Video-Retrieval-Dataset
Collection
4 items
•
Updated
messages
listlengths 2
2
| videos
listlengths 5
5
|
|---|---|
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man explains and demonstrates how to use exercise equipment, showcasing his technique and results.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video features a person using a NordicTrack exercise machine, focusing on its features and showing the person using the equipment. Although it demonstrates how to use the equipment, it focuses more on features and brand rather than technique or results.\n[2] The video shows a person wearing stilts or jumping shoes in an outdoor park setting, walking or engaging in a physical activity. The focus is on the activity rather than specific exercise equipment technique.\n[3] The video displays a man seated and lying down on an exercise bench, explaining techniques for using the bench. He is mostly talking and occasionally demonstrates exercises, which is relevant to explaining and demonstrating exercise equipment.\n[4] The video focuses on a man in a gym showing how to use various exercise machines, clearly demonstrating techniques and possibly discussing results, fitting the query perfectly.\n[5] The video is about a man explaining and demonstrating the use of vacuum cleaning equipment indoors, which is irrelevant to exercise equipment.\n</content>\n\n<contrast>\n- [4] ranks higher than [1] because the focus is on gym equipment specifically, with visible demonstration and potential technique explanation, whereas [1] is more brand-focused.\n- [3] ranks higher than [1] due to clearer demonstrations and verbal explanations of technique by an individual on the exercise bench.\n- [1] ranks higher than [2] because it shows exercise equipment, whereas [2] focuses on physical activity not tied to equipment use/explanation.\n- [2] ranks higher than [5] because it relates more to physical activity even if not equipment-focused, whereas [5] is unrelated to exercise.\n</contrast>\n\n<summary>\n1st=[4] (clear demonstration of exercise equipment use and technique)\n2nd=[3] (verbal explanation and demonstration of exercise techniques)\n3rd=[1] (demonstrates equipment use but focused more on brand)\n4th=[2] (shows physical activity but not focused on exercise equipment)\n5th=[5] (unrelated to exercise equipment)\n</summary>\n</think>\n<answer> [4] > [3] > [1] > [2] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_NzRNlTfyYtI.mp4",
"activitynet/videos/v_NLTd7qCLT7o.mp4",
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_AuVL_nkYXw0.mp4",
"activitynet/videos/v_C1TWr5XH8b0.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people play an exciting game of beach volleyball, with the match culminating in a victory for the team featuring a man and a woman.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This sequence involves an indoor futsal match, showing players from two opposing teams (one in red, the other in yellow) competing on a blue court with a focus on action near the goal and celebrations.\n[2] The footage displays a beach volleyball game with several women playing. It shows the game in progress, but there's no clear indication of victory or involvement of a mixed-gender team.\n[3] The frames depict a beach soccer setup with a group of people. It includes shots of a sandy court and close-ups, but lacks a focus on volleyball or a mixed-gender climax.\n[4] This sequence captures a casual game of beach volleyball near the water, played by two men. The action appears relaxed, with no definitive competitive elements visible.\n[5] The video shows a mixed-gender team playing beach volleyball. It culminates with celebratory actions, suggesting a possible victory fitting the query's requirement of a team with a man and a woman being involved in an exciting game and winning.\n\n</content>\n<contrast>\n- [5] is better than [2] because it features a mixed-gender team playing beach volleyball with clear celebratory actions suggesting a victory, whereas [2] shows only women playing without clear victory indicators.\n- [2] is preferred over [4] due to [2]'s more competitive setup and clearer beach volleyball context, while [4] appears more casual and unclear.\n- [4] beats [1] because it is at least on a beach with a volleyball net, while [1] is about indoor futsal, which is irrelevant.\n- [1] is ranked higher than [3] as futsal may be a closer sport context than beach soccer, even though both lack direct relevance.\n- [3] is the least relevant with no connection to volleyball, focusing on beach soccer content.\n\n</contrast>\n<summary>\n1st=[5] Mixed-gender team plays and seems to win beach volleyball, fulfilling the query.\n2nd=[2] Women playing beach volleyball, lacks mixed-gender element and clear victory.\n3rd=[4] Casual beach volleyball between men, lacks mixed gender and competitive climax.\n4th=[1] Indoor futsal with no volleyball content, irrelevant sport.\n5th=[3] Beach soccer, irrelevant to volleyball query context.\n\n</summary>\n</think>\n<answer> [5] > [2] > [4] > [1] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_XxMzH75Bhr8.mp4",
"activitynet/videos/v_FC5FsugGt8o.mp4",
"activitynet/videos/v_XD3yFrJHiv8.mp4",
"activitynet/videos/v_ymEh5T11kSQ.mp4",
"activitynet/videos/v_SLPD1U5iDjY.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Several people take turns performing impressive kicks and tricks in the center of a circle while an enthusiastic crowd watches and reacts from the sidelines.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] A group of people in orange shirts are on a field, possibly engaged in a sports activity, but there are no visible kicks or tricks. The focus is more on people standing or walking, with a calm setting and spectators in the background.\n\n[2] People in costumes are on an indoor sports field, participating in what appears to be a humorous or entertaining event. The crowd is lively, but the activities do not clearly center on kicking or tricks.\n\n[3] A sumo wrestling match is taking place with a large audience watching. The action involves wrestling rather than kicking or tricks, and it does not fit the query of kicks and tricks in a circle.\n\n[4] Several individuals are performing martial arts or dance-like movements in a circle, surrounded by a crowd. The focus is on physical tricks and kicks performed in the center, while the audience watches and reacts enthusiastically.\n\n[5] Rodeo activities are shown, with horse riding and cattle events. The focus here is on rodeo-style competitions, not on kicks or tricks performed by people in a circle.\n</content>\n\n<contrast>\n- [4] is the best match as it clearly shows people performing kicks and tricks within a circle, with an engaged crowd responding from the sidelines.\n- [1] is less relevant as it shows a calm sports-like setting without kicking or tricks.\n- [2] involves a performance with a crowd but lacks the specific kicking or trick actions.\n- [3] is focused on wrestling, which does not match the described activity of performing tricks in a circle.\n- [5] displays rodeo activities, which do not involve the type of kicks and tricks described in the query.\n</contrast>\n\n<summary>\n1st=[4] (People perform tricks and kicks in a circle with audience engagement)\n2nd=[2] (Costumed event with a crowd, lacks the specific kicking/tricks)\n3rd=[1] (Sports-like setting without kicks and tricks)\n4th=[3] (Wrestling action, not trick performance)\n5th=[5] (Rodeo activities focus, not on kicks/tricks)\n</summary>\n</think>\n<answer> [4] > [2] > [1] > [3] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_0jBwj0bfZ3Y.mp4",
"activitynet/videos/v_hK3E6njydQA.mp4",
"activitynet/videos/v_slUvIngXl4g.mp4",
"activitynet/videos/v_AkeJ-lJLNkw.mp4",
"activitynet/videos/v_w9cJ3FNGw_U.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people work together to move and spread mulch and dirt in a yard using shovels, rakes, a wheelbarrow, and a small tractor.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] A person is chopping wood using an axe in a yard, with wood pieces and a wheelbarrow nearby. There is no evidence of mulch, dirt, or group activity with different tools.\n[2] Children are playing outdoors, hitting a hanging piñata. This is unrelated to the query about yard work with tools.\n[3] A toddler is playing with a lacrosse stick on a wooden deck. There is no evidence of yard work or people working with tools.\n[4] People are working in a yard spreading mulch with rakes, shovels, a wheelbarrow, and a small tractor visible. This closely matches the query description of collaborative yard work.\n[5] People are chopping wood with axes and carrying logs. There is no evidence of spreading mulch or dirt with multiple tools.\n</content>\n\n<contrast>\n- [4] contains multiple people and tools used in spreading mulch, aligning with the yard work context, whereas [1] and [5] involve wood chopping.\n- [2] features children playing with a piñata, unrelated to yard work, while [4] shows active yard maintenance.\n- [3] is unrelated, showing a toddler playing rather than any yard work activities, while [4] involves the specified yard work activities.\n</contrast>\n\n<summary>\n1st=[4] (Matches the query with people spreading mulch using shovels, rakes, a wheelbarrow, and a small tractor)\n2nd=[1] (Involves yard work but limited to wood chopping and lacks group and tool diversity)\n3rd=[5] (Similar yard setting but focused on wood chopping, not mulch spreading)\n4th=[3] (Contains a child playing with a stick, unrelated to the query)\n5th=[2] (Involves a piñata, unrelated to yard work)\n</summary>\n</think>\n<answer> [4] > [1] > [5] > [3] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_b2uAgV5n3FU.mp4",
"activitynet/videos/v_3HP2E_a9xrU.mp4",
"activitynet/videos/v_CG-7jcSB5_c.mp4",
"activitynet/videos/v_FhWxgGQtCJY.mp4",
"activitynet/videos/v_yiFKPKXevOU.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two boys play soccer and pass a ball to each other on a busy beach as people walk by and enjoy the water.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows children swimming and playing on a beach but does not feature soccer or a ball being passed.\n[2] This video depicts two boys on a beach passing a ball to each other, fitting the query description well. There is visible beach activity in the background.\n[3] The video shows a professional beach soccer match setting with organized teams and a crowd, which does not align with the recreational and informal query requirement.\n[4] The video focuses mainly on beach volleyball with no evidence of soccer or two boys playing individually. The scene appears crowded with beachgoers.\n[5] The video shows a beach volleyball game with no sign of a soccer ball or two boys playing soccer. It captures a casual beach environment with some activity in the background.\n</content>\n\n<contrast>\n- [2] fits the query because it shows two boys playing with a ball on a beach, whereas [1] shows no ballplay.\n- [2] is more relevant than [3] because it features casual play instead of a professional setting.\n- [2] is superior to [4] and [5] which focus on volleyball and lack the described soccer activity.\n</contrast>\n\n<summary>\n1st=[2] (features two boys passing a ball on a beach, fits query well)\n2nd=[1] (shows children on a beach, but no soccer activity)\n3rd=[3] (professional beach soccer but not the informal play described)\n4th=[4] (features beach volleyball, not soccer)\n5th=[5] (focused on volleyball, lacks soccer element)\n</summary>\n</think>\n<answer> [2] > [1] > [3] > [4] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_tQmsDeu1d6M.mp4",
"activitynet/videos/v_ymEh5T11kSQ.mp4",
"activitynet/videos/v_09MaNbzc2TA.mp4",
"activitynet/videos/v_KNpeiKm3xyM.mp4",
"activitynet/videos/v_SLPD1U5iDjY.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man stands on a roof, speaks briefly, and proceeds to repair the roof by removing, organizing, and replacing tiles and wooden parts.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video focuses on interior work, involving people in a room laying floor tiles. There are several sequences displaying the process of placing and setting these tiles. The actions are tile-centric, not related to roofing.\n\n[2] This video shows a man on a roof, as per the query. It starts with him standing and presumably speaking, followed by the removal and organization of roof tiles. The man is involved in direct roof repair work, aligning closely with the query.\n\n[3] The video captures a sequence of a person working on a roof installing a vent pipe. There's a focus on sealing and adjusting the vent roof component. However, it doesn't involve organizing or replacing tiles or parts.\n\n[4] This video displays a person performing maintenance on a sloped roof. The person appears to be checking or fixing something on the roof's edge, but the specific actions of removing, organizing, or replacing tiles or wooden parts are not clear.\n\n[5] The video shows a man applying plaster or paint on a wall indoors. The actions are related to wall finishing and have no association with roofing activities or the sequence requested in the query.\n</content>\n\n<contrast>\n- [2] is preferred over [3] because it clearly shows roof repair involving tile removal and organization, which matches the query best, whereas [3] focuses on a vent installation without tile work.\n- [2] is preferred over [4] because [2] demonstrates clear actions of tile removal and reorganization, whereas [4] shows general roof maintenance without clarity on tile work.\n- [4] beats [3] as the actions occur on a roof, offering some relation, though indirect, to the query, whereas [3] is more specialized on vent installation.\n- [1] and [5] are ranked lower because they involve activities completely unrelated to roofing (tile flooring and wall plastering, respectively).\n</contrast>\n\n<summary>\n1st=[2] Demonstrates roof work with tile removal and replacement.\n2nd=[4] Shows a man on a roof with some maintenance activity.\n3rd=[3] Involves roof work but focuses on vent pipe adjustments.\n4th=[1] Entirely focused on indoor tile flooring work.\n5th=[5] Displays wall plastering, unrelated to roofing.\n</summary>\n</think>\n<answer> [2] > [4] > [3] > [1] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_fVg3StD8LL0.mp4",
"activitynet/videos/v_6sorAV7KJxA.mp4",
"activitynet/videos/v_mCdKLZGnKxk.mp4",
"activitynet/videos/v_fljxcvQe_Mo.mp4",
"activitynet/videos/v_MZ4yIxM6snw.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man enjoys an exhilarating water skiing experience, skillfully maneuvering across the water while others watch from a nearby boat.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a man water skiing skillfully on a lake, with a noticeable wake trail. Occasionally, other people appear on a boat watching the activity. This directly matches the query of a man water skiing while being observed.\n\n[2] This sequence features a mix of activities, primarily water skiing. There are dynamic shots of a person water skiing with impressive maneuvers, but there is no visible interaction with spectators from a boat, which is a part of the query.\n\n[3] The video depicts whitewater kayaking through rapids, with scenes of individuals navigating the water. This does not relate to water skiing or the presence of observers on a boat.\n\n[4] This sequence is about surfing, where a person rides waves on a surfboard. It does not include water skiing or boat watchers, making it irrelevant to the query.\n\n[5] The video consists of snow tubing on a slope, showing people enjoying sliding down the snow. There is no water skiing or presence of spectators on a boat, making it unrelated to the query.\n</content>\n<contrast>\n- [1] is ranked higher than [2] because it showcases water skiing with spectators from a boat, aligning perfectly with the query, whereas [2] lacks the spectator aspect.\n- [2] is ranked higher than [4] as it features water skiing, though lacks boat spectators, which is closer to the query than surfing.\n- [4] is ranked higher than [3] because surfing is more related to water activities than kayaking through rapids, which do not fit the query.\n- [3] is ranked higher than [5] because whitewater kayaking is more closely related to aquatic sports than snow tubing, which is not related to the query.\n</contrast>\n<summary>\n1st=[1] (full match to query: water skiing with spectators on a boat)\n2nd=[2] (water skiing without boat spectators)\n3rd=[4] (related as an aquatic sport: surfing)\n4th=[3] (aquatic sport: kayaking, less relevant)\n5th=[5] (unrelated activity: snow tubing)\n</summary>\n</think>\n<answer> [1] > [2] > [4] > [3] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_-5KAycAQlC4.mp4",
"activitynet/videos/v_G3TPqsLNlrw.mp4",
"activitynet/videos/v__3lgJ6yp7o8.mp4",
"activitynet/videos/v_9ZGy24Geu5k.mp4",
"activitynet/videos/v_6TgVNz6PATk.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man demonstrates how to change a tire tube by removing the old one, inserting a new tube, and inflating it.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The images depict a snowy environment where a person is clearing snow from a car, indicative of weather-related maintenance but unrelated to tire tube changing.\n[2] This series shows a person starting a fire using sticks and paper, an action unrelated to changing a tire tube.\n[3] These images display individuals working on a large vehicle's wheel, possibly removing and replacing parts. It appears relevant to tire maintenance but not specific to tube changing.\n[4] Shows a person using stilts in a park setting, unrelated to tire tube changing.\n[5] Clearly demonstrates a man changing a bicycle tire tube, including removing the old tube, inserting a new one, and inflating it, matching the query exactly.\n</content>\n\n<contrast>\n- [5] is ranked highest because it explicitly shows step-by-step tire tube changing.\n- [3] displays wheel-related work but lacks clear tube replacement, whereas [5] does.\n- [1] involves automotive maintenance but not tire-related, whereas [5] does.\n- [2] and [4] are unrelated to tire tube changing; therefore, [3] is prioritized over these despite lesser accuracy than [5].\n- [2] and [4], both unrelated, show outdoor activities with [2] involving fire and [4] stilt walking, which do not involve any wheel or tire activity.\n</contrast>\n\n<summary>\n1st=[5] (Explicitly matches tire tube changing with clear actions)\n2nd=[3] (Involves wheel-related repair but not as clear on tube change)\n3rd=[1] (Involves car maintenance but unrelated to tube changing)\n4th=[2] (Fire lighting activity, unrelated)\n5th=[4] (Stilt walking activity, unrelated)\n</summary>\n</think>\n<answer> [5] > [3] > [1] > [2] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_3UbQ0UDmbbw.mp4",
"activitynet/videos/v_K-kJ-0nkKZk.mp4",
"activitynet/videos/v_YoJxVl_hUWg.mp4",
"activitynet/videos/v_NLTd7qCLT7o.mp4",
"activitynet/videos/v_C_bwHYiX-Vw.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"The video showcases various athletes participating in shotput competitions, taking turns to throw while spectators observe from the sidelines.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video shows athletes participating in javelin competitions. The frames display competitors taking turns to throw the javelin, with distances marked and spectators in the stands.\n[2] The video captures a group of individuals standing on a field, possibly engaging in casual or practice activities. The setup doesn’t suggest any competitive sporting event.\n[3] This video aligns with the query. It shows athletes in an indoor arena participating specifically in shotput competitions. Several athletes take turns, and measures or judges are visible in the background.\n[4] The video is about a men’s triple jump competition. It focuses on athletes performing jumps, with event details displayed prominently.\n[5] The video depicts a historical athletic event focusing on a triple jump competition. Athletes are seen preparing and executing jumps with spectators in the stadium.\n\n</content>\n\n<contrast>\n- [3] features shotput events clearly and matches the query, whereas [1] showcases javelin, a different event.\n- [3] displays shotput actions indoors in a competition, whereas [2] shows casual field activity with no clear shotput event.\n- [3] directly involves shotput with detailed action sequences, whereas [4] focuses on triple jump, unrelated to shotput.\n- [3] centers on shotput competitions; [5] is focused on triple jump, which differs from the query topic.\n\n</contrast>\n\n<summary>\n1st=[3] (Includes shotput events with athletes competing and detailed sequences that match the query)\n2nd=[1] (Displays athletes but in javelin events, not shotput)\n3rd=[4] (Covers a triple jump competition, unrelated but with a competition setup)\n4th=[5] (Similarly engages in a triple jump rather than shotput)\n5th=[2] (Shows a generic field scene with no competitive event indication)\n\n</summary>\n</think>\n<answer> [3] > [1] > [4] > [5] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_sO7ZGxFwbm8.mp4",
"activitynet/videos/v_0jBwj0bfZ3Y.mp4",
"activitynet/videos/v_hniQpwn3Ob4.mp4",
"activitynet/videos/v_cwQQj3VZLC8.mp4",
"activitynet/videos/v_tnXjdv_GM9g.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people prepare for and enjoy a snowboarding adventure in a snowy mountain range, traveling by helicopter to the mountaintop and capturing their experience on camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This sequence is about BMX biking indoors on a dirt track with riders competing, showcasing jumps and stunts. It doesn't relate to the snowboarding adventure theme.\n\n[2] The video depicts a winter sports event with snowboarding and skiing at a snowy location. There are competitors and spectators, but no visible helicopter or mountain travel.\n\n[3] This sequence shows a person painting various designs, unrelated to snowboarding or outdoor adventure.\n\n[4] The video captures a person waterskiing behind a boat, unrelated to a snowy mountain adventure or snowboarding.\n\n[5] This sequence shows a snowy mountain range with people preparing and possibly engaging in snow sports. It includes wide shots of the mountains and individuals in snowboarding gear, fitting the query well.\n\n</content>\n\n<contrast>\n- [5] includes snowy mountains, preparing individuals, and scenes coherent with the snowboarding adventure, whereas [2] lacks travel by helicopter and full preparation context.\n- [2] features winter sports but shows more of a competitive event atmosphere, whereas [5] aligns more with the leisurely, adventurous essence of the query.\n- [1] involves BMX biking which is unrelated to snowboarding, lacking the snow and mountain environment.\n- [3] and [4] are completely off-topic, focusing on painting and waterskiing respectively.\n- [5] beats [2] because it better encompasses the adventurous preparation aspect of the query.\n- [2] has snow sports visuals, but with a sports competition focus, unlike [5].\n- [4] captures water-based action, standing far from the snowy mountain theme.\n- [3] provides an indoor painting process, irrelevant to outdoor snowboarding.\n \n</contrast>\n\n<summary>\n1st=[5] (Best visual alignment with snowy mountain adventure and preparation)\n2nd=[2] (Shows snow sports but leans towards competition rather than adventure)\n3rd=[1] (BMX biking, unrelated to snowboarding)\n4th=[4] (Waterskiing, unrelated to the query's theme)\n5th=[3] (Painting, completely off-topic from snowboarding adventure)\n</summary>\n</think>\n<answer> [5] > [2] > [1] > [4] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_Vfb3LmFDols.mp4",
"activitynet/videos/v_FNB1BMEtIvw.mp4",
"activitynet/videos/v_N_zbcVs419E.mp4",
"activitynet/videos/v_G5mKcPzVMG4.mp4",
"activitynet/videos/v_Lr0Vm9zBXKE.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man and woman host a talk show from a studio, discussing and watching video clips featuring men playing outdoor soccer in a city setting.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a man and woman hosting a talk show in a studio setting. They are sitting on a couch, discussing sports-related topics. The video also shows clips of men playing soccer on a sandy outdoor city setting, which aligns closely with the query description.\n\n[2] The video captures two men in a backyard setting playing croquet. This does not match the query about hosting a talk show and soccer in a city setting.\n\n[3] The video involves a man and a woman discussing car-related topics within a studio and outdoor environments. It involves cars and driving, which do not relate to the query focused on soccer and talk shows.\n\n[4] This video features a cooking show with a chef and a woman demonstrating cooking techniques in a kitchen. It is unrelated to the query about soccer or a talk show.\n\n[5] The video presents a tutorial or entertainment segment on \"How to Win Rock, Paper, Scissors.\" It features a man and woman, but they aren't hosting a talk show or discussing soccer.\n</content>\n\n<contrast>\n- [1] is most relevant because it features a talk show setting and includes video clips of outdoor soccer, matching the query directly, whereas [2], [3], [4], and [5] do not involve soccer or talk show discussions of soccer.\n- [2] focuses on croquet in a backyard, whereas [1] has a clear focus on soccer clips relevant to the query.\n- [3] involves car discussions and activities, whereas [1]'s soccer theme aligns with the query.\n- [4] is about cooking, with no relationship to soccer or a talk show format, unlike [1].\n- [5] shows a game tutorial, lacking any soccer or talk show elements that [1] includes.\n</contrast>\n\n<summary>\n1st=[1] (Direct match with query: talk show and soccer clips.)\n2nd=[3] (Studio setup discussion, but unrelated topic.)\n3rd=[5] (Interaction of a man and woman with a minor talk show element.)\n4th=[2] (Features an outdoor game but not soccer or a city setting.)\n5th=[4] (Least relevant; focused on cooking, no link to soccer or talk shows.)\n</summary>\n</think>\n<answer> [1] > [3] > [5] > [2] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_XD3yFrJHiv8.mp4",
"activitynet/videos/v_eypKc4FyZ2s.mp4",
"activitynet/videos/v_PZjWkB_q2lE.mp4",
"activitynet/videos/v_xZdCmghMcvU.mp4",
"activitynet/videos/v_AnRYS02tvRA.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man demonstrates the step-by-step process of fixing a car tire onto a wheel rim, including the necessary tools and techniques for assembly, tightening, and checking tire pressure.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video appears to show a man working on a bicycle wheel, possibly assembling the tire. Tools and steps involving a bicycle tire are visible, suggesting a demonstration on this topic. However, it focuses on a bicycle, not a car.\n\n[2] The sequence shows a man on a workout bench, possibly demonstrating an exercise routine. This content is unrelated to fixing a car tire.\n\n[3] The video depicts a man in a garage setting, with cars and tires visible. There appears to be a discussion on tire-related topics, but not a detailed step-by-step tire mounting process.\n\n[4] This sequence shows a man working with a car tire and rim. A variety of tools are displayed, and there are steps showing the tire being mounted on the rim, tightening, and adjustments, aligning closely with the query.\n\n[5] The video depicts people working on a vehicle wheel, involving tools and some steps are unclear due to the outdoor setting and less focus on the tire-rim assembly. Though it involves a tire, it lacks the clarity and step-by-step demonstration shown in [4].\n</content>\n\n<contrast>\n- [4] closely matches the query with clear step-by-step instructions using tools on a car tire, whereas [3] lacks specific assembly details.\n- [3] has relevant car and tire content, but focuses more on tire information rather than hands-on assembly.\n- [5] involves a car tire but lacks clarity in demonstrating specific techniques or a systematic process as seen in [4].\n- [1] shows a detailed step-by-step process but is about a bicycle tire, not a car, whereas [4] directly addresses car tires.\n- [2] is unrelated as it involves exercise demonstration, not tire fixing.\n</contrast>\n\n<summary>\n1st=[4] (detailed step-by-step process with tools on a car tire)\n2nd=[3] (relevant car tire information, lacks assembly specifics)\n3rd=[5] (some related activity with a car tire, less clear process)\n4th=[1] (detailed process but focuses on bicycle tire)\n5th=[2] (unrelated to tire fixing, focuses on exercises)\n</summary>\n</think>\n<answer> [4] > [3] > [5] > [1] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_C_bwHYiX-Vw.mp4",
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_9ddD5Ob93J0.mp4",
"activitynet/videos/v_4r0qYLCucEI.mp4",
"activitynet/videos/v_YoJxVl_hUWg.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Scuba divers explore the ocean, observing various fish and a shark while interacting with the camera both on a boat and underwater.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video shows windsurfing activities. The sequence includes people windsurfing on the ocean and interacting with the camera onboard a boat. It lacks any underwater scenes or interaction with marine life typical for scuba diving.\n\n[2] This video includes sequences of scuba diving with scenes underwater featuring fish and divers. There are views from a boat and interaction underwater, aligning with the query of scuba divers exploring the ocean and observing marine life.\n\n[3] This video primarily features scuba diving and underwater exploration. Divers can be seen entering the water from a boat, and there are scenes of marine life, including jellyfish and other underwater elements. However, there is no interaction with a shark visible.\n\n[4] The video is a scuba diving adventure, with scenes of divers underwater observing various fish, including a shark. There are both above-water and underwater interactions which closely match the query.\n\n[5] This video takes place in a swimming pool with people practicing swimming techniques. There is no ocean exploration or marine life interaction.\n\n</content>\n\n<contrast>\n- [4] aligns strongly with the query because it involves scuba divers, marine life including a shark, and both boat and underwater interactions; whereas [2] lacks a clear shark interaction.\n- [2] is relevant with its underwater exploration and fish observation, whereas [3] lacks the shark but shows divers entering from a boat.\n- [3] involves scuba divers and underwater scenes, but there is no clear interaction with a shark, unlike [4].\n- [1] involves windsurfing, completely unrelated to scuba diving or marine life exploration.\n- [5] occurs in a swimming pool, unrelated to oceanic or marine life exploration.\n\n</contrast>\n\n<summary>\n1st=[4] (includes scuba diving, marine life, shark presence, boat/underwater interaction)\n2nd=[2] (scuba diving and marine life exploration, no shark)\n3rd=[3] (scuba diving and underwater, no clear shark)\n4th=[1] (windsurfing, unrelated to marine life exploration)\n5th=[5] (pool swimming, unrelated to ocean exploration)\n\n</summary>\n</think>\n<answer> [4] > [2] > [3] > [1] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_AhWkUdag6NA.mp4",
"activitynet/videos/v_PT18KK_6jmU.mp4",
"activitynet/videos/v_hpU50i4WBK8.mp4",
"activitynet/videos/v_LrwBGQ9B0Vg.mp4",
"activitynet/videos/v_XC6tvSBS0PA.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A young boy performs an energetic drum solo, playing both the drums and cymbals.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a person in traditional attire performing with drums. There is no young boy visible. The setting is outdoors with traditional elements, but it does not match the query specifics.\n\n[2] The video features a person, not a young boy, playing a drum set indoors. The focus is on the drums, but the performer does not match the age specified in the query.\n\n[3] This video includes multiple performers, but none appear to be a young boy. There is a focus on drums, but the context involves additional instruments, which does not match the query closely.\n\n[4] The video depicts a foosball tournament, unrelated to a drum performance. No musical instruments or young boys are visible, making it irrelevant to the query.\n\n[5] The video shows a young boy energetically playing a drum kit, including cymbals. The setting is indoors, with close-ups on the performance. It is highly relevant to the query, as it captures the action and specifics requested.\n</content>\n\n<contrast>\n- [5] is highly relevant because it depicts a young boy playing drums and cymbals energetically, matching the query directly.\n- [2] shows a drum performance but by an adult, whereas [5] features a young performer as specified.\n- [3] includes drums but involves multiple performers and instruments, lacking the focus on a young boy.\n- [1] involves drumming but not by a young boy, whereas [5] matches the age and action specifics.\n- [4] is unrelated, focusing on a foosball game, whereas [5] perfectly depicts the query.\n</contrast>\n\n<summary>\n1st=[5] (perfect match: young boy energetically playing drums and cymbals)\n2nd=[2] (involves drums but not a young boy)\n3rd=[3] (features drums but lacks focus on a single young performer)\n4th=[1] (involves drumming but not by a young boy)\n5th=[4] (unrelated content)\n</summary>\n</think>\n<answer> [5] > [2] > [3] > [1] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_GHcNgllmcpM.mp4",
"activitynet/videos/v_DYahQgHG1Gk.mp4",
"activitynet/videos/v_zm8gZpwZkRE.mp4",
"activitynet/videos/v_iC1C5wfb0iU.mp4",
"activitynet/videos/v_FRsHew2Pcko.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A person demonstrates lifting, carrying, and lunging with weights in a gym setting.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The person is using an elliptical machine. The sequence shows exercise with the machine, without any lifting, carrying, or lunging with weights.\n[2] The person demonstrates lifting a barbell and performing a lunge. It includes preparatory movements, lifting, and balanced lunging in a gym setting.\n[3] The sequence shows a person lifting a barbell. There is no clear demonstration of carrying or lunging.\n[4] The person is performing a snatch, showcasing weightlifting. Lifting is visible, but not the full range of carrying and lunging.\n[5] The sequence shows a dance performance in a gymnasium setting. It involves typical dance movements without weights.\n</content>\n\n<contrast>\n- [2] is ranked higher because it includes lifting, carrying, and lunging with weights, whereas [3] only shows lifting without any lunging or carrying.\n- [3] demonstrates weightlifting, but lacks the carrying and lunging present in [2].\n- [4] includes lifting, similar to [3], but lacks additional elements like carrying and lunging seen in [2].\n- [1] and [5] do not show any lifting, carrying, and lunging with weights, focusing on different activities instead.\n</contrast>\n\n<summary>\n1st=[2] (demonstrates lifting, carrying, and lunging with weights)\n2nd=[3] (focuses on weightlifting but lacks carrying and lunging)\n3rd=[4] (shows lifting but lacks carrying and lunging)\n4th=[1] (exercises on an elliptical machine, not related to query)\n5th=[5] (a dance routine, unrelated to weightlifting activities)\n</summary>\n</think>\n<answer> [2] > [3] > [4] > [1] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_3cmHM1Yu92s.mp4",
"activitynet/videos/v_3oJ62-Ce9ys.mp4",
"activitynet/videos/v_u08gU4eQFHY.mp4",
"activitynet/videos/v_xMQcYD044z4.mp4",
"activitynet/videos/v_8w9pf_Ecm_U.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man and his wife float down a river on intertubes with a large group, enjoying the scenery and camaraderie along the way.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video features a group of people riding horses through a natural setting, including river crossings. There are no intertubes or floating involved, which mismatches the query.\n\n[2] The video shows people floating down a river on intertubes, wearing helmets and enjoying the activity. Some frames show multiple intertubes, aligning well with the query.\n\n[3] This video depicts a group of people white-water rafting in inflatable rafts, not on intertubes. The focus is on more intense waters, which is not a perfect match for the query's leisurely theme.\n\n[4] People are paddling in canoes down a river, engaging in playful activities on the water. While it involves a group on a river, the equipment doesn't match intertubing.\n\n[5] The video shows a group of people floating down a river on intertubes, showing scenes of relaxing, social interactions, and scenic views. This closely matches the query.\n</content>\n\n<contrast>\n- [5] is ranked above [2] because it shows people relaxing and enjoying the intertubing with a large group, directly aligning with the query's emphasis on camaraderie.\n- [2] outranks [4] as it shows intertubing rather than canoeing, which better matches the query's specification.\n- [4] beats [3] since it includes a leisurely river trip with multiple people, more closely resembling the query than the intense rafting in [3].\n- [3] outranks [1] as it involves a river activity, whereas [1] is entirely about horseback riding.\n</contrast>\n\n<summary>\n1st=[5] (closest match with group intertubing on a river)\n2nd=[2] (intertubing activity, less focus on camaraderie)\n3rd=[4] (river journey, but with canoes)\n4th=[3] (river activity, although more intense than intertubing)\n5th=[1] (no river floating; horseback riding instead)\n</summary>\n</think>\n<answer> [5] > [2] > [4] > [3] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_Vq2mQvMp_c4.mp4",
"activitynet/videos/v_b_v5uGSheEw.mp4",
"activitynet/videos/v_WxefBZ7Iaow.mp4",
"activitynet/videos/v_p4YTDxTASBI.mp4",
"activitynet/videos/v_OYPyiUC4h68.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A festive parade features groups in green uniforms marching down the street while waving flags and playing various brass and percussion instruments.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video depicts a bull being led down a street by several individuals. There is no sign of a festive parade or green uniforms. The focus is on the bull event.\n\n[2] This video shows a pool tournament with children playing billiards. There are no signs of a parade, instruments, or green uniforms. The setting is indoors and involves a game event.\n\n[3] The scene involves individuals riding camels and participating in camel rides at a festival or event. There are no parades or groups in uniform depicted.\n\n[4] This video shows a marching band performance with individuals in uniforms, but the uniforms are not green. They are playing instruments, which aligns partially with the query.\n\n[5] This video features individuals in green uniforms marching down the street. They are waving flags and playing brass and percussion instruments, matching the query description of a festive parade.\n</content>\n\n<contrast>\n- [5] matches the query completely with green uniforms, flags, and instruments, whereas [4] lacks the color detail specifically mentioned.\n- [4] includes a marching band but doesn't show the green uniforms specified in the query description, whereas [5] does.\n- [1], [2], and [3] do not depict parades or match any elements of the query as [5] does with its clear depiction of a parade in green uniforms.\n</contrast>\n\n<summary>\n1st=[5] (features a parade with green uniforms, flags, and instruments)\n2nd=[4] (features a marching band with instruments, partial relevance)\n3rd=[3] (festival environment but lacks parade and uniform details)\n4th=[1] (street event but unrelated to the parade concept)\n5th=[2] (billiards tournament, completely unrelated)\n</summary>\n</think>\n<answer> [5] > [4] > [3] > [1] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_esQnfUcBbPE.mp4",
"activitynet/videos/v_SnBTp7iV2kE.mp4",
"activitynet/videos/v_SHfFrzy_fKM.mp4",
"activitynet/videos/v_xC5RVs9mXyM.mp4",
"activitynet/videos/v_jkn6uvmqwh4.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man practices serving tennis balls on a court with and without other players present.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Images show a racquetball game indoors, with players using racquets in a closed court. The focus is on gameplay, not tennis serving.\n[2] Similar to [1], this sequence involves a racquetball game with players in an enclosed space. Activity isn't related to serving tennis balls.\n[3] Features table tennis, with players at a ping pong table. It does not show serving or a full-sized tennis court.\n[4] Displays a badminton game in an indoor court. Actions resemble rallies rather than serving tennis balls.\n[5] A man is seen practicing serves on a tennis court, both alone and in the presence of another person, clearly matching the query.\n\n</content>\n\n<contrast>\n- [5] accurately shows a man practicing tennis serves with and without other players, whereas [1] and [2] show racquetball.\n- [5] has a clear depiction of tennis serving, whereas [3] shows table tennis, which does not match the query.\n- [5] uniquely displays a tennis serving scenario, whereas [4] focuses on badminton rallies, not related to tennis at all.\n- [1] and [2] are similar in domain but none like [5] which actually covers tennis serving with and without other players.\n</contrast>\n\n<summary>\n1st=[5] (Shows tennis serves being practiced clearly and matches the query)\n2nd=[2] (Shows a relevant indoor racquet sport but not tennis)\n3rd=[1] (Similar indoor racquet sport; lacks tennis-serving action)\n4th=[3] (Shows table tennis, unrelated to the query's tennis focus)\n5th=[4] (Focuses on badminton, not relevant to tennis serving)\n</summary>\n</think>\n<answer> [5] > [2] > [1] > [3] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_mhqfGS59FG0.mp4",
"activitynet/videos/v_rfxXEgc9RTQ.mp4",
"activitynet/videos/v_UPZm0tx77Vw.mp4",
"activitynet/videos/v_F7V-FqgG3T8.mp4",
"activitynet/videos/v_BryW4niZT9Y.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman performs a song on the flute, pausing briefly before finishing with a smile at the camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] A young girl with a blue wig is playing the violin in a room filled with bookshelves. She appears focused on playing throughout the sequence. There is no flute, pause, or smile implied.\n\n[2] A woman is seen using a hookah in a cafe setting. She exhales smoke and smiles at the camera. There is no flute or music performance depicted.\n\n[3] A woman plays a flute while sitting on a couch with orange cushions in the background. The video shows her performing, pausing, and then smiling at the camera, which matches the query.\n\n[4] A woman is smoking a cigarette in a dimly lit room. She poses and occasionally smiles. There is no flute or musical activity present.\n\n[5] A woman performs on a flute with sheet music and a Christmas tree in the background. She appears to pause and ends with a smile towards the camera, consistent with the query.\n</content>\n\n<contrast>\n- [3] is the most fitting as it shows a woman playing the flute, pausing, and smiling at the camera, aligning perfectly with the query.\n- [5] also matches the query by depicting a woman playing the flute with a pause and smile but has less close-up.\n- [1] features an instrument performance but it is a violin, not related to the flute.\n- [2] involves a hookah activity, irrelevant to musical performance.\n- [4] is centered on smoking and lacks any musical elements.\n</contrast>\n\n<summary>\n1st=[3] (perfect match with flute performance, pause, and smile)\n2nd=[5] (flute performance with pause and smile, but less focus on the face)\n3rd=[1] (instrument performance, but it's a violin, not a flute)\n4th=[2] (hookah use and smile, unrelated to query)\n5th=[4] (smoking scene, unrelated to musical performance)\n</summary>\n</think>\n<answer> [3] > [5] > [1] > [2] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_KYl67H9-4TA.mp4",
"activitynet/videos/v_svSM-UqjNWE.mp4",
"activitynet/videos/v_6HyNydVIji4.mp4",
"activitynet/videos/v_zuNQFkkyBNo.mp4",
"activitynet/videos/v_J6ScF5n_Cug.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A person participates in a group bike ride around a track, capturing the experience with a GoPro camera.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The sequence shows people running on a trail in a natural setting, possibly for a trail running event. Most images show a first-person perspective, but no biking or GoPro usage is apparent.\n\n[2] This sequence depicts several individuals using stilts or jumping devices in an urban area. There is no indication of biking or use of a GoPro camera.\n\n[3] This sequence features a person using pogo sticks or similar jumping devices in a park setting. There is no biking involved or use of a GoPro.\n\n[4] The frames capture a person using a skateboard in a suburban neighborhood. No biking or clear use of a GoPro camera is observed.\n\n[5] This sequence is a first-person perspective of a group bike ride on a track, clearly captured with a GoPro camera mounted on a helmet. The images display various angles and riders in action.\n\n</content>\n\n<contrast>\n- [5] is ranked highest because it clearly depicts a group bike ride on a track using a GoPro, matching the query perfectly.\n- [1] involves running in nature, not biking or using a GoPro, whereas [5] directly relates to the query.\n- [2], [3], and [4] show unrelated activities involving stilts and skateboarding, not involving bikes or GoPros.\n- [1] is slightly more relevant than [2], [3], and [4] because it involves outdoor physical activity, but still does not match as well as [5].\n- [2] and [3] are similar in their focus on jumping devices, providing no relevance to biking or GoPro use.\n- [4] involves skateboarding, which is closer to biking but still does not involve group rides or GoPros.\n\n</contrast>\n\n<summary>\n1st=[5] (perfect match with group bike ride and GoPro use)\n2nd=[1] (outdoor physical activity but no biking or GoPro)\n3rd=[4] (skateboarding, which is closer to biking but no GoPro)\n4th=[2] (stilts, unrelated to biking or GoPro use)\n5th=[3] (pogo sticks, unrelated and no biking or GoPro)\n\n</summary>\n</think>\n<answer> [5] > [1] > [4] > [2] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_PntiXZ692xM.mp4",
"activitynet/videos/v_qxlVkDpdyOA.mp4",
"activitynet/videos/v_NLTd7qCLT7o.mp4",
"activitynet/videos/v_DXIHbnyfNGA.mp4",
"activitynet/videos/v_XPN_PSadJ_A.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A young boy plays hopscotch, eagerly running, jumping, and hopping across the course.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a young boy playing hopscotch. He is seen actively running, jumping, and hopping across a hopscotch course drawn on the ground.\n[2] The video captures a beach soccer game with adult players. There is no relevance to hopscotch.\n[3] This video depicts a young child playing with a lacrosse stick, not playing hopscotch.\n[4] The video shows an outdoor gathering with people engaging in different activities, including playing with a racket. It doesn’t involve hopscotch.\n[5] The video features elderly individuals playing croquet on a lawn, unrelated to hopscotch.\n</content>\n\n<contrast>\n- [1] is directly related to a young boy playing hopscotch, whereas [2] features a beach soccer match.\n- [1] shows a relevant hopscotch activity, while [3] depicts a child playing with a lacrosse stick.\n- [1] involves hopscotch, contrasting with [4], which shows a garden setting with no hopscotch.\n- [1] matches the query closely, unlike [5], which shows croquet being played on a lawn.\n</contrast>\n\n<summary>\n1st=[1] (features a boy playing hopscotch as described in the query)\n2nd=[3] (another young child, but playing with a lacrosse stick instead)\n3rd=[4] (outdoor activity, unrelated to hopscotch)\n4th=[5] (features another outdoor game, croquet, unrelated to hopscotch)\n5th=[2] (features a beach soccer game, least relevant)\n</summary>\n</think>\n<answer> [1] > [3] > [4] > [5] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_Nj_fvFbf56I.mp4",
"activitynet/videos/v_Vcv9P-4Tty0.mp4",
"activitynet/videos/v_CG-7jcSB5_c.mp4",
"activitynet/videos/v_DozJpP2cClI.mp4",
"activitynet/videos/v_3YdmY4oPE5s.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman guides viewers through the process of mixing, baking, and cooling a cake in her kitchen.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a sequence in which a woman is in the kitchen. There is some baking, but it appears more focused on cookies. The sequence shows baking trays, cookies in an oven, and cooling steps, but there's no clear cake-making process visible. \n\n[2] This sequence features the making of an Oreo cheesecake, showing steps like mixing ingredients and assembling the cake, but no baking process, as it is likely a no-bake cake. It does not match the full query of mixing, baking, and cooling.\n\n[3] A decorated cake is being made, with activities focused on icing and adding fruits. The sequence skips the mixing and baking parts, focusing solely on decoration.\n\n[4] In this video, a woman is in a kitchen, but the activity or object involved is not clear, particularly related to cake-making. It lacks visible steps like mixing, baking, and cooling.\n\n[5] The video displays a comprehensive cake-making process which includes a woman preparing ingredients, mixing, baking in an oven, and cooling. This aligns well with the query description.\n</content>\n\n<contrast>\n- [5] clearly follows the entire cake-making process including mixing, baking, and cooling, whereas [1] focuses on cookies and lacks a step-by-step cake process.\n- [5] matches the query's baking and cooling stages, while [2] features an Oreo cheesecake, lacking baking.\n- [5] documents the entire process, contrasting with [3]'s focus on decoration only.\n- [5] presents a clear sequence of cake preparation, unlike [4] which lacks visible detail related to the query.\n</contrast>\n\n<summary>\n1st=[5] (comprehensive match with mixing, baking, and cooling a cake)\n2nd=[2] (detailed preparation but without baking a cake)\n3rd=[3] (cake decoration but no baking steps)\n4th=[1] (baking visible but focused on cookies)\n5th=[4] (unclear process and relevance)\n</summary>\n</think>\n<answer> [5] > [2] > [3] > [1] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_3OGD7if0zs8.mp4",
"activitynet/videos/v_vl7OBBTv7KY.mp4",
"activitynet/videos/v_7yndv2xOmn0.mp4",
"activitynet/videos/v_lfGmSfTjnA8.mp4",
"activitynet/videos/v_KpoH4pBp9fg.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man demonstrates how to use different objects while swimming in a pool, performing strokes and showcasing techniques as he moves back and forth.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows several individuals using flotation devices in a pool. They seem to interact and perform some movements, but there is no clear demonstration of specific swimming techniques or strokes.\n\n[2] This video involves a man demonstrating exercises on a bench outside. He shows different positions and movements, but it is unrelated to swimming or pool activities.\n\n[3] The video captures a water polo game in a pool. Participants are engaged in a match rather than demonstrating individual swimming techniques.\n\n[4] The video features a single individual underwater in a pool demonstrating a technique labeled \"Backward Sink (nose holding).\" This showcases a specific swimming maneuver.\n\n[5] The video shows a man demonstrating swimming techniques with accessories, such as a pull buoy and paddles, in a pool. It highlights the use of different objects while swimming.\n</content>\n\n<contrast>\n- Item [5] beats item [4] because it explicitly shows a man demonstrating swimming techniques with different objects in a pool, which directly matches the query.\n- Item [4] beats item [1] because it clearly demonstrates a specific technique underwater, whereas item [1] involves general activities in a pool without focus on swimming techniques.\n- Item [1] beats item [3] because it involves people in a pool, albeit without clear demonstrations, while item [3] focuses on a water polo game, not on showcasing swimming techniques.\n- Item [3] beats item [2] because it is pool-related, although not a technique demonstration, whereas item [2] is entirely unrelated to swimming or pool activities.\n</contrast>\n\n<summary>\n1st=[5] (demonstrates swimming techniques with objects in a pool)\n2nd=[4] (shows a specific underwater technique)\n3rd=[1] (people in a pool but no clear technique showcase)\n4th=[3] (water polo game, not a technique demonstration)\n5th=[2] (unrelated to swimming or pool activities)\n</summary>\n</think>\n<answer> [5] > [4] > [1] > [3] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_rse-MW1helQ.mp4",
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_U0jlI70N_DQ.mp4",
"activitynet/videos/v_e51NGAPMp1s.mp4",
"activitynet/videos/v_fgBFlwM466w.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man explains and demonstrates how to properly adjust and position bike handlebars, brake levers, and shifter levers for optimal riding comfort.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] A man demonstrates exercises on a bench, primarily related to fitness. There's no indication of bikes or bike adjustments.\n[2] A man is working on bike wheels, possibly changing a bike tire or tube, but not focusing on handlebars, brake levers, or shifter levers.\n[3] The video shows a man explaining and working on a bike, specifically focusing on adjusting the handlebars and levers, clearly aligning with the query.\n[4] The content is about arm wrestling with no connection to bike adjustments or comfort.\n[5] This video involves assembling a road bike, including setting up components, but doesn't focus on adjusting handlebars, brake levers, or shifter levers specifically for comfort.\n</content>\n\n<contrast>\n- Item [3] shows the adjustment of bike components whereas item [5] is more about assembly.\n- Item [3] focuses on handlebars and levers, which are the specific subjects of the query whereas item [2] is about changing tires.\n- Item [3] involves instructions relevant to riding comfort adjustments whereas item [1] is unrelated, focusing on fitness exercises.\n- Item [5] involves bike assembly, which is closer to the query than item [1] and item [4], but less specific than item [3].\n- Item [4] is completely unrelated, focusing on arm wrestling whereas item [2] is tangentially related due to the presence of a bike.\n</contrast>\n\n<summary>\n1st=[3] (Directly focuses on adjusting handlebars and levers for optimal riding comfort, matching the query perfectly.)\n2nd=[5] (Related to bike setup, but less specific to adjustments for comfort compared to [3].)\n3rd=[2] (Involves bike maintenance, but focuses on tires instead of handlebars and levers.)\n4th=[1] (Entirely unrelated to the query, focused on exercises.)\n5th=[4] (Completely unrelated, focused on arm wrestling.)\n</summary>\n</think>\n<answer> [3] > [5] > [2] > [1] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_C_bwHYiX-Vw.mp4",
"activitynet/videos/v_nQM5LT1-ZRU.mp4",
"activitynet/videos/v_w6kBE7BHHeU.mp4",
"activitynet/videos/v_IbYlWVA8Dh8.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man engages with a group of young people playing field hockey, observes and interviews from the sidelines, receives a jersey, and then joins in the game, ultimately interacting with the players on the field.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video captures a high jump event at an athletic competition. It focuses on an athlete preparing for, attempting, and clearing a high jump. There is some interaction, but it is limited to congratulatory exchanges after the jump.\n[2] This video displays a sequence where a man observes a sports game, receives a jersey, and participates in some drills on the field. It involves interaction and participation with others.\n[3] The video is about trail running, showcasing runners on various outdoor terrains, with some interview segments mixed in. There is no field hockey or related interaction as described in the query.\n[4] The video consists of various javelin throwing scenes in an athletic competition setting. There is no sideline interaction or joining in as per the query.\n[5] This video involves a futsal game taking place indoors. It contains gameplay and player interactions but no observational or sideline interviews or activities.\n\n</content>\n\n<contrast>\n- [2] is relevant as it shows a man observing, receiving a jersey, and participating in a sports activity, fulfilling the query requirements, whereas [1] is solely about a high jump event with limited interaction.\n- [1] focuses on a single sport performance in an athletic event, lacking the specific engagement and participation elements present in [2].\n- [5] involves indoor gameplay without the sideline behavior specified in the query, whereas [2] includes observing and interacting outside the game.\n- [3] and [4] depict individual sports performance and have no engagement or group interaction aspect as mentioned in the query.\n- [1], [3], [4], and [5] lack the progression from observation to active engagement present in [2].\n\n</contrast>\n\n<summary>\n1st=[2] Engages with observing, interacting, and participating in sports as specified.\n2nd=[1] Displays interaction, albeit limited, and includes sports activity.\n3rd=[5] Involves sports gameplay but lacks the observational aspect.\n4th=[3] Focuses on individual running with limited interaction.\n5th=[4] Shows athletic attempts with no relevant interaction or observation.\n\n</summary>\n</think>\n<answer> [2] > [1] > [5] > [3] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_RatbnDSuY7w.mp4",
"activitynet/videos/v_LFiGhD1OEws.mp4",
"activitynet/videos/v_lTFCUuLtUJs.mp4",
"activitynet/videos/v_FOlMVTmAeaQ.mp4",
"activitynet/videos/v_XxMzH75Bhr8.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man demonstrates how to balance and walk on a tightrope in a forest, highlighting foot placement and techniques for maintaining stability.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video shows a group of people preparing to bungee jump, visible from a platform overlooking a river. There is no tightrope or forest setting, and it does not involve tightrope walking.\n\n[2] This video depicts several people running in different outdoor settings, such as parks and dirt roads. The focus is on running and there is no demonstration of tightrope walking in a forest.\n\n[3] The video shows a man demonstrating exercises on a workout bench, likely for abdominal workouts. This does not relate to tightrope walking or forest scenes.\n\n[4] This video involves people playing croquet on a grass field. It does not have any relevance to tightrope walking or a forest environment.\n\n[5] The video illustrates a person slacklining in a forest setting. There are clear visuals of foot placement and techniques for balance on the slackline, which aligns with tightrope walking in a forest context.\n</content>\n\n<contrast>\n- [5] clearly demonstrates the action of balancing and walking on a slackline in a forest, aligning with the query, whereas [1] focuses on bungee jumping preparation.\n- [5] shows foot placement and techniques relevant to the query, whereas [2] focuses solely on running without similar context.\n- [5] is directly related to tightrope-like activity, while [3] and [4] are about exercising on a bench and playing croquet respectively, with no connection to the query.\n</contrast>\n\n<summary>\n1st=[5] (demonstrates slackline walking in a forest, closely matching the query)\n2nd=[2] (outdoor activity visible but does not relate to tightrope walking)\n3rd=[1] (outdoor setting, but focuses on bungee jumping preparation)\n4th=[3] (exercise demonstration unrelated to tightrope walking)\n5th=[4] (entirely unrelated activity: croquet on grass)\n</summary>\n</think>\n<answer> [5] > [2] > [1] > [3] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_VZ2CPdIPa30.mp4",
"activitynet/videos/v_lTFCUuLtUJs.mp4",
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_3YdmY4oPE5s.mp4",
"activitynet/videos/v_Bs3TR80BRco.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Children build and play in a sandcastle by the sea, using a toy shovel and fetching water.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows two children at the beach constructing a sandcastle. They are using a toy shovel and bringing water to the castle, closely matching the query of building and playing in a sandcastle by the sea.\n\n[2] This video features a group of children dancing and playing in a yard, which does not relate to the query about building a sandcastle by the sea.\n\n[3] Participants are engaged in a sandcastle-building competition at the beach, with adults involved in constructing and shaping the sand. Although it involves sandcastle building, it doesn’t show children using a toy shovel or fetching water.\n\n[4] The video depicts a child playing alone in a colorful playground, unrelated to constructing a sandcastle by the sea.\n\n[5] Children are seen riding camels at a fairground, with no connection to a sandcastle activity or setting by the sea.\n</content>\n\n<contrast>\n- [1] beats [3] because it directly involves children using a toy shovel and fetching water for a sandcastle, aligning exactly with the query, whereas [3] involves adults.\n- [3] ranks higher than [2] because it involves sandcastle building at a beach, unlike the unrelated dance activity in [2].\n- [2] beats [4] as it involves multiple children playing, whereas [4] is a lone play activity unrelated to sandcastles or a beach setting.\n- [4] beats [5] as it involves children playing, albeit not on the beach, whereas [5] is a fairground camel ride not related to sand or the beach.\n</contrast>\n\n<summary>\n1st=[1] (Children building and playing in a sandcastle match all query elements)\n2nd=[3] (Sandcastle competition aligns partially with the query)\n3rd=[2] (Involves children playing but not related to sandcastles)\n4th=[4] (Child playing but not related to sandcastles or sea)\n5th=[5] (Fairground activity unrelated to the query)\n</summary>\n</think>\n<answer> [1] > [3] > [2] > [4] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_jalqZE5ekho.mp4",
"activitynet/videos/v_PjSOjB7qhcA.mp4",
"activitynet/videos/v_gYARGADLcmQ.mp4",
"activitynet/videos/v_0GpNcvAVWVg.mp4",
"activitynet/videos/v_SHfFrzy_fKM.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men play a lively game of tennis indoors, hitting the ball back and forth while moving around the room.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This sequence shows two men in a squash court; one holds a racket and appears to explain something or coach the other. They eventually engage in playing a game inside the glass-enclosed court.\n[2] Two men are playing an indoor racquetball game in a court. They are actively hitting the ball back and forth, showcasing movement and interaction similar to the query description.\n[3] Two individuals are playing shuffleboard on a long table in an indoor setting. This does not relate to tennis or any racquet sport.\n[4] This sequence involves children practicing basketball skills on an indoor court, focusing on lay-up techniques.\n[5] Two men play badminton indoors. They hit a shuttlecock over a net and move around a green indoor court. This involves rackets but is not tennis.\n\n</content>\n<contrast>\n- [2] shows a racquetball game with two men in an indoor court, closely matching the tennis theme in terms of action and environment, whereas [1] involves squash with more focus on instruction.\n- [1] includes explanations and squash playing but transitions from a coaching scenario, whereas [2] consistently displays a back-and-forth game dynamic.\n- [5] involves rackets but is a badminton game, not tennis, lacking the specific tennis element.\n- [3] shuffleboard and [4] basketball do not involve racket sports and are therefore less relevant to the tennis theme.\n\n</contrast>\n<summary>\n1st=[2] Two men actively play racquetball indoors, similar dynamic to tennis.\n2nd=[1] Features squash with an eventual game play, involves rackets in an indoor setting.\n3rd=[5] Involves racket play with badminton, lacks specific tennis element.\n4th=[3] Shuffleboard game, unrelated to racket sports.\n5th=[4] Indoor basketball practice, unrelated to racket sports.\n\n</summary>\n</think>\n<answer> [2] > [1] > [5] > [3] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_jzBR9ihZBbI.mp4",
"activitynet/videos/v_mhqfGS59FG0.mp4",
"activitynet/videos/v_NZ5iioSnCO8.mp4",
"activitynet/videos/v_y3Wfx-RvTpk.mp4",
"activitynet/videos/v_F7V-FqgG3T8.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"An older man repairs and adjusts a bike chain outside, demonstrating the process and explaining his work as he goes.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video features a younger man inside a shop as he adjusts a bike, likely focusing on repairs. He seems to be working on gears but isn't seen outside or visibly explaining his work.\n\n[2] An older man is seen outdoors working closely on a bike chain. He handles the chain with tools, suggesting adjustments and repairs consistent with the query. His presence and actions strongly match the description.\n\n[3] The video shows a person welding indoors, with no connection to bicycle repairs or adjustments. The process involves heavy machinery, irrelevant to the query.\n\n[4] Displays a man working on a green bike indoors. The focus appears to be on general bike assembly or checks, but not specifically on chain adjustments.\n\n[5] This sequence features a man indoors demonstrating bicycle shifters, focusing on different bike parts than the chain. There is no outdoor setting or older man present.\n</content>\n\n<contrast>\n- [2] performs the task specified in the query outdoors, whereas [1] occurs indoors without clear chain work.\n- [3] is irrelevant due to the absence of a bicycle and focuses on welding.\n- [4] does not clearly emphasize chain work and happens indoors.\n- [5] emphasizes shifter demonstration indoors instead of chain adjustment.\n</contrast>\n\n<summary>\n1st=[2] (Match: Older man outdoors repairing bike chain clearly shown)\n2nd=[1] (Bike repair shown, but indoors and with a younger individual)\n3rd=[4] (Indoors bike work shown, not specifically chain-focused)\n4th=[5] (Focus on different bike components, no chain work)\n5th=[3] (Irrelevant welding activity)\n</summary>\n</think>\n<answer> [2] > [1] > [4] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_jbSBQL08VHA.mp4",
"activitynet/videos/v_NpKBAtQ5M6I.mp4",
"activitynet/videos/v_5Bo0gFXxDQk.mp4",
"activitynet/videos/v_5BAvlsHfTLk.mp4",
"activitynet/videos/v_nQM5LT1-ZRU.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of boys spend time together outdoors, starting with gardening and then playing a game of croquet while chatting and enjoying each other's company.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows people playing a team sport on a large grassy area, which appears to be ultimate frisbee or a similar game. There is no evidence of gardening or a croquet game. \n[2] The video aligns perfectly with the query. It shows two boys starting with gardening activities, followed by setting up and playing a game of croquet. The atmosphere is relaxed, fitting the theme of spending time outdoors with company.\n[3] This video depicts a man and a child mowing a lawn in a suburban neighborhood. There's no evidence of a group of boys or croquet. \n[4] This video shows a croquet game being played, but it appears to involve older individuals rather than a group of boys. There is no sign of gardening activities.\n[5] The video depicts a toddler playing with a lacrosse stick on a wooden deck. There is no evidence of a group activity, gardening, or croquet within the video.\n</content>\n\n<contrast>\n- [2] accurately depicts both gardening and croquet with a group of boys, whereas [4] only shows croquet with older individuals.\n- [1] includes an outdoor game but not croquet or gardening, whereas [2] features both gardening and croquet.\n- [3] lacks both croquet and gardening, featuring a different outdoor activity instead.\n- [5] depicts a single child playing, which does not align with the group activity described in the query.\n- [4] involves croquet but not with a group of boys or any gardening, unlike [2], which covers both aspects.\n</contrast>\n\n<summary>\n1st=[2] (perfect match: gardening and croquet with a group of boys)\n2nd=[4] (croquet game visible but not with boys or gardening aspects)\n3rd=[1] (outdoor activity with a group, not gardening or croquet)\n4th=[3] (outdoor activity but unrelated to query specifics)\n5th=[5] (single child playing, not related to group activity)\n</summary>\n</think>\n<answer> [2] > [4] > [1] > [3] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_wUg9S2xx850.mp4",
"activitynet/videos/v_eypKc4FyZ2s.mp4",
"activitynet/videos/v_L_fvvmvV-Tc.mp4",
"activitynet/videos/v_3YdmY4oPE5s.mp4",
"activitynet/videos/v_CG-7jcSB5_c.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Several men gather around a table to watch and record a game as it unfolds.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a bowling game in progress. Different frames display bowlers throwing balls down lanes, pins being knocked down, and scoreboards. No table or gathering around a table is evident.\n[2] This video depicts an athletics event, specifically a hammer throw. There are shots of athletes preparing, throwing the hammer, and the audience watching. No scene of men gathering around a table.\n[3] The sequence involves a weightlifting event. Athletes are lifting weights on a stage with an audience and cameras capturing the event. There isn't any gathering around a table.\n[4] This video fits the query closely. Several men are engaged around a shuffleboard table, apparently watching and possibly recording or scoring as the game progresses. The setting is casual, indicating a relevant scenario.\n[5] This video contains a hockey game with players, referees, and some crowd interactions. There is action on the ice, but no evidence of men around a table watching or recording a game.\n</content>\n\n<contrast>\n- [4] perfectly matches the query with men gathering around a shuffleboard table, whereas others feature different sports settings.\n- [1] shows a bowling scene which lacks the table-focused activity described, whereas [4] captures such a gathering.\n- [2] features an athletics event, not involving a table setting, unlike [4].\n- [3] presents weightlifting without a table scene, whereas [4] shows the relevant setup.\n- [5] revolves around ice hockey and player interaction, not around a table, unlike [4].\n</contrast>\n\n<summary>\n1st=[4] (Men gather around a shuffleboard table, aligning with the query)\n2nd=[1] (Bowling game with minimal relevance to watching around a table)\n3rd=[2] (Athletics with audience; different focus than gathering around a table)\n4th=[3] (Weightlifting event, no table-related action)\n5th=[5] (Hockey game lacking the table element)\n</summary>\n</think>\n<answer> [4] > [1] > [2] > [3] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_1t0yXLlX1XE.mp4",
"activitynet/videos/v_KnHUAc20WEU.mp4",
"activitynet/videos/v_YK5n3YTf8pI.mp4",
"activitynet/videos/v_NZ5iioSnCO8.mp4",
"activitynet/videos/v_ruHObln9mwI.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of guards march and play trumpets before a man demonstrates an elaborate shoe-polishing process involving heat and brushing, observed by soldiers.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Shows a group activity on a field, possibly a tug-of-war with participants pulling on a rope. No guards or shoe-polishing process visible.\n\n[2] Depicts a pole vaulting competition at a stadium, featuring athletes preparing and jumping. No guards or shoe-polishing involved.\n\n[3] Captures a jump rope competition indoors with an audience. No guards or shoe-polishing process present.\n\n[4] Displays another group activity resembling tug-of-war with uniforms but lacks any shoe-polishing demonstration.\n\n[5] Features guards marching and playing trumpets with soldiers observing a shoe-polishing process involving heat and brushing.\n</content>\n<contrast>\n- [5] is the most relevant because it precisely matches the query with guards, trumpet playing, and a shoe-polishing demonstration observed by soldiers.\n- [1] and [4] both include group activities and uniforms but lack the shoe-polishing context.\n- [2] and [3] focus on unrelated sports activities, making them irrelevant to the query's specifics.\n</contrast>\n<summary>\n1st=[5] (exact match with marching, trumpets, and shoe-polishing)\n2nd=[1] (group activity with uniforms, no shoe-polishing)\n3rd=[4] (similar to [1], but still lacks key elements)\n4th=[2] (completely unrelated sports event)\n5th=[3] (unrelated sports event with no thematic elements from the query)\n</summary>\n</think>\n<answer> [5] > [1] > [4] > [2] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_H3cFZelOk2Y.mp4",
"activitynet/videos/v_rv9jW-t3mT4.mp4",
"activitynet/videos/v_Sma-ydx49eQ.mp4",
"activitynet/videos/v_T3ngvDyxYiE.mp4",
"activitynet/videos/v_MnzVdvbvnMc.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A gymnast prepares, performs an impressive tumbling routine at an Olympic event, receives applause and support from the crowd and her coach, and is celebrated for her performance.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Features a weightlifting event, showing athletes preparing, lifting weights, and results on a leaderboard. No gymnastics or tumbling routines are present.\n\n[2] Displays a gymnast performing on the parallel bars at a well-attended event, showing a complete routine which culminates in the gymnast celebrating the performance with the crowd and coaches present. \n\n[3] Centers around an athletic event (discus throw), focusing on athletes, the action of throwing, and the return of results with a podium finish and celebration, but does not feature gymnastics.\n\n[4] Shows a gymnastics event with a focus on a female gymnast preparing for and performing a tumbling routine on a track, including interactions with a coach and audience. The event concludes with visible celebration.\n\n[5] Contains multiple clips of tumbling and gymnastics routines, including athlete preparations and performances at various events. Some sequences show applause and interaction with the audience, but the footage is less clear.\n</content>\n\n<contrast>\n- [4] clearly matches the query with a complete sequence of preparation, performance, and celebration at a gymnastics event, whereas [2] focuses on a parallel bar routine without evident crowd celebration.\n- [2] features a high-quality performance with visible audience but lacks the full sequence of preparation to celebration demonstrated in [4].\n- [5] contains some related content across various events but the quality and coherence are lower than [4] and [2].\n- [3] and [1] depict athletics and weightlifting events respectively, lacking relevant gymnastics content.\n</contrast>\n\n<summary>\n1st=[4] (provides a full narrative arc matching the query: preparation, performance, celebration)\n2nd=[2] (contains performing gymnast; lacks full narrative and celebration details)\n3rd=[5] (has scattered relevant gymnastics content; low clarity)\n4th=[3] (athletics content; no gymnastics)\n5th=[1] (weightlifting content; not relevant)\n</summary>\n</think>\n<answer> [4] > [2] > [5] > [3] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_uTVjevTM6V0.mp4",
"activitynet/videos/v_5xgBlI9Xx0I.mp4",
"activitynet/videos/v_BERvPz1e_AU.mp4",
"activitynet/videos/v_DEVD2oszH48.mp4",
"activitynet/videos/v_VEDRmPt_-Ms.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men engage in a fencing match on a platform while a woman observes their duel.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The frames show a performance on a platform with two individuals engaging in acrobatic or tightrope actions, not fencing, and a spectator visible. It does not include fencing equipment or actions, but there is a platform presence.\n\n[2] This scene takes place in a backyard setting, featuring casual activities and social interactions among people. There's no platform, and no fencing activities are seen.\n\n[3] The indoor gym features multiple people performing dance or gymnastics routines. No fencing or platform observed.\n\n[4] Olympic gymnastics activities, focusing on pommel horse routines. It doesn't show fencing activities or a platform setting for dueling.\n\n[5] Two individuals are engaged in a fencing match on a platform. A woman is observing, fulfilling all query criteria with visible fencing equipment and actions.\n</content>\n\n<contrast>\n- [5] matches the fencing and platform setting with an observer whereas [1] involves a performance on a platform without real fencing actions.\n- [5] shows actual fencing whereas [2] is a casual outdoor scene with no relation to fencing or platforms.\n- [5] involves structured sports activity on a platform, unlike [3], which features indoor dance or gymnastics.\n- [5] directly visualizes fencing and matches the query, whereas [4] focuses on gymnastics with no relation to fencing.\n</contrast>\n\n<summary>\n1st=[5] (Direct match with fencing, platform, and observer)\n2nd=[1] (Platform setting and observer, but no fencing involved)\n3rd=[4] (Sports setting, but gymnastics instead of fencing)\n4th=[3] (Indoor activity but not related to fencing)\n5th=[2] (Unrelated outdoor social activity)\n</summary>\n</think>\n<answer> [5] > [1] > [4] > [3] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_oeFUzyNgxQU.mp4",
"activitynet/videos/v_DozJpP2cClI.mp4",
"activitynet/videos/v_NVtRGWuiEP4.mp4",
"activitynet/videos/v_Le6fNx5IWRI.mp4",
"activitynet/videos/v_J5wZTdD4XeU.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"The video features a group gathering outside a building and showcases a cartoon depiction of sumo wrestlers battling while a referee observes.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video features a person creating a Chinese painting of waterfalls and rocks. There is no depiction of sumo wrestlers or a group gathering outside.\n\n[2] This video shows an athletic event featuring a high jump. There are no sumo wrestlers or group gatherings outside depicted.\n\n[3] This video depicts an indoor activity where people are playing a game, possibly involving a floor mat resembling a sports field. There's no depiction of sumo wrestlers or an outdoor gathering.\n\n[4] The video includes animated scenes of a building with people gathering outside, followed by cartoon depictions of sumo wrestlers battling with a referee. This matches the query.\n\n[5] This video captures a live sumo wrestling match with wrestlers and a referee in a traditional setting, but lacks the cartoon depiction or outdoor group gathering described in the query.\n</content>\n\n<contrast>\n- [4] is ranked highest because it features both an outdoor gathering and a cartoon depiction of sumo wrestling, directly matching the query.\n- [5] focuses on a real sumo match and includes a referee, but lacks the cartoon style and outdoor gathering.\n- [3] shows an indoor game activity and lacks any connection to sumo wrestling or outdoor gatherings.\n- [2] is about a high jump event and is unrelated to the query's themes.\n- [1] focuses on painting, which is completely unrelated to the query.\n</contrast>\n\n<summary>\n1st=[4] (matches both aspects of the query: outdoor gathering and cartoon sumo wrestling)\n2nd=[5] (shows sumo wrestling and a referee but lacks cartoon style and outdoor aspect)\n3rd=[3] (indoor activity unrelated to the query's topics)\n4th=[2] (depicts athletic high jump, unrelated to the query)\n5th=[1] (features traditional painting, unrelated to the query)\n</summary>\n</think>\n<answer> [4] > [5] > [3] > [2] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_S47vfJ9g3Mw.mp4",
"activitynet/videos/v_VCg6_fuipp8.mp4",
"activitynet/videos/v_y0VZOcxbjRM.mp4",
"activitynet/videos/v_P9jIpcRGeOk.mp4",
"activitynet/videos/v_om1vXrpctVE.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two men take turns playing guitar and interacting with the instrument.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a man playing a saxophone in multiple sequences. There is no presence of a guitar or interaction with two people sharing turns.\n[2] The frames depict a violin and provide a textual guide on playing minor chords. There is no sign of guitar playing or two men interacting.\n[3] This video features two individuals preparing to play rock-paper-scissors. The focus is on their interaction, but not on guitar playing.\n[4] The video frames show individuals involved in a construction or renovation project, laying down tiles inside a room. No guitars or two men trading turns playing an instrument are present.\n[5] The series of images centers on guitar-related activity. Both a close-up of a guitar and a man operating the instrument are featured. However, the interaction does not explicitly show two men taking turns with the guitar.\n</content>\n\n<contrast>\n- Candidate [5] shows guitar-related activities, whereas [1], [2], [3], and [4] do not involve guitars.\n- [5] beats [1] because [1] involves playing a saxophone, not a guitar, whereas [5] at least shows guitar use.\n- [5] beats [2] because [2] involves a violin, not a guitar, and does not feature two people interacting with an instrument.\n- [5] beats [3] because [3] shows people preparing for rock-paper-scissors with no musical instruments involved.\n- [5] beats [4] since [4] involves construction, not a musical or guitar context.\n</contrast>\n\n<summary>\n1st=[5] (Involves guitar playing, close-up views, partial alignment with query)\n2nd=[1] (Musical setting, but wrong instrument)\n3rd=[2] (Instrument interaction, but wrong instrument)\n4th=[3] (Two-person interaction, no musical context)\n5th=[4] (Unrelated construction activity)\n</summary>\n</think>\n<answer> [5] > [1] > [2] > [3] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_CB0yYGVNcOk.mp4",
"activitynet/videos/v_MNpV9WvVPSA.mp4",
"activitynet/videos/v_AnRYS02tvRA.mp4",
"activitynet/videos/v_fVg3StD8LL0.mp4",
"activitynet/videos/v_Y-1QkIGm81w.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"The video shows a person riding a bull in an arena, followed by the bull charging at people and knocking them down as others watch from around the arena.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The sequence clearly shows a rodeo arena setting with a person riding a bull initially, followed by the bull running across the arena and people interacting with the scene, matching the query well.\n[2] This sequence involves equestrian activities like jumping and horseback riding, neither bulls nor events matching the query.\n[3] The frames depict an indoor sports event, specifically futsal, which is unrelated to the query scenario of a bull riding and charging event.\n[4] This video shows a rodeo scene, but it focuses on calf roping rather than bull riding or a bull charging at people.\n[5] Similar to [4], this video captures a roping event in a rodeo setting, lacking bull riding or a bull charging scene.\n\n</content>\n<contrast>\n- [1] ranks higher than [2] because it involves bull riding and subsequent charging, whereas [2] only features horse jumping.\n- [1] is above [3] because it depicts rodeo activities rather than unrelated indoor sports.\n- [1] beats [4] and [5] due to its clear depiction of bull riding and interaction, whereas [4] and [5] focus on roping.\n- [4] and [5] are ranked based on their closer relation to rodeo, yet neither includes bull charging scenes as in [1].\n- [2] is preferred over [3] due to equestrian content, which is nearer to rodeo than indoor team sports.\n</contrast>\n<summary>\n1st=[1] (depicts exact bull riding and charging)\n2nd=[4] (rodeo setting, lacks bull charging)\n3rd=[5] (rodeo setting, lacks bull charging)\n4th=[2] (equestrian, not rodeo)\n5th=[3] (unrelated indoor sports)\n</summary>\n</think>\n<answer> [1] > [4] > [5] > [2] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_F4ERtlGMFt4.mp4",
"activitynet/videos/v_2i_rotAjuoE.mp4",
"activitynet/videos/v_XxMzH75Bhr8.mp4",
"activitynet/videos/v_-X7fBYN5fBc.mp4",
"activitynet/videos/v_nnWON1EzK0o.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man surfs in the ocean, skillfully gliding over and riding waves on his surfboard.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a man wakesurfing behind a boat on a body of water, using a surfboard and performing tricks. This involves riding the wake produced by the boat rather than ocean waves.\n\n[2] The video captures a scene where several people are in the ocean waiting for waves to surf. Although large waves are present, no one is seen surfing them in the frames.\n\n[3] This video is unrelated to the query as it shows a person staining a fence in a backyard. There is no ocean or surfing activity present.\n\n[4] This video displays a man surfing large ocean waves skillfully. He is visible maneuvering on the surfboard, taking on challenging waves that indicate advanced surfing techniques.\n\n[5] The video depicts windsurfing activities. People are seen using windsurfing equipment on the ocean, which is a different sport from traditional surfing.\n</content>\n\n<contrast>\n- [4] is ranked higher than others because it directly shows a man surfing large ocean waves skillfully.\n- [1] involves wakesurfing which is close to the query but differs as it relies on a boat's wake rather than ocean waves.\n- [2] shows waves and surfers in the water, but lacks visible surfing action compared to [1] and [4].\n- [5] involves windsurfing, which is distinct from the query involving traditional surfing.\n- [3] is completely unrelated as it features fence staining, not any form of surfing.\n</contrast>\n\n<summary>\n1st=[4] (direct match with skillful ocean surfing displayed)\n2nd=[1] (close match with wakesurfing, showing surfing maneuvers)\n3rd=[2] (lesser match due to lack of visible surfing action, only surfers waiting)\n4th=[5] (different sport: windsurfing, not traditional surfing)\n5th=[3] (unrelated to surfing, shows fence staining)\n</summary>\n</think>\n<answer> [4] > [1] > [2] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_3svMy4Kfjd8.mp4",
"activitynet/videos/v_Cw5NDI8NnZU.mp4",
"activitynet/videos/v_FZix27qFZTc.mp4",
"activitynet/videos/v_9ZGy24Geu5k.mp4",
"activitynet/videos/v_AhWkUdag6NA.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man and a boy spend time together on a basketball court, with the man talking and the boy playing basketball.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] A young boy is seen playing hopscotch alone in what appears to be a driveway. There is no basketball court or interaction with a man.\n[2] This sequence depicts an indoor futsal game with multiple players, unrelated to a basketball or interaction between a man and a boy.\n[3] The frames show various activities unrelated to basketball, including a computer screen, a boy indoors, and skateboarding. No basketball court or interaction is visible.\n[4] This sequence shows a man and a boy on a basketball court. The man appears to be talking, and the boy is playing basketball, matching the query.\n[5] Individuals are seen using jumping stilts in an outdoor setting, unrelated to a basketball court.\n</content>\n\n<contrast>\n- Item 4 matches the query exactly with a man talking and a boy playing basketball on a court, whereas Item 1 features a boy playing hopscotch alone.\n- Item 4 has a basketball setting which fits the query, whereas Item 2 shows a futsal environment with no basketball or family interaction.\n- Item 4 involves the right actions within a basketball context, whereas Item 3 depicts unrelated scenes like skateboarding and computer use.\n- Item 4 is directly relevant with basketball interaction compared to Item 5, which shows jumping stilts without a basketball court.\n</contrast>\n\n<summary>\n1st=[4] (matches the setting and actions)\n2nd=[1] (features a child playing, but not basketball)\n3rd=[5] (contains outdoor play, different activity)\n4th=[3] (different activities showcased, no basketball)\n5th=[2] (features futsal, wholly unrelated setting)\n</summary>\n</think>\n<answer> [4] > [1] > [5] > [3] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_Nj_fvFbf56I.mp4",
"activitynet/videos/v_c6ie4KwFnAs.mp4",
"activitynet/videos/v_DXIHbnyfNGA.mp4",
"activitynet/videos/v_Kbr2nr94EB0.mp4",
"activitynet/videos/v_qxlVkDpdyOA.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man practices motocross by performing high jumps and riding his motorbike in a dusty field.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows people and dogs performing agility tasks in a grassy field. This is unrelated to motocross.\n[2] The video features a high jump athletic event, focusing on an athlete jumping over a bar. No motocross or motorbikes are visible.\n[3] The video depicts motocross stunts, with a person riding a motorbike in a dusty field, performing high jumps and tricks. This matches the query well.\n[4] The video involves people outdoors, possibly a comedic scene or social event, not related to motocross.\n[5] The video includes motorbikes and riders in a race-like setting with multiple bikers on a dirt track. It somewhat matches motocross but less focus on high jumps or stunts.\n</content>\n\n<contrast>\n- [3] clearly depicts motocross activities with visible high jumps and tricks, whereas [5] focuses more on racing without distinct stunts.\n- [5] shows a motorbike-focused activity, better fitting the motocross context than [1], [2], and [4], which do not involve motorbikes.\n- [2] showcases athletic high jumps but without motorbikes, making it less relevant than any motocross content.\n- [4] involves a non-motocross outdoor social activity, less relevant than any video involving bikes.\n- [1] features a different sports activity involving dogs, irrelevant to motocross or biking.\n</contrast>\n\n<summary>\n1st=[3] (best match for motocross with stunts and jumps)\n2nd=[5] (motorbike racing activity, less on stunts)\n3rd=[2] (high jump event, no bikes but conceptually closer than others)\n4th=[4] (non-motocross social activity, unrelated)\n5th=[1] (dog agility sport, unrelated)\n</summary>\n</think>\n<answer> [3] > [5] > [2] > [4] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_e__FVkfXB-U.mp4",
"activitynet/videos/v_VCg6_fuipp8.mp4",
"activitynet/videos/v_p6jip892RdM.mp4",
"activitynet/videos/v_BJGACTBaU_Y.mp4",
"activitynet/videos/v_Fpivz0Yie_Q.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"The video follows a group of men engaging in different activities and hobbies in the mountains, culminating with a man speaking as the credits roll.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video seems to follow a group of men engaging in different activities in a mountainous area. It concludes with a man speaking as credits roll, matching the query's description.\n\n[2] The video is primarily focused on skiing events or competitions in a snowy mountain setting. It doesn't feature a group of men engaging in various activities or any speaking parts with credits.\n\n[3] This video shows snowboarding on a mountain, focusing on individuals rather than a group of men engaging in various activities. No speaking or credits are evident.\n\n[4] The video features solo kayak paddling on a lake; it does not align with the setting or content of the query (mountains, multiple activities, speaking).\n\n[5] This video displays snowboarding in a mountain setting but lacks the element of varied activities or any speaking and credits rolling.\n</content>\n\n<contrast>\n- [1] matches the query with varied activities in the mountains and includes a speaking part with credits, whereas [2] focuses solely on skiing competitions.\n- [2] shows a skiing event, whereas [3] displays snowboarding but lacks varied activities or a speaking segment.\n- [3] involves snowboarding only, whereas [4] involves kayaking in a non-mountainous setting.\n- [4] features kayaking without the mountain setting or group activities, whereas [5] includes snowboarding but misses varied activities and a speaking part.\n</contrast>\n\n<summary>\n1st=[1] (Covers varied mountain activities and ends with speaking and credits)\n2nd=[2] (Focused on snow sports but lacks varied activities and speaking)\n3rd=[3] (Displays snowboarding in mountains, no varied activities or speaking)\n4th=[5] (Shows snowboarding, lacks varied activities and speaking)\n5th=[4] (Focused on kayaking, doesn't fit mountainous group activities)\n</summary>\n</think>\n<answer> [1] > [2] > [3] > [5] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_jHbf_E8aY1k.mp4",
"activitynet/videos/v_FNB1BMEtIvw.mp4",
"activitynet/videos/v_gBTnWp9VLz4.mp4",
"activitynet/videos/v_sQtT9sUyUwE.mp4",
"activitynet/videos/v_vu65aIIJHtU.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people play water polo in a swimming pool while others move around and interact both in and out of the water.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This sequence shows a water polo game in a swimming pool, with several players wearing caps, actively engaged in play. There are spectators and some interaction at the poolside.\n\n[2] This sequence features a diving event. An individual performs multiple dives from a platform into a pool. There is no water polo game or evident interaction between groups in or out of the pool as per the query.\n\n[3] In this sequence, many people are in a pool, but it mostly appears to be casual play or swimming without structured water polo activity. The individuals are interacting both in and out of the water, matching part of the query.\n\n[4] This sequence is a beach volleyball game with people playing on sand. There is no swimming pool or water interaction involved, which does not align with the query.\n\n[5] A group of people are in a pool playing a structured game that resembles water polo, with noticeable interaction among the players. There is evident engagement both in and around the pool area, fitting the query well.\n</content>\n\n<contrast>\n- [5] beats [1] because there is more evident interaction and movement around the pool area in addition to the water polo game.\n- [1] beats [3] because it features an actual water polo game, whereas [3] involves general pool play without structured water polo.\n- [3] beats [2] because it involves more group interaction and activity in the pool, whereas [2] focuses solely on diving.\n- [2] beats [4] because diving involves a pool setting, while [4] features beach volleyball with no water interaction.\n</contrast>\n\n<summary>\n1st=[5] (Best overall match for water polo and interaction in and around the pool)\n2nd=[1] (Clear water polo match but less interaction outside the pool)\n3rd=[3] (Good interaction but lacks structured water polo)\n4th=[2] (Diving event, involves a pool but no water polo or interaction)\n5th=[4] (Beach volleyball, no relevance to water polo or pool activities)\n</summary>\n</think>\n<answer>[5] > [1] > [3] > [2] > [4]</answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_kLflIBGCNrc.mp4",
"activitynet/videos/v_yVsOoFr61x4.mp4",
"activitynet/videos/v_xeFS0RuvVGA.mp4",
"activitynet/videos/v_SLPD1U5iDjY.mp4",
"activitynet/videos/v_7ZX3NHDmMZY.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A person demonstrates waxing their leg while lying on a bed.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video features a person demonstrating leg waxing in a professional setting. Various shots show the waxing process, including applying wax and using strips on the leg. The person is not on a bed but appears to be on a treatment table.\n[2] This video is related to installing floor tiles. It shows a person cutting and fitting tiles, which is irrelevant to the query.\n[3] This video depicts a person performing wrestling moves on a bed. There are no scenes of waxing; instead, it involves playful interaction, unrelated to the query.\n[4] The video captures an arm-wrestling event taking place outdoors with a crowd watching. It does not involve waxing and is non-relevant to the query.\n[5] This video shows the process of waxing legs while the person is lying on a bed. It includes applying wax and using strips, closely matching the query.\n</content>\n\n<contrast>\n- [5] is the best match because it shows leg waxing on a person lying on a bed, closely aligning with the entire query.\n- [1] also features leg waxing but on a treatment table, making it slightly less relevant than [5] which fits the bed aspect.\n- [3] involves activities on a bed but no waxing, making it less relevant.\n- [4] features arm-wrestling which is entirely unrelated to the query.\n- [2] is about tile installation, which is irrelevant to waxing a leg or any bed activity.\n</contrast>\n\n<summary>\n1st=[5] (Best match: waxing on a bed, aligns with query)\n2nd=[1] (Good match: waxing demonstrated, but not on a bed)\n3rd=[3] (Some relevance: involves a bed, but no waxing)\n4th=[4] (Irrelevant: arm-wrestling event)\n5th=[2] (Irrelevant: tile installation)\n</summary>\n</think>\n<answer> [5] > [1] > [3] > [4] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_2Xfigl8xrXc.mp4",
"activitynet/videos/v_ZIBWRRBft8g.mp4",
"activitynet/videos/v_hgpekgU915k.mp4",
"activitynet/videos/v_eil9mWGJB8E.mp4",
"activitynet/videos/v_cRDXBF2RcYI.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A cheerleading team from Mill Creek High School performs an energetic and synchronized routine filled with stunts and cheers before celebrating together at the end.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The sequence depicts a small group of people performing a coordinated routine in what appears to be a gymnasium. The individuals are dressed in athletic clothing and are using pom-poms, indicative of a cheerleading performance. There is movement and stunts throughout, although the setting is informal, hinting at a practice or community event rather than an official high school team performance. \n\n[2] This sequence captures an individual performing a gymnastics routine on a balance beam. The setting is a large venue with many spectators, indicating a competition. The focus is on acrobatics and balance rather than cheerleading or team dynamics.\n\n[3] The scene shows a nighttime baseball or softball game with several players on a field. The participants are actively engaged in the game, but there is no indication of cheerleading elements such as stunts or routines.\n\n[4] The sequence displays a formal cheerleading competition with a large group of cheerleaders performing a well-synchronized routine. It includes complex stunts, formations, and cheer techniques. There are banners indicating a state championship setting, making it closely aligned with the query’s mention of a cohesive and dynamic cheer performance.\n\n[5] Similar to [2], this showcases a gymnastics beam routine in a competitive environment with a large audience. The focus is on individual performance and acrobatics, not cheerleading or team interaction.\n</content>\n\n<contrast>\n- [4] is highly relevant due to depicting a full cheerleading team in a formal setting performing an advanced routine, whereas [1] features an informal and smaller performance that lacks the same complexity.\n- [1] involves cheerleading elements and synchronization but lacks the competitive and complete team environment shown in [4].\n- [2] and [5] are about gymnastics, not cheerleading, making them less relevant. [2] is similar in competitive atmosphere but lacks the cheerleader focus.\n- [3] is unrelated as it captures a sports event with no cheer performance.\n</contrast>\n\n<summary>\n1st=[4] (captures a full, formal cheerleading routine with all key elements)\n2nd=[1] (features cheerleading but in an informal setting and smaller scale)\n3rd=[2] (captures athletic performance but unrelated to cheerleading)\n4th=[5] (similar to [2], a gymnastic routine, unrelated to query)\n5th=[3] (completely unrelated as it features a baseball/softball game)\n</summary>\n</think>\n<answer> [4] > [1] > [2] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_8w9pf_Ecm_U.mp4",
"activitynet/videos/v_3j52keiQuiw.mp4",
"activitynet/videos/v_URzytLugoVw.mp4",
"activitynet/videos/v_xqYII12ta4E.mp4",
"activitynet/videos/v_ok3Kpgv0PzE.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Several people of different ages take turns serving and hitting a shuttlecock while playing a game of badminton together.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This sequence shows multiple people on a badminton court, taking turns hitting a shuttlecock. The action is consistent with playing badminton, involving serving and hitting back and forth.\n[2] This sequence shows people playing croquet in a backyard. They use mallets to hit balls through hoops, which does not match the badminton query.\n[3] This video depicts people playing in a backyard, with a focus on casual outdoor activity. While there is a badminton racket visible, it lacks clarity in action.\n[4] This sequence features several people of different ages playing badminton indoors, with a clear view of serving and hitting a shuttlecock across the net.\n[5] This video shows a group of people playing croquet on a lawn. The focus is on using mallets and balls rather than badminton play.\n</content>\n\n<contrast>\n- [4] shows multiple people actively playing badminton, clearly displaying serving and hitting, whereas [1] has less diversity in action.\n- [1] focuses on badminton, displaying the movement and equipment related to a game setting, whereas [2] and [5] depict croquet.\n- [3] includes a badminton racket but lacks a clear focus on actual play compared to [1] and [4].\n- [2] and [5] are clear mismatches focused on croquet, whereas [1] and [4] include badminton gameplay.\n</contrast>\n\n<summary>\n1st=[4] (features a clear focus on multiple people of different ages playing badminton)\n2nd=[1] (showcases badminton play but with less variety in participants and action)\n3rd=[3] (includes a backyard setting and a badminton racket but lacks focused play)\n4th=[2] (depicts croquet, not matching the badminton query)\n5th=[5] (also focused on croquet, not badminton)\n</summary>\n</think>\n<answer> [4] > [1] > [3] > [2] > [5] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_9_wuEvN2OnQ.mp4",
"activitynet/videos/v_uZC3WPkta-I.mp4",
"activitynet/videos/v_DozJpP2cClI.mp4",
"activitynet/videos/v_EL47wkhiOq8.mp4",
"activitynet/videos/v_3YdmY4oPE5s.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"People enjoy sliding down a snowy hill on inflated tires, with both children and adults participating in the fun.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video shows a snowy urban area with vehicles and people walking. No evidence of people sliding on inflated tires.\n[2] People are sliding down snowy tracks on inflatable tubes. Both children and adults are visible enjoying the activity.\n[3] Various winter activities occur, including people sliding on snow, though inflatable tires aren't clearly visible. There are also scenes of snowball making and playing.\n[4] The video is related to ice hockey, with scenes of players and hockey action, not related to sliding on snow.\n[5] The video appears to involve winter sports like snowboarding or skiing, but not specifically tubing on snow with inflatable tires.\n</content>\n\n<contrast>\n- [2] is the best match because it clearly shows people sliding on snow using inflatable tubes, matching the query directly.\n- [3] relates to snow activities but does not clearly show sliding on inflatable tires, making it less relevant than [2].\n- [1] is unrelated as it shows an urban setting with no sliding activity visible.\n- [5] involves winter sports like snowboarding, which doesn't match the specific activity requested.\n- [4] is entirely unrelated as it focuses on ice hockey, not snow sliding.\n\n</contrast>\n\n<summary>\n1st=[2] (clearly shows people sliding on snow with inflatable tubes)\n2nd=[3] (includes snow sliding activities but not specific to tubes)\n3rd=[5] (winter sports shown, but not the queried activity)\n4th=[1] (urban area with no relevant activities)\n5th=[4] (ice hockey, unrelated to the query)\n</summary>\n</think>\n<answer> [2] > [3] > [5] > [1] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_thvpt_lUxTI.mp4",
"activitynet/videos/v_7QvvqWJRwNo.mp4",
"activitynet/videos/v_HEuC9ZEY91E.mp4",
"activitynet/videos/v_wZ-teiWX4mg.mp4",
"activitynet/videos/v_FNB1BMEtIvw.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man performs various wakeboarding tricks, including jumping obstacles, spinning, and flipping in the air while sliding on ramps.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video contains various activities, including skateboarding and kayaking, with no focus on wakeboarding tricks or obstacles.\n\n[2] This video shows a man performing wakeboarding tricks at a wake park, including jumping over obstacles and spinning in the air. It matches the query well.\n\n[3] The video features a demonstration of a wakeboarding invention, but it lacks the performance of specific tricks such as jumping, spinning, or flipping.\n\n[4] The video is unrelated, depicting a person on an exercise machine in an indoor setting, with no connection to wakeboarding.\n\n[5] This video shows wakeboarding on a lake but lacks the variety of tricks mentioned in the query, such as jumping obstacles, spinning, or flipping.\n</content>\n\n<contrast>\n- [2] shows wakeboarding tricks and park settings, matching the query because it includes jumping over obstacles and spinning, whereas [5] lacks specific trick performances.\n- [5] shows basic wakeboarding without tricks, whereas [3] includes wakeboarding with a focus on an invention.\n- [3] relates to wakeboarding but is more about a device than performing tricks, whereas [1] shows mixed sports content unrelated to the query.\n- [1] shows multiple sports but not focused on wakeboarding tricks, whereas [4] is entirely unrelated, depicting indoor exercise.\n</contrast>\n\n<summary>\n1st=[2] because it features wakeboarding tricks and obstacles.\n2nd=[5] because it shows wakeboarding but lacks tricks.\n3rd=[3] because it involves wakeboarding with focus on a device.\n4th=[1] because it shows unrelated sports activities.\n5th=[4] because it is unrelated and indoors.\n</summary>\n</think>\n<answer> [2] > [5] > [3] > [1] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_1opIvQF0m_M.mp4",
"activitynet/videos/v_hHxEBnhLsXs.mp4",
"activitynet/videos/v_wdsZn1Yu_5M.mp4",
"activitynet/videos/v_8874vqLm958.mp4",
"activitynet/videos/v_8UvKQnfXnCk.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of people participate in a step workout routine at the gym and finish by raising their hands and stopping the exercise.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video sequence in the frames shows people engaged in an activity in a gym, but it appears to be more of a dodgeball or group sport rather than a step workout routine. The focus is on movement with a ball, and there's no progression towards raising hands and stopping exercise in a step workout manner.\n\n[2] This sequence shows a group of people in a gym environment participating in a step workout. The presence of step platforms and synchronized movement aligns with step exercises, and it concludes with group activity, which may include a final movement such as raising hands.\n\n[3] The images depict training on monkey bars, primarily involving children and an outdoor setting. This is unrelated to a gym-based step workout routine, as it focuses on individual physical training rather than group step exercises.\n\n[4] This shows a workout instruction scenario, likely focused on abdominal exercises given the presence of crunches. While related to gym activity, it doesn't match the group dynamic or step workout focus of the query.\n\n[5] The setting involves a group of people dancing or participating in an aerobics-like exercise in a gym environment. However, there aren't visible step platforms or the raising hands ending described in the query.\n</content>\n\n<contrast>\n- [2] beats [5] because it shows visible step platforms and synchronized group movement, fitting the step workout criteria, whereas [5] suggests more of a dance routine.\n- [5] beats [1] because it involves a group exercise setting similar to a gym class, whereas [1] depicts a sport activity unrelated to the query.\n- [1] beats [4] as it involves a larger group dynamic in a gym, whereas [4] focuses on an individual exercise session.\n- [4] beats [3] because it at least takes place in a gym setting, whereas [3] is entirely out of scope with outdoor training on monkey bars.\n</contrast>\n\n<summary>\n1st=[2] (clear step workout with ending fit)\n2nd=[5] (group exercise class setting)\n3rd=[1] (group activity in a gym)\n4th=[4] (gym setting with exercise focus)\n5th=[3] (outdoor, unrelated to step workout)\n</summary>\n</think>\n<answer> [2] > [5] > [1] > [4] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_t_2jTjX3a_o.mp4",
"activitynet/videos/v_0Q9RHSEFeMI.mp4",
"activitynet/videos/v_tB_B3HVdO2I.mp4",
"activitynet/videos/v_0OxOI3sAIrM.mp4",
"activitynet/videos/v_nY8a1E4QH5Q.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A girl in a purple leotard performs a gymnastics routine on the balance beam, including jumps and a somersault, while an audience watches.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Shows a female athlete preparing for a track event, possibly a pole vault or long jump. She is wearing green shorts and a white top. No gymnastics or balance beam is present.\n\n[2] A male gymnast is performing on the parallel bars. He is wearing a blue leotard, and an audience is visible. This does not involve a balance beam routine.\n\n[3] A female gymnast in a purple leotard is performing on a balance beam. The sequence shows jumps and various movements, with an audience watching. This matches the query description closely.\n\n[4] Various gymnastics activities are shown, including floor and vault exercises. It is unclear if a balance beam routine with a purple leotard is included, as the frames are mixed and unclear.\n\n[5] A female gymnast performs on the balance beam in a black leotard. She executes complex moves and an audience is visible. However, she is not wearing a purple leotard.\n</content>\n\n<contrast>\n- [3] matches the query with a gymnast in a purple leotard executing a balance beam routine, whereas [5] has the right apparatus but the wrong leotard color.\n- [5] contains a balance beam routine but lacks the correct leotard color compared to [3].\n- [2] and [4] lack the apparatus focus; [2] is about parallel bars, and [4] contains mixed activities with unclear relevance.\n- [1] is unrelated as it shows a track event.\n</contrast>\n\n<summary>\n1st=[3] (Matches query with purple leotard and balance beam routine)\n2nd=[5] (Has balance beam routine, but incorrect leotard color)\n3rd=[4] (Mixed gymnastics, unclear if includes balance beam or purple leotard)\n4th=[2] (Focus on parallel bars, no balance beam)\n5th=[1] (Track event, not related to gymnastics routine)\n</summary>\n</think>\n<answer> [3] > [5] > [4] > [2] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_hS7VEMlJ4N0.mp4",
"activitynet/videos/v_ZT63nK4lexg.mp4",
"activitynet/videos/v_wlAnWPxnQ8k.mp4",
"activitynet/videos/v_VEDRmPt_-Ms.mp4",
"activitynet/videos/v_ShiBZnuxlmc.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman demonstrates and explains proper exercise techniques using a large exercise bar.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a woman performing exercises on a mat. She is demonstrating movements like sit-ups, but there is no large exercise bar in use. This is not relevant to the query.\n[2] The video features a man demonstrating exercises on a bench. There is no large exercise bar involved, and it does not match the query.\n[3] The video shows a woman using a leaf blower in a garden setting. There is no connection to exercise techniques or a large exercise bar.\n[4] A woman is shown performing step exercises outdoors. She uses a step platform but not a large exercise bar. This is somewhat related due to the exercise theme but does not match the query for a large bar.\n[5] This video depicts a male gymnast performing on a pommel horse. It involves gymnastics skills but not the demonstration of exercise techniques using a large exercise bar, which does not fit the query.\n</content>\n\n<contrast>\n- [4] is ranked higher than [1] because it involves exercise, whereas [1] does not involve a bar.\n- [1] is ranked higher than [2] because [1] focuses strictly on exercise techniques, whereas [2] features a man and lacks coherence with the query.\n- [1] is ranked higher than [5] because [1] is exercise-focused, even though neither uses a large bar.\n- [2] is ranked higher than [5] because it involves explaining and demonstrating exercises, whereas [5] involves gymnastics.\n- [5] ranks higher than [3] as it shows gymnastic equipment and physical activity, unlike [3], which features unrelated activities.\n</contrast>\n\n<summary>\n1st=[4] (shows exercise although no bar)\n2nd=[1] (exercise shown, no bar)\n3rd=[2] (exercise-related, no bar)\n4th=[5] (athletic related, no bar)\n5th=[3] (no relation to exercise with a bar)\n</summary>\n</think>\n<answer> [4] > [1] > [2] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_zNpILhjhFbQ.mp4",
"activitynet/videos/v_FujUrbL1qc0.mp4",
"activitynet/videos/v_1P_y_DLlg-E.mp4",
"activitynet/videos/v_DxNIzbD6uD4.mp4",
"activitynet/videos/v_bmf7otW5TQo.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A woman bathes and grooms a small dog, carefully washing, shampooing, and handling the pet throughout the process.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a person bathing a dog outdoors. The sequence includes the dog standing in a tub, getting shampooed, and having water poured over it. The later frames show the dog being rinsed with a hose and finally placed in a cage.\n\n[2] The video portrays a person bathing a dog in a sink indoors. The process involves using shampoo, rinsing, and drying the dog with a towel. The event occurs on a countertop, with consistent handling of the dog throughout.\n\n[3] This video involves a person washing a large dog in a tub. The person is applying soap and scrubbing the dog, with consistent focus on washing activities. The setting is an indoor space.\n\n[4] The sequence shows a woman involved in various activities near a washing station. No clear dog bathing is visible.\n\n[5] The video appears to capture a child playing with a dog in a bath. It involves water but does not focus on grooming or careful handling of the dog.\n</content>\n\n<contrast>\n- [2] is ranked higher than [1] because it clearly shows indoors grooming with a focus on careful handling and consistent bathing.\n- [1] beats [3] since [1] has a visible sequence of washing and grooming a small dog, matching the query's focus on a small dog.\n- [3] is preferable to [5] as it involves a deliberate washing process, even though the dog is larger.\n- [5] ranks higher than [4] as it involves interaction with a dog in water, unlike [4] which lacks a specific dog bathing scene.\n</contrast>\n\n<summary>\n1st=[2] (indoor grooming, careful handling, focus on small dog)\n2nd=[1] (outdoor bathing, clear sequence on small dog washing)\n3rd=[3] (large dog washing focus)\n4th=[5] (interaction with dog in water)\n5th=[4] (no dog bathing visible)\n</summary>\n</think>\n<answer> [2] > [1] > [3] > [5] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_Djlmto9iibw.mp4",
"activitynet/videos/v_y76trNI6U0Y.mp4",
"activitynet/videos/v_DXOKFXlx84M.mp4",
"activitynet/videos/v_eaR8oEBlYWk.mp4",
"activitynet/videos/v_O9qI26TB3R0.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two women demonstrate and discuss furniture polishing techniques, showcasing their results and the surrounding scenery while engaging another woman in conversation.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Features a news report and an outdoor community event with conversations but no relevance to furniture polishing.\n[2] Shows a woman alone demonstrating a product that resembles a cleaning activity, relevant to polishing but lacks the presence of two women conversing.\n[3] Depicts an interaction between two generations focused on knitting, with no relevance to furniture or polishing.\n[4] Shows two women demonstrating furniture polishing and discussing techniques. Scene includes the setting and results, matching the query.\n[5] Displays outdoor activities and social gatherings unrelated to furniture polishing.\n</content>\n\n<contrast>\n- [4] is best because it shows two women actively demonstrating and discussing furniture polishing, closely fitting the query.\n- [2] is relevant as it involves a product demonstration for cleaning/polishing, though it lacks the interaction aspect specified in the query.\n- [1] involves conversations and interactions but lacks any reference to furniture or polishing tasks.\n- [5] features unrelated outdoor activities, making it less relevant.\n- [3] focuses on a different skill (knitting) and lacks any connection to furniture or polishing.\n</contrast>\n\n<summary>\n1st=[4] (Two women demonstrate and discuss furniture polishing)\n2nd=[2] (Demonstrates related product but lacks two women interaction)\n3rd=[1] (Involves conversation but unrelated to polishing)\n4th=[5] (No connection to polishing, just social activities)\n5th=[3] (Focuses on a different activity—knitting)\n</summary>\n</think>\n<answer> [4] > [2] > [1] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_p800u2wCKbE.mp4",
"activitynet/videos/v_VQPfRCsSmQk.mp4",
"activitynet/videos/v_xxXspvK4tEY.mp4",
"activitynet/videos/v_pn1XDTlNMso.mp4",
"activitynet/videos/v_DozJpP2cClI.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A young boy escapes the challenges of school and family life through drawing, dancing, and hopscotch, ultimately finding hope and connection in his creativity.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video depicts a young boy at home and school, feeling isolated, but finding joy and expression through drawing and dancing. It ends with a shot of hopscotch, aligning closely with the query about escape and hope through creativity and childhood games.\n\n[2] A young boy is playing hopscotch, showing joy and engagement in the activity. However, it focuses solely on hopscotch without elements of drawing or broader creative escape.\n\n[3] A child is playing hopscotch with a parent, but the focus is primarily on the game itself, lacking the creative escape narrative and diversity of activities described in the query.\n\n[4] The video instructs on painting flowers with no depiction of a child, drawing, or dancing, and lacks narrative elements of escape or childhood.\n\n[5] A young girl is playing hopscotch in a neighborhood, similar to [2] and [3], but lacks elements related to drawing or dancing, focusing solely on the game.\n</content>\n\n<contrast>\n- [1] beats [2] because it shows the themes of drawing, dancing, and hopscotch, thus capturing the full spectrum of escape and creativity.\n- [2] beats [3] because it focuses more on the child and the hopscotch game, showing joy which aligns partly with the query about finding hope.\n- [3] beats [5] because it includes a social aspect with an adult that might hint at a connection, whereas [5] is purely focused on the activity itself.\n- [5] beats [4] because it relates to one aspect of the query, hopscotch, whereas [4] does not relate to any part of the query involving children or escape through creativity.\n</contrast>\n\n<summary>\n1st=[1] (captures full narrative of escape through drawing, dancing, and hopscotch)\n2nd=[2] (focus on hopscotch with the child's joy partially aligning with the query)\n3rd=[3] (includes hopscotch and slight social interaction but lacks full narrative)\n4th=[5] (focuses solely on hopscotch without additional creative elements)\n5th=[4] (unrelated to the themes of childhood escape through creativity)\n</summary>\n</think>\n<answer> [1] > [2] > [3] > [5] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_mBZAFJ-Q6Mw.mp4",
"activitynet/videos/v_Nj_fvFbf56I.mp4",
"activitynet/videos/v_HafSt7EDin0.mp4",
"activitynet/videos/v_fRUoSevi63M.mp4",
"activitynet/videos/v_b5GJUtjiWkQ.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A large marching band gathers in the center of a crowd and performs together as onlookers watch from the sides.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The images depict a large marching band gathering in the center of a plaza. The band members are in uniform, holding instruments, and are surrounded by a crowd of onlookers who are standing and watching from the sides. The sequence captures their performance in a public outdoor setting, aligning well with the query.\n\n[2] This sequence shows a capoeira demonstration, where participants engage in acrobatic movements in the center of a circle formed by onlookers. While there is a crowd and a group performance, it does not match the marching band context.\n\n[3] A group of people in teal shirts and black pants are performing a choreographed routine in the center of a ring of spectators. While it shows a public performance, it lacks the specific marching band elements and instruments described in the query.\n\n[4] The video displays a musical performance with accordion players and a brass band on a stage, but it lacks the outdoor setting and crowd interaction specified in the query about a marching band.\n\n[5] People are seen dancing in the street with a crowd around them, indicative of a festive street event. However, it does not involve a marching band or the organization of such a group formation.\n</content>\n\n<contrast>\n- [1] beats [3] because it clearly features a marching band with instruments and uniforms, whereas [3] is a choreographed dance without instruments.\n- [1] beats [4] as it depicts an outdoor marching band event with crowd involvement, whereas [4] is a studio band performance.\n- [1] beats [5] because it involves a large organized group of musicians, whereas [5] focuses on street dancing.\n- [3] beats [2] and [5] due to its more organized group performance and crowd setting reminiscent of a marching band situation.\n- [2] beats [5] since it involves a structured group performance with an audience, which [5] lacks.\n</contrast>\n\n<summary>\n1st=[1] (Direct match: marching band in outdoor setting with crowd)\n2nd=[3] (Organized group performance in public setting)\n3rd=[2] (Focused group performance with an audience)\n4th=[5] (Crowd event but lacking marching band elements)\n5th=[4] (Indoor musical performance, lacks outdoor and crowd elements)\n</summary>\n</think>\n<answer> [1] > [3] > [2] > [5] > [4] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_xC5RVs9mXyM.mp4",
"activitynet/videos/v_AkeJ-lJLNkw.mp4",
"activitynet/videos/v_vX0xxYxGj-4.mp4",
"activitynet/videos/v_D5EgASje8MQ.mp4",
"activitynet/videos/v_i1llwxnI_Vo.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of boys play catch with a yellow ball in an outdoor pool, repeatedly tossing it to each other and out of the pool in a playful game.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a group of boys standing on an outdoor court-like area, not in a pool. They are playing a game involving poles, but there is no visible yellow ball or pool-related activity.\n[2] This video features a group of boys and some adults in an outdoor pool, clearly engaging in a game involving a yellow ball. The ball is tossed around among the participants in the pool.\n[3] Displays children in the ocean and on the beach, but there is no visible yellow ball or focused game of catch.\n[4] The scene is indoors with people in a pool, but it involves floatation devices rather than a ball game. The focus is not on a yellow ball being tossed.\n[5] Shows two individuals on a beach passing a ball, but it lacks a group setting or clear indication of a playful game in a pool environment. The ball isn't discernible as yellow.\n\n</content>\n\n<contrast>\n- [2] is the best match because it shows an outdoor pool setting with a group involved in a game with a yellow ball, fulfilling all aspects of the query. \n- [5] shows a ball being tossed but lacks the group dynamic and pool setting that [2] provides.\n- [3] includes beach and ocean play but not the specific catch game with a yellow ball in a pool.\n- [4] has a pool setting but focuses on floatation devices, without a visible yellow ball game.\n- [1] features an unrelated game outside of a pool setting with no yellow ball.\n\n</contrast>\n\n<summary>\n1st=[2] (outdoor pool, group playing with a yellow ball)\n2nd=[5] (ball tossing, lacks group and pool setting)\n3rd=[3] (outdoor water setting, no focused game with a yellow ball)\n4th=[4] (pool with floatation devices, no visible yellow ball)\n5th=[1] (unrelated outdoor activity, no pool or ball)\n\n</summary>\n</think>\n<answer> [2] > [5] > [3] > [4] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_zlXvqnBqVvI.mp4",
"activitynet/videos/v_xeFS0RuvVGA.mp4",
"activitynet/videos/v_tQmsDeu1d6M.mp4",
"activitynet/videos/v_rse-MW1helQ.mp4",
"activitynet/videos/v_ymEh5T11kSQ.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A man demonstrates how to create a small bag by folding, knotting, and securing a scarf with accessories placed inside.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] The video shows a person constructing and flying a kite using sticks, string, and a garbage bag in an outdoor setting. There is no indication of creating a bag with a scarf.\n\n[2] The video depicts a man wrapping a gift with wrapping paper, yard stick, tape, and a razor blade. No scarf or bag creation is involved.\n\n[3] The video contains scenes of shot putting, with various individuals in athletic settings. This does not relate to creating a bag with a scarf.\n\n[4] This video shows a person folding and knotting a patterned scarf, placing items inside to form a small bag. This directly aligns with the query about creating a small bag with a scarf and accessories.\n\n[5] The content showcases adjusting a dog harness, demonstrating how it fits on a dog. It does not involve making a bag with a scarf.\n</content>\n\n<contrast>\n- [4] is most relevant as it directly shows folding and knotting a scarf to make a bag, matching the query, whereas others do not.\n- [1] focuses on kite construction and flying outdoors, not related to the query, whereas [4] matches perfectly.\n- [2] involves gift wrapping, missing the specific elements of scarf folding, unlike [4].\n- [3] is about shot putting, which is unrelated to the task of creating a bag.\n- [5] involves a dog harness and lacks the elements of scarf folding and bag creation.\n</contrast>\n\n<summary>\n1st=[4] (It perfectly matches the query, showing how to create a bag using a scarf.)\n2nd=[2] (Though about wrapping, it involves folding objects, somewhat close to crafting.)\n3rd=[1] (Focuses on crafting a kite, unrelated but involves creative assembly.)\n4th=[5] (Dog harness demonstration, unrelated to scarf or bag creation.)\n5th=[3] (Shot putting events, not relevant to creating a bag with a scarf.)\n</summary>\n</think>\n<answer> [4] > [2] > [1] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_AH-3mF6wWhU.mp4",
"activitynet/videos/v_c9mrRiwmhZw.mp4",
"activitynet/videos/v_Y5qDKbTkCaY.mp4",
"activitynet/videos/v_Mcutz37Bowg.mp4",
"activitynet/videos/v_oyljZJZJ7IA.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Performers sing, dance, and engage with the audience through energetic choreography and dynamic stage presence during a concert performance.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Shows a dynamic concert performance with performers singing and dancing on a stage, interacting with the audience. The presence of bright lights and large audience denotes high energy and engagement, fitting the query well.\n\n[2] Displays a sequence of art creation using ink and paint to draw floral and animal shapes. This doesn't align with a concert performance, lacking any live audience or stage presence.\n\n[3] Features a dancer performing on stage, with instruments visible in the background, suggesting a live setting. However, it seems more focused on individual dance rather than an energetic concert involving audience engagement.\n\n[4] Depicts a solo dancer performing with hula hoops in various dynamic poses. While the performance is lively and engaging, it lacks elements of singing or a band setup typical for a concert.\n\n[5] Illustrates a large group dance or acrobatic performance, with performers in formation engaging in synchronized movements under stage lights. The setting is lively and dynamic, suitable for a high-energy concert context.\n\n</content>\n\n<contrast>\n- [1] beats [5] because [1] includes both dancing and singing with evident audience interaction, whereas [5] focuses on dance without clear audience engagement.\n- [5] beats [3] because [5] has a larger group dynamic, enhancing the stage presence, whereas [3] focuses on a solo performance.\n- [3] beats [4] because [3] involves more elements of stage performance with musical equipment visible, whereas [4] is a solo act with no signs of singing or a concert setup.\n- [4] beats [2] because [4] shows a performance on stage with dynamic action, aligning more with the concept of a live event, whereas [2] is about art creation.\n- [2] has no concert elements, so it ranks last.\n\n</contrast>\n\n<summary>\n1st=[1] (Engages with both singing and dancing in a large concert setting)\n2nd=[5] (Displays dynamic group performance suitable for concerts)\n3rd=[3] (Stage performance with instruments, though focused on solo dance)\n4th=[4] (Dynamic solo act but lacks concert setup)\n5th=[2] (Art creation, no concert relevance)\n</summary>\n</think>\n<answer> [1] > [5] > [3] > [4] > [2] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_cRBnLFujD3g.mp4",
"activitynet/videos/v_N_zbcVs419E.mp4",
"activitynet/videos/v_cNvTm72aGcM.mp4",
"activitynet/videos/v_NiQaDgj8Z10.mp4",
"activitynet/videos/v_HysxcMFrTkc.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"Two scuba divers prepare to enter the water from a boat, with one entering smoothly while the other gets stuck and struggles before making it in.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] Shows people getting into inflatable tubes to float down a river. They carry the tubes to the water and then float downstream. Not related to scuba diving or entering the water from a boat.\n\n[2] Features two people in wetsuits and masks on a boat. One person smoothly enters the water with a backward roll, while the other struggles and gets stuck initially but manages to get in. Matches the query by showing the sequence of entering the water.\n\n[3] Displays a surfing scene with several surfers in the ocean waiting for and riding waves. It does not involve scuba diving or entering from a boat.\n\n[4] Shows scuba divers on a boat before entering the water and then underwater scenes, such as marine life and a diving site. While it includes preparation to enter the water, it does not clearly show one diver struggling to enter.\n\n[5] Includes a mix of underwater footage with scuba divers and marine life; however, it lacks clear footage of preparing to enter the water and showing one diver struggling.\n</content>\n\n<contrast>\n- [2] is more relevant because it clearly shows the scenario of scuba divers entering the water from a boat, with one diver struggling, matching the query exactly.\n- [4] involves scuba diving but lacks the clear struggle and smooth entry depicted in the query, whereas [2] does show this distinction.\n- [5] also involves scuba diving but does not show the entry process well, compared to [2], which clearly shows both entering scenes.\n- [3] features surfing and thus involves an unrelated activity compared to [2]’s accurate depiction of divers entering water.\n- [1] is about tubing on a river, which does not match the scuba diving setup of [2].\n</contrast>\n\n<summary>\n1st=[2] (clearly matches query with specific entry struggle and smooth entry)\n2nd=[4] (shows scuba diving and preparation, but not the specific struggle scenario)\n3rd=[5] (involves scuba diving, lacks specific entry details)\n4th=[3] (unrelated surfing scene)\n5th=[1] (unrelated tubing scene)\n</summary>\n</think>\n<answer> [2] > [4] > [5] > [3] > [1] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_6EN1q4TmPtI.mp4",
"activitynet/videos/v_25dJIdZj6Xs.mp4",
"activitynet/videos/v_Cw5NDI8NnZU.mp4",
"activitynet/videos/v_hpU50i4WBK8.mp4",
"activitynet/videos/v_PT18KK_6jmU.mp4"
] |
[
{
"content": "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. \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<think>\n<content>\n[1] ...\n[2] ...\n[3] ...\n[4] ...\n[5] ...\n</content>\n\n<contrast>\n...\n</contrast>\n\n<summary>\n1st=[i] ...\n2nd=[j] ...\n3rd=[k] ...\n4th=[m] ...\n5th=[n] ...\n</summary>\n</think>\n<answer> [i] > [j] > [k] > [m] > [n] </answer>\n\nConstraints:\n- Inside <think>, use ONLY <content>, <contrast>, <summary>.\n- Do NOT use per-candidate XML tags.\n- Always output a total order in <answer>.\n\n\nQuery: \"A group of girls experience the excitement and fear of bungee jumping at an amusement park, supporting each other as they take the plunge while a pop band performs in the background.\"\n\nCandidates:\n[1] video:<video>\n[2] video:<video>\n[3] video:<video>\n[4] video:<video>\n[5] video:<video>\n",
"role": "user"
},
{
"content": "<think>\n<content>\n[1] This video shows a gymnastics setting indoors where a gymnast is performing on the bars with others watching, which does not relate to bungee jumping or an amusement park setting.\n\n[2] This video captures people tubing down a river, including various scenes of people in life jackets. While adventurous, it does not match the bungee jumping context at an amusement park with a pop band.\n\n[3] The video involves children playing on a playground slide, with no connection to bungee jumping, an amusement park, or a pop band performance.\n\n[4] This video accurately portrays girls experiencing bungee jumping, with visible emotions and support from each other in an outdoor setting. It partially matches the amusement park setting, although a pop band isn't visible.\n\n[5] This video shows a group of children hitting a pinata outdoors. It does not relate to bungee jumping or an amusement park setting with a pop band.\n</content>\n\n<contrast>\n- [4] best matches the query because it actually shows girls bungee jumping and supporting each other, whereas [1], [2], [3], and [5] do not show bungee jumping or an amusement park context.\n- [2] involves adventure with water activities but lacks the specific bungee jumping theme present in [4].\n- [1], [3], and [5] are clear mismatches as they depict indoor gymnastics, playground activities, and a pinata game respectively, with no relation to the query.\n</contrast>\n\n<summary>\n1st=[4] (accurately depicts bungee jumping and the support aspect)\n2nd=[2] (involves adventure, but not bungee jumping)\n3rd=[1] (sports activity unrelated to bungee jumping)\n4th=[5] (group activity unrelated to bungee jumping)\n5th=[3] (playground activity unrelated to bungee jumping)\n</summary>\n</think>\n<answer> [4] > [2] > [1] > [5] > [3] </answer>",
"role": "assistant"
}
] |
[
"activitynet/videos/v_mc5XVTo5PVk.mp4",
"activitynet/videos/v_OYPyiUC4h68.mp4",
"activitynet/videos/v_C4V6fqELvPY.mp4",
"activitynet/videos/v_Hev5Vj0Jjuk.mp4",
"activitynet/videos/v_WJ4tCIdAgVo.mp4"
] |
End of preview. Expand
in Data Studio
No dataset card yet
- Downloads last month
- 1
Size of downloaded dataset files:
678 kB
Size of the auto-converted Parquet files:
208 kB
Number of rows:
198