOEePHk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVNRQ_MPZAs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_LZEiFNEAyyw.mp4",
"activitynet/videos/v_A8dBgZCuQow.mp4",
"activitynet/videos/v_OYAyb_Ire24.mp4",
"activitynet/videos/v_1RQ27XZKU1E.mp4",
"activitynet/videos/v_2HmhRdKRVb4.mp4"
] | 2
|
<answer>1</answer>
|
[
1
] | false
| 0
| 37,200.703209
| 46
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman is seen waving to the camera and leads into her putting makeup all over her face. The woman continues putting makeup on all over her face and ends by smiling to the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LZEiFNEAyyw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_A8dBgZCuQow.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_OYAyb_Ire24.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1RQ27XZKU1E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2HmhRdKRVb4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_shBiO7aGy6k.mp4",
"activitynet/videos/v_SSoHwNbASQQ.mp4",
"activitynet/videos/v_2D22fVcAcyo.mp4",
"activitynet/videos/v__Ew3g9PXhvo.mp4",
"activitynet/videos/v_UTiSAR1o2nU.mp4"
] | 3
|
<answer>2</answer>
|
[
2
] | false
| 0
| 52,181.858492
| 44
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two kids are crossing a slack line over a blue mat. A man in a red jacket holds a microphone. A man in a gray shirt is doing tricks on a slack line. People are seen standing in front of a stage.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_shBiO7aGy6k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_SSoHwNbASQQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2D22fVcAcyo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__Ew3g9PXhvo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UTiSAR1o2nU.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_T_5ANYuDWOA.mp4",
"activitynet/videos/v_fxbEiZrQQzM.mp4",
"activitynet/videos/v_nezTU6Bq5hM.mp4",
"activitynet/videos/v_VhzPqd0Su5I.mp4",
"activitynet/videos/v_J4rzLO4u_pI.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 20,614.693651
| 47
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is kneeling down on grass. He is clipping the grass with large scissors. The man is wearing a yellow and red shirt.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_T_5ANYuDWOA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fxbEiZrQQzM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nezTU6Bq5hM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_VhzPqd0Su5I.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_J4rzLO4u_pI.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "a man is shown throwing darts at a target. The darts are all lined up in a neat row of three."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Q6KyDc24uSk.mp4",
"activitynet/videos/v_kTBEGydNpgg.mp4",
"activitynet/videos/v_3KsOJiA_uak.mp4",
"activitynet/videos/v_uBPWqgUiQWA.mp4",
"activitynet/videos/v_lVu-4SKcb4c.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 13,022.46858
| 48
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"a man is shown throwing darts at a target. The darts are all lined up in a neat row of three.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Q6KyDc24uSk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kTBEGydNpgg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3KsOJiA_uak.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uBPWqgUiQWA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lVu-4SKcb4c.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Several girls are in a big stadium on the field. One girl hits a ball with a stick she is holding. She then holds the camera while another girl hits a ball with a stick. A third girl stands at the end of the field where the balls are being hit to. The second girl to hit the ball waits for it to be thrown back to her and then attempts to hit the ball with the stick again but misses. She tries again and hits the ball this time. A girl opposite her hits the ball back. The two girls continue to hit the ball back and forth."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_mhYFpct97UE.mp4",
"activitynet/videos/v_TP8lUusp66Y.mp4",
"activitynet/videos/v_D5jLypnn6Ps.mp4",
"activitynet/videos/v_QZWyv6SShks.mp4",
"activitynet/videos/v_kl9xvnAKfdE.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 24,162.648545
| 49
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Several girls are in a big stadium on the field. One girl hits a ball with a stick she is holding. She then holds the camera while another girl hits a ball with a stick. A third girl stands at the end of the field where the balls are being hit to. The second girl to hit the ball waits for it to be thrown back to her and then attempts to hit the ball with the stick again but misses. She tries again and hits the ball this time. A girl opposite her hits the ball back. The two girls continue to hit the ball back and forth.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_mhYFpct97UE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_TP8lUusp66Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_D5jLypnn6Ps.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_QZWyv6SShks.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kl9xvnAKfdE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "We see a girl raking leaves in a yard. We then see a boy with a rake point to a tree. A large brown dog enters the room. A woman walks down the street. The boy scratches his chin. The boy is playing with his rake. We see the dog run towards the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_tMTvOaUYNeg.mp4",
"activitynet/videos/v_u-yFENQQxAo.mp4",
"activitynet/videos/v_POYg9zju63U.mp4",
"activitynet/videos/v_EvJqfGXb5Fo.mp4",
"activitynet/videos/v_7ZbH4vHTmVs.mp4"
] | 4
|
<answer>1</answer>
|
[
1
] | false
| 0
| 21,650.23519
| 51
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see a girl raking leaves in a yard. We then see a boy with a rake point to a tree. A large brown dog enters the room. A woman walks down the street. The boy scratches his chin. The boy is playing with his rake. We see the dog run towards the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tMTvOaUYNeg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_u-yFENQQxAo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_POYg9zju63U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EvJqfGXb5Fo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7ZbH4vHTmVs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is climbing up the side of a tree, then jumps down. Several people are shown doing long boarding stunts in the parking lots of a college. A boy is shown standing in his dorm before we go back to scenes of long boarding outdoors."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_nzjivjnk2Ac.mp4",
"activitynet/videos/v_NzxZdC-63LE.mp4",
"activitynet/videos/v_2FIQwmB362w.mp4",
"activitynet/videos/v_txsupdxCToQ.mp4",
"activitynet/videos/v_LElk0AlBpbI.mkv"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 29,166.774843
| 50
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is climbing up the side of a tree, then jumps down. Several people are shown doing long boarding stunts in the parking lots of a college. A boy is shown standing in his dorm before we go back to scenes of long boarding outdoors.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nzjivjnk2Ac.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_NzxZdC-63LE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2FIQwmB362w.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_txsupdxCToQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LElk0AlBpbI.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen looking to the camera while holding a violin. The man then begins playing the instrument while the camera zooms in on his fingers. The man continues to play and stops to speak to the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Ue90f5r-2Qw.mp4",
"activitynet/videos/v_zRNS_ebpi7o.mp4",
"activitynet/videos/v_993xtlhuVII.mp4",
"activitynet/videos/v_bCEdkW675dQ.mp4",
"activitynet/videos/v_z-iuSgXKUcw.mp4"
] | 3
|
<answer>1</answer>
|
[
1
] | false
| 0
| 14,548.622225
| 53
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen looking to the camera while holding a violin. The man then begins playing the instrument while the camera zooms in on his fingers. The man continues to play and stops to speak to the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Ue90f5r-2Qw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zRNS_ebpi7o.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_993xtlhuVII.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bCEdkW675dQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z-iuSgXKUcw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "The young man with headphones is pushing the grass cutter, while the man in gray sweater is guiding him. Young man in gray sweater is holding the other boys back as they go through the grass. The man with headphones is drinking from a cup as the young man in gray sweater have him a back hug."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Rq1MoqtH8fM.mkv",
"activitynet/videos/v_l4C-l6XeNRc.mp4",
"activitynet/videos/v_9wRQsxVFwkE.mp4",
"activitynet/videos/v_yE5whKJ-DE4.mp4",
"activitynet/videos/v_EQajiMQAW74.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 25,058.727454
| 52
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The young man with headphones is pushing the grass cutter, while the man in gray sweater is guiding him. Young man in gray sweater is holding the other boys back as they go through the grass. The man with headphones is drinking from a cup as the young man in gray sweater have him a back hug.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Rq1MoqtH8fM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_l4C-l6XeNRc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9wRQsxVFwkE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yE5whKJ-DE4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EQajiMQAW74.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man introduces a video about how he will assemble a new bike he just got. He unpacks the bike from the bow that it came in and removes the plastic. Be begins by attaching the handlebars to the bike. Then he attaches the front and back wheels to the bike. Someone rides off on the bike and the video ends with the closing credits."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_4XTJzFjjFp0.mp4",
"activitynet/videos/v_PCoxnf59j5U.mp4",
"activitynet/videos/v_4sm-tTbfamM.mp4",
"activitynet/videos/v_Boa880LnJ3w.mp4",
"activitynet/videos/v_swbCsf51XVg.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 15,968.016574
| 54
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man introduces a video about how he will assemble a new bike he just got. He unpacks the bike from the bow that it came in and removes the plastic. Be begins by attaching the handlebars to the bike. Then he attaches the front and back wheels to the bike. Someone rides off on the bike and the video ends with the closing credits.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4XTJzFjjFp0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_PCoxnf59j5U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4sm-tTbfamM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Boa880LnJ3w.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_swbCsf51XVg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People in wheel chairs dance with people standing in a studio. All the people in wheelchairs do circles around the dancers."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_K2Pws9z20Do.mp4",
"activitynet/videos/v_vL8Hy6lcnF8.mp4",
"activitynet/videos/v_LkUnT9fMIXc.mp4",
"activitynet/videos/v_Nn-KZMYbOv4.mp4",
"activitynet/videos/v_7toItxBIVtk.mkv"
] | 1
|
<answer>2</answer>
|
[
2
] | false
| 0
| 21,317.189877
| 55
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People in wheel chairs dance with people standing in a studio. All the people in wheelchairs do circles around the dancers.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_K2Pws9z20Do.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vL8Hy6lcnF8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LkUnT9fMIXc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Nn-KZMYbOv4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7toItxBIVtk.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two men are seen standing around an enclosed room and begin hitting a ball around. The men continue hitting the ball around the room while looking through the glass and are mainly seen standing around and talking."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_qI1ZayfiGHI.mp4",
"activitynet/videos/v_FYhB2rQwfCc.mp4",
"activitynet/videos/v_IiCN1md2MV4.mp4",
"activitynet/videos/v_8inrvRctXQ0.mp4",
"activitynet/videos/v_Ix8WFQ6-yx8.mp4"
] | 1
|
<answer>1</answer>
|
[
1
] | true
| 1
| 22,802.50422
| 56
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two men are seen standing around an enclosed room and begin hitting a ball around. The men continue hitting the ball around the room while looking through the glass and are mainly seen standing around and talking.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qI1ZayfiGHI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FYhB2rQwfCc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_IiCN1md2MV4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_8inrvRctXQ0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Ix8WFQ6-yx8.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A band is on a stage together. A man is holding a violin and inspecting it. Several people watch him as they talk about the violin."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_0YHCiC7IIg8.mp4",
"activitynet/videos/v_cZZM3bgmXE4.mp4",
"activitynet/videos/v_z-ttrQ38mOc.mp4",
"activitynet/videos/v_V3LvKGRzkeg.mp4",
"activitynet/videos/v_zRNS_ebpi7o.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 18,816.395263
| 57
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A band is on a stage together. A man is holding a violin and inspecting it. Several people watch him as they talk about the violin.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_0YHCiC7IIg8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cZZM3bgmXE4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z-ttrQ38mOc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_V3LvKGRzkeg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zRNS_ebpi7o.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "The badminton players are playing at the badminton court. On one net, there are four player playing, on the other net there are two player playing. The players chase the shuttlecock and hit it with their racket."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_f6j6lb0AaxM.mp4",
"activitynet/videos/v_qXD7myRvw0M.mp4",
"activitynet/videos/v_Z0eBz6QsI-c.mp4",
"activitynet/videos/v_FfYNkePtHjo.mp4",
"activitynet/videos/v_cyXWvxVt8qE.mp4"
] | 2
|
<answer>4</answer>
|
[
4
] | false
| 0
| 12,752.768734
| 59
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The badminton players are playing at the badminton court. On one net, there are four player playing, on the other net there are two player playing. The players chase the shuttlecock and hit it with their racket.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_f6j6lb0AaxM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qXD7myRvw0M.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Z0eBz6QsI-c.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FfYNkePtHjo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cyXWvxVt8qE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "The credits of the clip are shown. A guy is removing the skin off a pumpkin. The guy sits and discusses. The guy is carving unique face on the surface of pumpkins. The guy looks in a mirror while he mimics punching himself. The guy wraps white toilet paper on a pumpkin carving. A guy takes a picture of his carving."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_waFqh-Qkafc.mp4",
"activitynet/videos/v_z3xkE5Ox-2A.mp4",
"activitynet/videos/v_9svdYGBSMvM.mp4",
"activitynet/videos/v_cQYAi2drreo.mp4",
"activitynet/videos/v_tJ2xOG_EWOg.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 20,047.530611
| 58
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The credits of the clip are shown. A guy is removing the skin off a pumpkin. The guy sits and discusses. The guy is carving unique face on the surface of pumpkins. The guy looks in a mirror while he mimics punching himself. The guy wraps white toilet paper on a pumpkin carving. A guy takes a picture of his carving.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_waFqh-Qkafc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z3xkE5Ox-2A.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9svdYGBSMvM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cQYAi2drreo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tJ2xOG_EWOg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "There are some girls wearing karate uniforms doing karate on a stage. There's an orange belt and a yellow belt karate student doing some karate moves with batons in their hands. After they leave, another karate student wearing a yellow belt comes on stage to perform her karate moves with a baton. Then she leaves and another girl wearing an orange belt joins in holding two hammers to show her karate moves. She leaves and another girl wearing a yellow belt comes on stage with a hand fan and shows her karate moves. After she leaves the master comes on stage along with three other students. They take turns to smash the board held by the master. Then the master leaves and the three students demonstrate their coordinated karate moves."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_1B3XsffrM4M.mp4",
"activitynet/videos/v_dySzHZniFCo.mp4",
"activitynet/videos/v_75xhANnCOEg.mp4",
"activitynet/videos/v_saB1t3Znhk0.mp4",
"activitynet/videos/v_wGEaIInAtT4.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 14,950.507848
| 61
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"There are some girls wearing karate uniforms doing karate on a stage. There's an orange belt and a yellow belt karate student doing some karate moves with batons in their hands. After they leave, another karate student wearing a yellow belt comes on stage to perform her karate moves with a baton. Then she leaves and another girl wearing an orange belt joins in holding two hammers to show her karate moves. She leaves and another girl wearing a yellow belt comes on stage with a hand fan and shows her karate moves. After she leaves the master comes on stage along with three other students. They take turns to smash the board held by the master. Then the master leaves and the three students demonstrate their coordinated karate moves.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1B3XsffrM4M.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_dySzHZniFCo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_75xhANnCOEg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_saB1t3Znhk0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_wGEaIInAtT4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Scenes of different teams playing in a beach soccer tournament. Clips of the tourists in the beach town and spectators lining the beach sideline. More clips of some soccer play and beach scenes including stills of a dog sleeping on the beach and kids playing in the surf. A picture of one of the winning teams with their medals."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_zQVUXbyCV1o.mp4",
"activitynet/videos/v_vvk6f13VO5c.mkv",
"activitynet/videos/v_5JlwYD_GChY.mp4",
"activitynet/videos/v_q92zSoMudWU.mp4",
"activitynet/videos/v_pLVCuSq560Y.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 22,763.821869
| 60
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Scenes of different teams playing in a beach soccer tournament. Clips of the tourists in the beach town and spectators lining the beach sideline. More clips of some soccer play and beach scenes including stills of a dog sleeping on the beach and kids playing in the surf. A picture of one of the winning teams with their medals.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_zQVUXbyCV1o.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vvk6f13VO5c.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_5JlwYD_GChY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_q92zSoMudWU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_pLVCuSq560Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are in the river in a boat rushing downstream as the water splashes them. A mountain panorama is displayed onscreen. The 6 people row vigorously. We see them from the riverbed looking across, farm building in the background. A woman talks to the camera. They take group selfies on dry land. People jump from a rock into the river. A man talks to the camera. A man points out the directions to other riders. Another woman talks to the camera. Food is being cooked for the party and plated to the attendees."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_OabVylOVys4.mp4",
"activitynet/videos/v_gKLbdLKEG6U.mp4",
"activitynet/videos/v_PrR-kkpy1c8.mp4",
"activitynet/videos/v_LDIemY9nO-4.mkv",
"activitynet/videos/v_jQHGyqk21GI.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 23,648.544278
| 62
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are in the river in a boat rushing downstream as the water splashes them. A mountain panorama is displayed onscreen. The 6 people row vigorously. We see them from the riverbed looking across, farm building in the background. A woman talks to the camera. They take group selfies on dry land. People jump from a rock into the river. A man talks to the camera. A man points out the directions to other riders. Another woman talks to the camera. Food is being cooked for the party and plated to the attendees.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_OabVylOVys4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_gKLbdLKEG6U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_PrR-kkpy1c8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LDIemY9nO-4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_jQHGyqk21GI.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen paying pool on a table and pausing to point to the balls and table. Several people watch him on the side while he demonstrates how to shoot and ends by shooting several balls at once and cheering."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_fjN9Qe237bw.mp4",
"activitynet/videos/v_PRT0Z9HPF4U.mp4",
"activitynet/videos/v_Zw4illqWzFI.mp4",
"activitynet/videos/v_spZ_RrpyNJw.mkv",
"activitynet/videos/v_afqUOlnLHX0.mp4"
] | 5
|
<answer>1</answer>
|
[
1
] | false
| 0
| 20,116.968474
| 64
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen paying pool on a table and pausing to point to the balls and table. Several people watch him on the side while he demonstrates how to shoot and ends by shooting several balls at once and cheering.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fjN9Qe237bw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_PRT0Z9HPF4U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Zw4illqWzFI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_spZ_RrpyNJw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_afqUOlnLHX0.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person is seen putting three small children on a camel while a woman stands in front and the kids wave. The woman leads the camel around with the kids as they wave to the camera and let the kids off when they return back. The camera comes back to the kids as they walk away from the area."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_i49blayQ93Q.mp4",
"activitynet/videos/v_rO9SwC42Goo.mp4",
"activitynet/videos/v__jxpaVW4_cE.mp4",
"activitynet/videos/v_JZN0L8pp5hY.mp4",
"activitynet/videos/v_lq20hEghHtU.mp4"
] | 3
|
<answer>2</answer>
|
[
2
] | false
| 0
| 20,117.529091
| 63
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person is seen putting three small children on a camel while a woman stands in front and the kids wave. The woman leads the camel around with the kids as they wave to the camera and let the kids off when they return back. The camera comes back to the kids as they walk away from the area.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_i49blayQ93Q.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_rO9SwC42Goo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__jxpaVW4_cE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_JZN0L8pp5hY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lq20hEghHtU.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A group of children race dirt bikes over a series of rolling hills several times. A group of children race, ride, and jump over hilly race courses surrounded by trees and buildings. A group of children descend from a hill behind a gated start place in a professional race. Several more races are shown with the children traversing the same kinds of hilly obstacles on the race trail."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_W6JJ1L_EEBY.mp4",
"activitynet/videos/v_I6B4g85H2iI.mp4",
"activitynet/videos/v_l4UJiGsZVfE.mp4",
"activitynet/videos/v_mFDC1CLt6B4.mp4",
"activitynet/videos/v_UqSjGwxBuqA.mp4"
] | 3
|
<answer>1</answer>
|
[
1
] | false
| 0
| 16,176.025816
| 65
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A group of children race dirt bikes over a series of rolling hills several times. A group of children race, ride, and jump over hilly race courses surrounded by trees and buildings. A group of children descend from a hill behind a gated start place in a professional race. Several more races are shown with the children traversing the same kinds of hilly obstacles on the race trail.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_W6JJ1L_EEBY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_I6B4g85H2iI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_l4UJiGsZVfE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_mFDC1CLt6B4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UqSjGwxBuqA.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person is seek walking around knitting and leads into a woman hosting a news segment. Many people are seen running around while knitting and leads into a clip of a man playing an instrument in a street corner."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Nqh3RtLRleU.mp4",
"activitynet/videos/v_WxlJBRUU1A0.mp4",
"activitynet/videos/v_kGvs0Nv5zJo.mp4",
"activitynet/videos/v_9GYLUAFgCXE.mp4",
"activitynet/videos/v_ncXZIWMNKZQ.mp4"
] | 1
|
<answer>5</answer>
|
[
5
] | false
| 0
| 23,120.025262
| 66
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person is seek walking around knitting and leads into a woman hosting a news segment. Many people are seen running around while knitting and leads into a clip of a man playing an instrument in a street corner.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Nqh3RtLRleU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WxlJBRUU1A0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kGvs0Nv5zJo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9GYLUAFgCXE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ncXZIWMNKZQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "We see antique opening title screen. We see men in rock climbing gear talking about climbing. We see the man in the black shirt start climbing the rock. The two men then begin to talk. The man in black climbs the rock wall then down again. We see the closing screens."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_Pr6zL1ToSC4.mp4",
"activitynet/videos/v_at8e-jBBU5E.mp4",
"activitynet/videos/v_UALnEw4XhTY.mp4",
"activitynet/videos/v_ClW3USojCoE.mp4",
"activitynet/videos/v_6Yn2U58qxPs.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 27,645.684405
| 67
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see antique opening title screen. We see men in rock climbing gear talking about climbing. We see the man in the black shirt start climbing the rock. The two men then begin to talk. The man in black climbs the rock wall then down again. We see the closing screens.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Pr6zL1ToSC4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_at8e-jBBU5E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UALnEw4XhTY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ClW3USojCoE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_6Yn2U58qxPs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man tries to stop a man from shooting a basket ball. The ball is passed across the room and men chase it across the court. A boy catches and tosses the ball behind him which is caught by another boy on his team. The boy runs and shoots the ball to score."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_bOBQLGfEeyg.mp4",
"activitynet/videos/v_L21zcZlFfIY.mp4",
"activitynet/videos/v_3hZjxdMcG6o.mp4",
"activitynet/videos/v_DvIng_zQPyY.mp4",
"activitynet/videos/v_Vh4TxFOCNM8.mp4"
] | 3
|
<answer>4</answer>
|
[
4
] | false
| 0
| 21,102.371259
| 68
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man tries to stop a man from shooting a basket ball. The ball is passed across the room and men chase it across the court. A boy catches and tosses the ball behind him which is caught by another boy on his team. The boy runs and shoots the ball to score.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_bOBQLGfEeyg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_L21zcZlFfIY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3hZjxdMcG6o.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_DvIng_zQPyY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Vh4TxFOCNM8.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman in white shirt is brushing the fur of the brown dog as the blow dry bows on top of its head. A woman in white shirt is brushing the white dog's fur while the blow dry blows on its head while in the back, a woman is trimming the light brown dog's fur. A woman in black shirt and another woman in white hold a white poodle and check its ears."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_IfKGdI5egKc.mp4",
"activitynet/videos/v_MmOVjM5-D-U.mp4",
"activitynet/videos/v_uG_hgODoDes.mp4",
"activitynet/videos/v_DEduSDgovOQ.mp4",
"activitynet/videos/v_vgdcVhRSa9E.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 17,878.228532
| 69
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman in white shirt is brushing the fur of the brown dog as the blow dry bows on top of its head. A woman in white shirt is brushing the white dog's fur while the blow dry blows on its head while in the back, a woman is trimming the light brown dog's fur. A woman in black shirt and another woman in white hold a white poodle and check its ears.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_IfKGdI5egKc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_MmOVjM5-D-U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uG_hgODoDes.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_DEduSDgovOQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vgdcVhRSa9E.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A gym is shown and a large crowd of students is watching a person doing flips and throwing her baton over the floor. As the routine continues,she does doing splits and throwing the baton up in the air. The girl then moves to the other side of the gym and grabs fire sticks and the people in the crowd stand up in an uproar cheering for her."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_RzFqIN5hWJQ.mp4",
"activitynet/videos/v_GfiqDJA-qqU.mp4",
"activitynet/videos/v_iL5abexk3vQ.mp4",
"activitynet/videos/v_xftFhOCEqFs.mp4",
"activitynet/videos/v_UYe6JGaUZzg.mp4"
] | 3
|
<answer>5</answer>
|
[
5
] | false
| 0
| 18,002.406463
| 70
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A gym is shown and a large crowd of students is watching a person doing flips and throwing her baton over the floor. As the routine continues,she does doing splits and throwing the baton up in the air. The girl then moves to the other side of the gym and grabs fire sticks and the people in the crowd stand up in an uproar cheering for her.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_RzFqIN5hWJQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GfiqDJA-qqU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iL5abexk3vQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_xftFhOCEqFs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UYe6JGaUZzg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man sitting on a bucket by some snow drinks a beer. He speaks to the camera. He puts down his beer and grabs a fishing pole and begins to fish. He holds the fishing pole string."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_gdYr4E3qobI.mp4",
"activitynet/videos/v_tBGeBbO8gh0.mp4",
"activitynet/videos/v_7RESODKApso.mp4",
"activitynet/videos/v_FEqLmpNzxdg.mp4",
"activitynet/videos/v_7-jcXxwqf5E.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 24,519.27797
| 71
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man sitting on a bucket by some snow drinks a beer. He speaks to the camera. He puts down his beer and grabs a fishing pole and begins to fish. He holds the fishing pole string.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_gdYr4E3qobI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tBGeBbO8gh0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7RESODKApso.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_FEqLmpNzxdg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7-jcXxwqf5E.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman wearing black clothes is talking in front of an all white screen, she tilts her head from side to side then holds up a small bottle. The woman then applies water to her face, then pours contents from the little bottle onto her hands and she begins to rub it all over her face using her fingers. The woman speaks and then rinses her face off and then dries her face with a towel. When the woman's face is all dried she continues to talk."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_mbB7UFoTwpo.mp4",
"activitynet/videos/v_y9kk0ptXevk.mp4",
"activitynet/videos/v_vSV7arHrH5k.mp4",
"activitynet/videos/v_uhiQp0GCeKg.mp4",
"activitynet/videos/v_ffUtqOyJ7fM.mp4"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 20,171.080304
| 73
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman wearing black clothes is talking in front of an all white screen, she tilts her head from side to side then holds up a small bottle. The woman then applies water to her face, then pours contents from the little bottle onto her hands and she begins to rub it all over her face using her fingers. The woman speaks and then rinses her face off and then dries her face with a towel. When the woman's face is all dried she continues to talk.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_mbB7UFoTwpo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_y9kk0ptXevk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vSV7arHrH5k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_uhiQp0GCeKg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ffUtqOyJ7fM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A gymnast stands on his arms. Then, the gymnast performs pommel horse while spinning his body. A person behind the pommel horse takes pictures to the gymnast. After, the gymnast stands on his hands, turn and jumps to land on the mat, then walks. A man walks holding a paper and pen."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_lc-piYwzqsA.mp4",
"activitynet/videos/v_3JHIcli-Wlg.mp4",
"activitynet/videos/v_qkk2tK19sx8.mp4",
"activitynet/videos/v_4KE6dUAGZ94.mp4",
"activitynet/videos/v_cKMGacBQX0E.mp4"
] | 3
|
<answer>5</answer>
|
[
5
] | false
| 0
| 25,475.294069
| 72
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A gymnast stands on his arms. Then, the gymnast performs pommel horse while spinning his body. A person behind the pommel horse takes pictures to the gymnast. After, the gymnast stands on his hands, turn and jumps to land on the mat, then walks. A man walks holding a paper and pen.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lc-piYwzqsA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3JHIcli-Wlg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_qkk2tK19sx8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4KE6dUAGZ94.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_cKMGacBQX0E.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A close up of lemonade is shown followed by a man standing behind a bar speaking to the camera with various ingredients. The man then pours several liquids out into a glass, shakes it up, and then pours it into a glass with a lemon on top. The man finishes by still speaking to the camera and presenting a picture of his drink."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_UnOzWl0EGCA.mp4",
"activitynet/videos/v_yjazHd6a5SQ.mkv",
"activitynet/videos/v_rXwSSTGmvb8.mp4",
"activitynet/videos/v_vgXU0u-rN9c.mp4",
"activitynet/videos/v_7NG6UrY2Foo.mp4"
] | 2
|
<answer>1</answer>
|
[
1
] | false
| 0
| 15,514.944078
| 74
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A close up of lemonade is shown followed by a man standing behind a bar speaking to the camera with various ingredients. The man then pours several liquids out into a glass, shakes it up, and then pours it into a glass with a lemon on top. The man finishes by still speaking to the camera and presenting a picture of his drink.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_UnOzWl0EGCA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_yjazHd6a5SQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_rXwSSTGmvb8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_vgXU0u-rN9c.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7NG6UrY2Foo.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two men are kickboxing inside a building. One man holds up a block as the other is kicking and punching. He then turns, and another man kicks and punches at the blocks."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_HwTSF0VgmMU.mp4",
"activitynet/videos/v_sZRUTtoxY_s.mp4",
"activitynet/videos/v_2nPrH4Tv0yc.mp4",
"activitynet/videos/v_jdz4PzF1pO0.mp4",
"activitynet/videos/v_fWD0rL_72nw.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 10,588.535218
| 75
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two men are kickboxing inside a building. One man holds up a block as the other is kicking and punching. He then turns, and another man kicks and punches at the blocks.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HwTSF0VgmMU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sZRUTtoxY_s.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2nPrH4Tv0yc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_jdz4PzF1pO0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fWD0rL_72nw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A crowd watches a man leap into a large tunnel. Someone gives a thumbs up. Another man leaps into the large tunnel. A third man leaps into the tunnel. A fourth man leaps into the tunnel. A fifth man leaps into the tunnel with his arms flared open. A sixth man leaps into the tunnel."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_nKn2uQTVo-U.mp4",
"activitynet/videos/v_Z47QGlaQ1NE.mp4",
"activitynet/videos/v_koEfnIoZB_4.mp4",
"activitynet/videos/v_ZOQSDsJYXIA.mp4",
"activitynet/videos/v_45gAK3x_0ds.mp4"
] | 3
|
<answer>5</answer>
|
[
5
] | false
| 0
| 19,716.678367
| 76
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A crowd watches a man leap into a large tunnel. Someone gives a thumbs up. Another man leaps into the large tunnel. A third man leaps into the tunnel. A fourth man leaps into the tunnel. A fifth man leaps into the tunnel with his arms flared open. A sixth man leaps into the tunnel.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nKn2uQTVo-U.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Z47QGlaQ1NE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_koEfnIoZB_4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZOQSDsJYXIA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_45gAK3x_0ds.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "An illustrated egg, the website "startcooking com" and "Vegetable Salad" are shown on screen. Ingredients for the recipe are shown. A person starts preparing the recipe by chopping vegetables. The finished salad is shown from above."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_ux_qqONPSrc.mp4",
"activitynet/videos/v_sf2zGT5nN04.mp4",
"activitynet/videos/v_75cjK13ylJM.mp4",
"activitynet/videos/v_LoBjzA2z2Ls.mp4",
"activitynet/videos/v_Nt6cha3hK_s.mp4"
] | 1
|
<answer>5</answer>
|
[
5
] | false
| 0
| 19,550.615256
| 77
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"An illustrated egg, the website \"startcooking com\" and \"Vegetable Salad\" are shown on screen. Ingredients for the recipe are shown. A person starts preparing the recipe by chopping vegetables. The finished salad is shown from above.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ux_qqONPSrc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sf2zGT5nN04.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_75cjK13ylJM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LoBjzA2z2Ls.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Nt6cha3hK_s.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A fast motion video shows a picture on a pumpkin and leads into a person cutting open a pumpkin. The persons scoops out the pumpkin and place the picture in front, tracing the outline of the picture onto the pumpkin. The person then cuts out the outline, turns off the lights, and shows off the end results."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_-FWGLSfI13Q.mp4",
"activitynet/videos/v_z3xkE5Ox-2A.mp4",
"activitynet/videos/v_ZVIi4lPU6h0.mp4",
"activitynet/videos/v_1y2aqd5HQlU.mp4",
"activitynet/videos/v_O_L0CSZ7nnA.mp4"
] | 5
|
<answer>5</answer>
|
[
5
] | true
| 1
| 22,873.516066
| 78
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A fast motion video shows a picture on a pumpkin and leads into a person cutting open a pumpkin. The persons scoops out the pumpkin and place the picture in front, tracing the outline of the picture onto the pumpkin. The person then cuts out the outline, turns off the lights, and shows off the end results.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_-FWGLSfI13Q.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z3xkE5Ox-2A.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZVIi4lPU6h0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1y2aqd5HQlU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_O_L0CSZ7nnA.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen speaking to the camera while holding a bottle of lotion and then spread it throughout a woman's hair. He then brushes the hair and blow dries it while styling it into a certain look. He finishes the cut and dry and the woman sees herself in the mirror."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_TlDh_RZ3HDk.mp4",
"activitynet/videos/v_R_YZNqP1gSE.mp4",
"activitynet/videos/v_X82bc2v5kcM.mp4",
"activitynet/videos/v_Y8-7fr5bv24.mp4",
"activitynet/videos/v_oobYvNJU5ko.mp4"
] | 3
|
<answer>1</answer>
|
[
1
] | false
| 0
| 18,133.800828
| 79
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen speaking to the camera while holding a bottle of lotion and then spread it throughout a woman's hair. He then brushes the hair and blow dries it while styling it into a certain look. He finishes the cut and dry and the woman sees herself in the mirror.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_TlDh_RZ3HDk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_R_YZNqP1gSE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_X82bc2v5kcM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Y8-7fr5bv24.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_oobYvNJU5ko.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "People are sitting inside of a raft going over large bumps in the water. The raft tips over and the people fall out several times."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_K3sJnHGHQHM.mp4",
"activitynet/videos/v_z1QgzOfUjow.mp4",
"activitynet/videos/v_2rHsoF35eQw.mp4",
"activitynet/videos/v_Snj5CuEUbPI.mp4",
"activitynet/videos/v_WpKQV53ENHE.mkv"
] | 3
|
<answer>4</answer>
|
[
4
] | false
| 0
| 18,530.408973
| 80
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"People are sitting inside of a raft going over large bumps in the water. The raft tips over and the people fall out several times.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_K3sJnHGHQHM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_z1QgzOfUjow.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2rHsoF35eQw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Snj5CuEUbPI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WpKQV53ENHE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man and woman are seen hosting a segment and leads into several shots of a soccer match. The video continues with more shots of team mates cheering and playing soccer and ends with the hosts speaking to the camera again."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_STAvUAslEYM.mp4",
"activitynet/videos/v_QWqEi91fWOQ.mp4",
"activitynet/videos/v__Wag6CT_0j8.mp4",
"activitynet/videos/v_GlJ4DvArV6Q.mp4",
"activitynet/videos/v_VFqkLp5mzBM.mp4"
] | 1
|
<answer>1</answer>
|
[
1
] | true
| 1
| 17,058.232071
| 81
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man and woman are seen hosting a segment and leads into several shots of a soccer match. The video continues with more shots of team mates cheering and playing soccer and ends with the hosts speaking to the camera again.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_STAvUAslEYM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_QWqEi91fWOQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__Wag6CT_0j8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GlJ4DvArV6Q.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_VFqkLp5mzBM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A young woman is standing in front of a brick wall and speaking to the camera. She applies mascara to her eyes and is talking throughout. She applies make up to both of her eyes while still looking into the camera. She then applies cover up makeup to her face. She then goes back to her eyes to apply eyeliner and continues speaking into the camera. She finishes by applying lipstick, giving instructions throughout."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_fZQS02Ypca4.mp4",
"activitynet/videos/v_A8dBgZCuQow.mp4",
"activitynet/videos/v_0gf3AgK1YLY.mp4",
"activitynet/videos/v_LZEiFNEAyyw.mp4",
"activitynet/videos/v_v2zVnmbPmeQ.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 12,015.050397
| 82
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A young woman is standing in front of a brick wall and speaking to the camera. She applies mascara to her eyes and is talking throughout. She applies make up to both of her eyes while still looking into the camera. She then applies cover up makeup to her face. She then goes back to her eyes to apply eyeliner and continues speaking into the camera. She finishes by applying lipstick, giving instructions throughout.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fZQS02Ypca4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_A8dBgZCuQow.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_0gf3AgK1YLY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LZEiFNEAyyw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_v2zVnmbPmeQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A few boys stand around doing different things in a locker room. One boy kicks and spins around showing off his martial art skills."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_kW4ajodPtWU.mp4",
"activitynet/videos/v_saB1t3Znhk0.mp4",
"activitynet/videos/v_Z_YXWLkRmjQ.mp4",
"activitynet/videos/v_AFtFitXAFks.mp4",
"activitynet/videos/v_J_CJSmMFWlg.mp4"
] | 3
|
<answer>2</answer>
|
[
2
] | false
| 0
| 13,216.029915
| 83
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A few boys stand around doing different things in a locker room. One boy kicks and spins around showing off his martial art skills.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kW4ajodPtWU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_saB1t3Znhk0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Z_YXWLkRmjQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_AFtFitXAFks.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_J_CJSmMFWlg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A young child is seen sitting on a bar with another girl showing her teeth to the camera. The girl opens the box to take an object out while the young girl laughs to the camera. The girl continues taking items out of the box while the girl looks and laughs."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_0nPeqy-DA2E.mp4",
"activitynet/videos/v_8uV6u0QcTSs.mp4",
"activitynet/videos/v_F51cKkjt6tk.mp4",
"activitynet/videos/v_69DNcmkoapw.mp4",
"activitynet/videos/v_ZMTi498qnPc.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 13,580.052901
| 85
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A young child is seen sitting on a bar with another girl showing her teeth to the camera. The girl opens the box to take an object out while the young girl laughs to the camera. The girl continues taking items out of the box while the girl looks and laughs.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_0nPeqy-DA2E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_8uV6u0QcTSs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_F51cKkjt6tk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_69DNcmkoapw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZMTi498qnPc.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person is snowboarding down a hill of snow. A man is in the snow with no shirt on. A man has a bandanna on his face and no shirt on snowboarding down a hill."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_lQUqzLT7bl0.mkv",
"activitynet/videos/v_jF33TElZc_Y.mp4",
"activitynet/videos/v_ShKrNPaSdhY.mkv",
"activitynet/videos/v_nuaTROuaZPY.mp4",
"activitynet/videos/v_7H5oYHs7EJw.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 27,056.435724
| 84
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person is snowboarding down a hill of snow. A man is in the snow with no shirt on. A man has a bandanna on his face and no shirt on snowboarding down a hill.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lQUqzLT7bl0.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_jF33TElZc_Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ShKrNPaSdhY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nuaTROuaZPY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7H5oYHs7EJw.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A large group of people are seen walking down a sidewalk holding various signs and objects and skipping down the street. More people appear hoping down the street and ends with one final man looking at the camera."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_1517CiM5c0A.mp4",
"activitynet/videos/v_2ooY3GqZieg.mkv",
"activitynet/videos/v_HdZjxdQhtZo.mp4",
"activitynet/videos/v_9GYLUAFgCXE.mp4",
"activitynet/videos/v_fdd5ixvEXOE.mp4"
] | 5
|
<answer>4</answer>
|
[
4
] | false
| 0
| 21,780.936712
| 86
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A large group of people are seen walking down a sidewalk holding various signs and objects and skipping down the street. More people appear hoping down the street and ends with one final man looking at the camera.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_1517CiM5c0A.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2ooY3GqZieg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HdZjxdQhtZo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9GYLUAFgCXE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fdd5ixvEXOE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A woman paints the lower part of a gate with a hose while carrying on her back a backpack Sprayer. Then, the woman paints the upper part of the gate. After,the woman continues painting the lower part of the gate."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_HpJ2pr0ykqo.mp4",
"activitynet/videos/v_HgKZ4KAuhdI.mp4",
"activitynet/videos/v__8Zk9dfBgPg.mp4",
"activitynet/videos/v_Wzg4d-3ym1E.mp4",
"activitynet/videos/v_GGv0sCOf_tM.mp4"
] | 1
|
<answer>6</answer>
|
[] | false
| 0
| 23,775.6365
| 87
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A woman paints the lower part of a gate with a hose while carrying on her back a backpack Sprayer. Then, the woman paints the upper part of the gate. After,the woman continues painting the lower part of the gate.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HpJ2pr0ykqo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HgKZ4KAuhdI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__8Zk9dfBgPg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Wzg4d-3ym1E.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_GGv0sCOf_tM.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two people are boxing on a mat. A man in a white shirt is lifting his knee up to hit another man. They stop boxing and separate."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_LmioUbGNv04.mp4",
"activitynet/videos/v_fgoXpih2Kws.mp4",
"activitynet/videos/v_lneRTkBTPwg.mp4",
"activitynet/videos/v_g49F9coR2VU.mp4",
"activitynet/videos/v_CjoAnld43C4.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 12,316.718028
| 89
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two people are boxing on a mat. A man in a white shirt is lifting his knee up to hit another man. They stop boxing and separate.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_LmioUbGNv04.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_fgoXpih2Kws.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_lneRTkBTPwg.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_g49F9coR2VU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CjoAnld43C4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person is seen sitting behind a set of bongo drums and speaking to people off in the distance. The men then plays on the drums while stopping to speak and continuing to play."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_oRtMsdNQ1LE.mkv",
"activitynet/videos/v_EbGq9gXcXLQ.mp4",
"activitynet/videos/v_tN1_lOJlUlc.mkv",
"activitynet/videos/v_jYyN-nJcm0M.mp4",
"activitynet/videos/v_O_fdvOxYqiY.mp4"
] | 5
|
<answer>2</answer>
|
[
2
] | false
| 0
| 20,540.266734
| 88
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person is seen sitting behind a set of bongo drums and speaking to people off in the distance. The men then plays on the drums while stopping to speak and continuing to play.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_oRtMsdNQ1LE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_EbGq9gXcXLQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_tN1_lOJlUlc.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_jYyN-nJcm0M.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_O_fdvOxYqiY.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man is seen standing in the woods holding an ax and walking closer to a log. The man steps on the log a bit followed by him swinging the ax on the log."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_QnQ2D-tJ9pM.mp4",
"activitynet/videos/v_ZpyCrs-q-so.mp4",
"activitynet/videos/v_7QxUtHqQdbY.mp4",
"activitynet/videos/v_Kkkrap77n5M.mp4",
"activitynet/videos/v_2-S2fehRKVc.mp4"
] | 3
|
<answer>3</answer>
|
[
3
] | true
| 1
| 14,760.204618
| 91
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man is seen standing in the woods holding an ax and walking closer to a log. The man steps on the log a bit followed by him swinging the ax on the log.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_QnQ2D-tJ9pM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ZpyCrs-q-so.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_7QxUtHqQdbY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Kkkrap77n5M.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2-S2fehRKVc.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "We see the title screen on black. We see images of men in uniforms in various locations. A lady is washing a bike. A girl holds up the start card. The men start after the card and ride their dirt bikes. The lady with the hose is seen again. A man falls off his bike hard. The bike washing and other ladies appear. We see fireworks going off in the air. We see the winner throwing hands in the air and giving high five to each other. The end titles appear on a black screen."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_ieWgalZPc2g.mp4",
"activitynet/videos/v_K8XNOs0AwaE.mp4",
"activitynet/videos/v_RHpigjSwhVM.mp4",
"activitynet/videos/v_eXMF6Skt2To.mp4",
"activitynet/videos/v_my9Z4bun_Dk.mp4"
] | 4
|
<answer>2</answer>
|
[
2
] | false
| 0
| 23,227.363102
| 90
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"We see the title screen on black. We see images of men in uniforms in various locations. A lady is washing a bike. A girl holds up the start card. The men start after the card and ride their dirt bikes. The lady with the hose is seen again. A man falls off his bike hard. The bike washing and other ladies appear. We see fireworks going off in the air. We see the winner throwing hands in the air and giving high five to each other. The end titles appear on a black screen.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ieWgalZPc2g.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_K8XNOs0AwaE.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_RHpigjSwhVM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_eXMF6Skt2To.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_my9Z4bun_Dk.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Two teams play ice jockey and a man fell on the ice, then men help to stand the player. The players hit each other hard and push and the red team score, then the team jumps. Other teams play ice jockey and a man get injured, then the team play and win. A man talks on front a microphone. two team play and a man fall on the ice, then teams continue playing."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_oD0RWEO8D1g.mp4",
"activitynet/videos/v_pqVWGi0d4RU.mp4",
"activitynet/videos/v_WJfMz7joX4s.mp4",
"activitynet/videos/v_9FYVaOGQV6o.mp4",
"activitynet/videos/v_-_gDSRlC1kg.mp4"
] | 2
|
<answer>2</answer>
|
[
2
] | true
| 1
| 20,107.32679
| 92
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Two teams play ice jockey and a man fell on the ice, then men help to stand the player. The players hit each other hard and push and the red team score, then the team jumps. Other teams play ice jockey and a man get injured, then the team play and win. A man talks on front a microphone. two team play and a man fall on the ice, then teams continue playing.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_oD0RWEO8D1g.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_pqVWGi0d4RU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WJfMz7joX4s.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9FYVaOGQV6o.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_-_gDSRlC1kg.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A man plays hurling and serves a ball with a stick. The man throws the ball in the air and immediately hit the ball with the stick. The man throws the ball in the air, then swing his body to hit the ball with the stick."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_2q_4I3ae0J4.mp4",
"activitynet/videos/v_a4-5QFOiAiw.mp4",
"activitynet/videos/v_V9LudLaWGOM.mkv",
"activitynet/videos/v_WtNvqSFTgxI.mp4",
"activitynet/videos/v_V4cYhOQ6Pfs.mp4"
] | 1
|
<answer>1</answer>
|
[
1
] | true
| 1
| 15,283.295387
| 93
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A man plays hurling and serves a ball with a stick. The man throws the ball in the air and immediately hit the ball with the stick. The man throws the ball in the air, then swing his body to hit the ball with the stick.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2q_4I3ae0J4.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_a4-5QFOiAiw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_V9LudLaWGOM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_WtNvqSFTgxI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_V4cYhOQ6Pfs.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "The video takes place in a kitchen. A clip of a woman applying wallpaper is shown. The woman then begins speaking to the camera. The woman begins demonstrating how to remodel a kitchen. She soon applies wallpaper while speaking to the camera. The woman then places the final touches of the remodel, such as covering outlets and putting plates on the table. The video ends with the camera showing the newly remodeled kitchen."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_-OLPVREPy6Y.mp4",
"activitynet/videos/v_2vAaAy_WC7Y.mp4",
"activitynet/videos/v_RPr1ZbIGLwU.mp4",
"activitynet/videos/v_9VRLj4IfUzY.mp4",
"activitynet/videos/v_sRN_crwj3B4.mp4"
] | 5
|
<answer>1</answer>
|
[
1
] | false
| 0
| 16,495.479639
| 94
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"The video takes place in a kitchen. A clip of a woman applying wallpaper is shown. The woman then begins speaking to the camera. The woman begins demonstrating how to remodel a kitchen. She soon applies wallpaper while speaking to the camera. The woman then places the final touches of the remodel, such as covering outlets and putting plates on the table. The video ends with the camera showing the newly remodeled kitchen.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_-OLPVREPy6Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_2vAaAy_WC7Y.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_RPr1ZbIGLwU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_9VRLj4IfUzY.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_sRN_crwj3B4.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A shot of scenery is shown followed by a man walking on the rope. Several more people are seen walking on the rope on the sunset. More people take their turns walking on the rope."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v__4LZrf1GL1s.mp4",
"activitynet/videos/v_3qkNnr1_78I.mp4",
"activitynet/videos/v_73AGD3RWPEw.mp4",
"activitynet/videos/v__Ew3g9PXhvo.mp4",
"activitynet/videos/v_iddZ6YIWLWc.mp4"
] | 4
|
<answer>4</answer>
|
[
4
] | true
| 1
| 19,294.14761
| 96
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A shot of scenery is shown followed by a man walking on the rope. Several more people are seen walking on the rope on the sunset. More people take their turns walking on the rope.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__4LZrf1GL1s.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_3qkNnr1_78I.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_73AGD3RWPEw.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v__Ew3g9PXhvo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_iddZ6YIWLWc.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "men are wearing together a costume and a man is helping them. man is wearing headphones talking in a microphonr. other men are wearing the same costume and are wresting on a red carpet and men are helping them. men are watching them around the carpet."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_mKm75VWThAI.mp4",
"activitynet/videos/v_4lxS8OJRsa8.mp4",
"activitynet/videos/v_ywsH9kD033I.mp4",
"activitynet/videos/v_kXvFkU7gQSM.mp4",
"activitynet/videos/v_nB0JECwGK0c.mp4"
] | 5
|
<answer>1</answer>
|
[
1
] | false
| 0
| 27,731.372477
| 95
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"men are wearing together a costume and a man is helping them. man is wearing headphones talking in a microphonr. other men are wearing the same costume and are wresting on a red carpet and men are helping them. men are watching them around the carpet.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_mKm75VWThAI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_4lxS8OJRsa8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_ywsH9kD033I.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kXvFkU7gQSM.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_nB0JECwGK0c.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A lady gives a man a piece of paper. The man fills a white bowl with food. The man slides the bowl towards the lady."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_HHG1kCydLYU.mp4",
"activitynet/videos/v_kj8L5yu-fGs.mp4",
"activitynet/videos/v_h3thb-S-3L8.mp4",
"activitynet/videos/v_Xc70KHd4zhI.mp4",
"activitynet/videos/v_YrdpvaBDDlE.mp4"
] | 4
|
<answer>3</answer>
|
[
3
] | false
| 0
| 21,320.415925
| 97
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A lady gives a man a piece of paper. The man fills a white bowl with food. The man slides the bowl towards the lady.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_HHG1kCydLYU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_kj8L5yu-fGs.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_h3thb-S-3L8.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Xc70KHd4zhI.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_YrdpvaBDDlE.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "A person is drawing on a sweet potato. They fill a basket with hair products. She rips out pages from a music book."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_I4y6q9oIIQo.mp4",
"activitynet/videos/v_wcmO0R3Kqzo.mp4",
"activitynet/videos/v_juiMCvZUYwk.mp4",
"activitynet/videos/v_Hhc10CrukfA.mp4",
"activitynet/videos/v_P6Z-7k-erfc.mp4"
] | 3
|
<answer>5</answer>
|
[
5
] | false
| 0
| 14,776.236729
| 98
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"A person is drawing on a sweet potato. They fill a basket with hair products. She rips out pages from a music book.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_I4y6q9oIIQo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_wcmO0R3Kqzo.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_juiMCvZUYwk.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Hhc10CrukfA.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_P6Z-7k-erfc.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.
System Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.
Decision rules (concise):
- Judge relevance ONLY from what is visible in the frames.
- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.
- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.
ABSOLUTE OUTPUT CONTRACT:
<answer> [a] > [b] > [c] > [d] > [e] </answer>
Constraints:
- Do NOT use per-candidate XML tags.
- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.
- Always output a total order in <answer>.
Query: "Several shots are shown of people performing jump roping tricks on a large stage in front of an audience. The people do several jumps and tricks with each other as well as by themselves."
Candidates:
[1] video:<video>
[2] video:<video>
[3] video:<video>
[4] video:<video>
[5] video:<video>
|
[
"activitynet/videos/v_K3Z3z8t-RIQ.mp4",
"activitynet/videos/v_shBiO7aGy6k.mp4",
"activitynet/videos/v_Amgt0yzQido.mp4",
"activitynet/videos/v_-lEsnrNNZFU.mp4",
"activitynet/videos/v_CBW_uJJpmZY.mp4"
] | 1
|
<answer>2</answer>
|
[
2
] | false
| 0
| 15,623.346826
| 100
|
[
{
"role": "user",
"content": [
{
"type": "text",
"text": "You will receive a Query and N candidates. Each candidate is a video. Your task is to identify the most relevant video to the Query. Output only the index of the most relevant video among the candidates. Your answer should be strictly inside <answer></answer> tags.\n\nSystem Prompt: You are RankLLM, a vision-only reranker. You will receive a Query and N candidates. Each candidate is a video described via frames.\n\nDecision rules (concise):\n- Judge relevance ONLY from what is visible in the frames.\n- Down-rank clear mismatches (wrong domain/scene/action). Consider temporal coherence.\n- Tie-breakers (in order): action visibility/close-up > temporal coherence > low occlusion/clutter > overall coverage.\n\nABSOLUTE OUTPUT CONTRACT:\n\n<answer> [a] > [b] > [c] > [d] > [e] </answer>\n\n\nConstraints:\n- Do NOT use per-candidate XML tags.\n- a,b,c,d,e are indices of the candidates. you should output the number in the place of a,b,c,d,e.\n- Always output a total order in <answer>.\n\nQuery: \"Several shots are shown of people performing jump roping tricks on a large stage in front of an audience. The people do several jumps and tricks with each other as well as by themselves.\"\n\nCandidates:\n[1] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_K3Z3z8t-RIQ.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[2] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_shBiO7aGy6k.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[3] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_Amgt0yzQido.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[4] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_-lEsnrNNZFU.mp4",
"nframes": 48,
"total_pixels": 50176
}
},
{
"type": "text",
"text": "\n[5] video:",
"video_url": null
},
{
"type": "video_url",
"text": null,
"video_url": {
"url": "file:///hub_data3/seohyun/activitynet/videos/v_CBW_uJJpmZY.mp4",
"nframes": 48,
"total_pixels": 50176
}
}
]
}
] |
Subsets and Splits
No community queries yet
The top public SQL queries from the community will appear here once available.