images images listlengths 1 1 | data_source stringclasses 1
value | reward_model dict | extra_info dict | prompt listlengths 2 2 | ability stringclasses 1
value | env_name stringclasses 1
value |
|---|---|---|---|---|---|---|
sealvqa_spatial | {
"ground_truth": "Yes, the hot dog is on the right side of the cup."
} | {
"answer": "Yes, the hot dog is on the right side of the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the hot dog on the right side of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The handbag is to the left of the dog."
} | {
"answer": "The handbag is to the left of the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"imag... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag to the left or right of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the handbag is on the left side of the bottle."
} | {
"answer": "Yes, the handbag is on the left side of the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": ... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag on the left side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the dog is not above the motorcycle."
} | {
"answer": "No, the dog is not above the motorcycle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"im... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog above the motorcycle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the traffic light is above the person."
} | {
"answer": "Yes, the traffic light is above the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the traffic light above the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the car is not on the left side of the person."
} | {
"answer": "No, the car is not on the left side of the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": t... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the car on the left side of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The car is below the traffic light."
} | {
"answer": "The car is below the traffic light.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_p... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the car above or below the traffic light?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the car is above the chair."
} | {
"answer": "Yes, the car is above the chair.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the car above the chair?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The wine glass is above the knife."
} | {
"answer": "The wine glass is above the knife.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the wine glass above or below the knife?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The backpack is above the dog."
} | {
"answer": "The backpack is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the backpack above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The person is above the dog."
} | {
"answer": "The person is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the person above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dog is to the left of the bottle."
} | {
"answer": "The dog is to the left of the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog to the left or right of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the bottle is not to the left of the person."
} | {
"answer": "No, the bottle is not to the left of the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tru... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle to the left of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dog is below the book."
} | {
"answer": "The dog is below the book.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "co... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog above or below the book?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the book is not below the bottle."
} | {
"answer": "No, the book is not below the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the book below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the dog is not above the traffic light."
} | {
"answer": "No, the dog is not above the traffic light.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog above the traffic light?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the truck is above the dog."
} | {
"answer": "Yes, the truck is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the truck above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the apple is not below the oven."
} | {
"answer": "No, the apple is not below the oven.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the apple below the oven?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bottle is above the apple."
} | {
"answer": "The bottle is above the apple.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above or below the apple?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dining table is below the cup."
} | {
"answer": "The dining table is below the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dining table above or below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dog is to the left of the cell phone."
} | {
"answer": "The dog is to the left of the cell phone.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"i... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog to the left or right of the cell phone?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "us... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The cell phone is above the bird."
} | {
"answer": "The cell phone is above the bird.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pat... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cell phone above or below the bird?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the bird is below the dog."
} | {
"answer": "Yes, the bird is below the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bird below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The truck is above the fire hydrant."
} | {
"answer": "The truck is above the fire hydrant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the truck above or below the fire hydrant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the truck is above the stop sign."
} | {
"answer": "Yes, the truck is above the stop sign.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"imag... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the truck above the stop sign?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the fire hydrant is not to the left of the stop sign."
} | {
"answer": "No, the fire hydrant is not to the left of the stop sign.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targ... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the fire hydrant to the left of the stop sign?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "use... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is on the right side of the bottle."
} | {
"answer": "The sink is on the right side of the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink on the left or right side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bottle is below the dog."
} | {
"answer": "The bottle is below the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the bottle is not above the backpack."
} | {
"answer": "No, the bottle is not above the backpack.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"i... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dog is to the right of the backpack."
} | {
"answer": "The dog is to the right of the backpack.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"im... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog to the left or right of the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the handbag is on the right side of the dog."
} | {
"answer": "Yes, the handbag is on the right side of the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag on the right side of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The stop sign is above the person."
} | {
"answer": "The stop sign is above the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the stop sign above or below the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the clock is not on the left side of the bottle."
} | {
"answer": "No, the clock is not on the left side of the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the clock on the left side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The dog is to the left of the person."
} | {
"answer": "The dog is to the left of the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog to the left or right of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the oven is not above the cup."
} | {
"answer": "No, the oven is not above the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven above the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bowl is on the left side of the laptop."
} | {
"answer": "The bowl is on the left side of the laptop.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the left or right side of the laptop?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The cup is on the left side of the microwave."
} | {
"answer": "The cup is on the left side of the microwave.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup on the left or right side of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role":... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the cup is above the dog."
} | {
"answer": "Yes, the cup is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the surfboard is not to the right of the dog."
} | {
"answer": "No, the surfboard is not to the right of the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the surfboard to the right of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The clock is above the handbag."
} | {
"answer": "The clock is above the handbag.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the clock above or below the handbag?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the dog is not above the backpack."
} | {
"answer": "No, the dog is not above the backpack.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"imag... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog above the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The person is above the dog."
} | {
"answer": "The person is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the person above or below the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the motorcycle is to the left of the chair."
} | {
"answer": "Yes, the motorcycle is to the left of the chair.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tru... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the motorcycle to the left of the chair?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the dog is to the left of the person."
} | {
"answer": "Yes, the dog is to the left of the person.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog to the left of the person?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the handbag is above the dog."
} | {
"answer": "Yes, the handbag is above the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag above the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the dog is on the right side of the car."
} | {
"answer": "Yes, the dog is on the right side of the car.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dog on the right side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the bowl is to the left of the dog."
} | {
"answer": "Yes, the bowl is to the left of the dog.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"im... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl to the left of the dog?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The handbag is below the backpack."
} | {
"answer": "The handbag is below the backpack.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag above or below the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the backpack is on the left side of the car."
} | {
"answer": "Yes, the backpack is on the left side of the car.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the backpack on the left side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the handbag is to the left of the car."
} | {
"answer": "Yes, the handbag is to the left of the car.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the handbag to the left of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the microwave is above the bottle."
} | {
"answer": "Yes, the microwave is above the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"ima... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the microwave above the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bottle is below the clock."
} | {
"answer": "The bottle is below the clock.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above or below the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is above the bottle."
} | {
"answer": "The sink is above the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": ... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The vase is above the toilet."
} | {
"answer": "The vase is above the toilet.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": ... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the vase above or below the toilet?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the sink is not above the clock."
} | {
"answer": "No, the sink is not above the clock.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the cup is not above the sink."
} | {
"answer": "No, the cup is not above the sink.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup above the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the microwave is on the right side of the bottle."
} | {
"answer": "Yes, the microwave is on the right side of the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the microwave on the right side of the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "use... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the oven is not below the cup."
} | {
"answer": "No, the oven is not below the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The oven is below the cup."
} | {
"answer": "The oven is below the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "co... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven above or below the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The cup is above the orange."
} | {
"answer": "The cup is above the orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup above or below the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the oven is on the right side of the orange."
} | {
"answer": "Yes, the oven is on the right side of the orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven on the right side of the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The chair is below the sink."
} | {
"answer": "The chair is below the sink.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the chair above or below the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the sink is not to the right of the toaster."
} | {
"answer": "No, the sink is not to the right of the toaster.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tru... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink to the right of the toaster?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the bowl is on the right side of the wine glass."
} | {
"answer": "Yes, the bowl is on the right side of the wine glass.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the right side of the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The wine glass is below the bottle."
} | {
"answer": "The wine glass is below the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_p... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the wine glass above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the bottle is not above the scissors."
} | {
"answer": "No, the bottle is not above the scissors.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"i... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above the scissors?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The oven is below the wine glass."
} | {
"answer": "The oven is below the wine glass.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pat... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven above or below the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the potted plant is not below the wine glass."
} | {
"answer": "No, the potted plant is not below the wine glass.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the potted plant below the wine glass?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the oven is below the potted plant."
} | {
"answer": "Yes, the oven is below the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"im... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the potted plant is below the orange."
} | {
"answer": "Yes, the potted plant is below the orange.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the potted plant below the orange?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is below the potted plant."
} | {
"answer": "The sink is below the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_p... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above or below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the sink is not below the vase."
} | {
"answer": "No, the sink is not below the vase.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_p... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink below the vase?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the sink is below the microwave."
} | {
"answer": "Yes, the sink is below the microwave.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink below the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The oven is to the right of the microwave."
} | {
"answer": "The oven is to the right of the microwave.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the oven to the left or right of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "us... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the clock is not below the oven."
} | {
"answer": "No, the clock is not below the oven.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the clock below the oven?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the sink is below the clock."
} | {
"answer": "Yes, the sink is below the clock.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pat... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink below the clock?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bowl is on the left side of the sandwich."
} | {
"answer": "The bowl is on the left side of the sandwich.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the left or right side of the sandwich?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role":... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The bowl is on the right side of the sink."
} | {
"answer": "The bowl is on the right side of the sink.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the left or right side of the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "us... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The cup is above the sink."
} | {
"answer": "The cup is above the sink.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "co... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup above or below the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The microwave is above the bottle."
} | {
"answer": "The microwave is above the bottle.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the microwave above or below the bottle?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the bottle is not above the toaster."
} | {
"answer": "No, the bottle is not above the toaster.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"im... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bottle above the toaster?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The truck is to the left of the cup."
} | {
"answer": "The truck is to the left of the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the truck to the left or right of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the cup is not on the left side of the car."
} | {
"answer": "No, the cup is not on the left side of the car.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup on the left side of the car?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the cell phone is not below the backpack."
} | {
"answer": "No, the cell phone is not below the backpack.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cell phone below the backpack?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the dining table is not to the left of the sink."
} | {
"answer": "No, the dining table is not to the left of the sink.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets":... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the dining table to the left of the sink?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the microwave is not on the right side of the dining table."
} | {
"answer": "No, the microwave is not on the right side of the dining table.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"ha... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the microwave on the right side of the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role"... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the sink is not to the left of the microwave."
} | {
"answer": "No, the sink is not to the left of the microwave.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tr... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink to the left of the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is below the potted plant."
} | {
"answer": "The sink is below the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_p... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above or below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the sink is below the bowl."
} | {
"answer": "Yes, the sink is below the bowl.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink below the bowl?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The book is above the vase."
} | {
"answer": "The book is above the vase.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "c... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the book above or below the vase?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is below the bowl."
} | {
"answer": "The sink is below the bowl.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path": "c... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above or below the bowl?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The sink is below the microwave."
} | {
"answer": "The sink is below the microwave.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_path... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink above or below the microwave?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the bowl is on the right side of the potted plant."
} | {
"answer": "Yes, the bowl is on the right side of the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_target... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the right side of the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "us... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the cup is on the right side of the potted plant."
} | {
"answer": "Yes, the cup is on the right side of the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the cup on the right side of the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "use... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the bowl is not on the left side of the cup."
} | {
"answer": "No, the bowl is not on the left side of the cup.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 2,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": tru... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the bowl on the left side of the cup?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "The tie is above the dining table."
} | {
"answer": "The tie is above the dining table.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image_pa... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the tie above or below the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}... | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the vase is not below the dining table."
} | {
"answer": "No, the vase is not below the dining table.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the vase below the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the tie is below the potted plant."
} | {
"answer": "Yes, the tie is below the potted plant.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"ima... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the tie below the potted plant?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "Yes, the clock is above the dining table."
} | {
"answer": "Yes, the clock is above the dining table.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"i... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the clock above the dining table?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 | |
sealvqa_spatial | {
"ground_truth": "No, the sink is not below the toilet."
} | {
"answer": "No, the sink is not below the toilet.",
"bbox_format": "absolute_xywh",
"bbox_format_description": "Bounding boxes use absolute pixel coordinates in [x, y, width, height] format",
"conversation_turns": 4,
"data_split": "train",
"dataset_type": "spatial_relation",
"has_targets": true,
"image... | [
{
"content": "",
"role": "system"
},
{
"content": "<image>\nIs the sink below the toilet?\nThink first, call **image_zoom_in_tool** if needed, then answer. Format strictly as: <think>...</think> <tool_call>...</tool_call> (if tools needed) <answer>...</answer> ",
"role": "user"
}
] | sealvqa_spatial_spatial | visual_toolbox_v2 |
End of preview. Expand in Data Studio
SEAL VQA Spatial Relation Dataset
This dataset contains spatial relation questions from SEAL VQA.
Dataset Information
- Total samples: 26,961
- COCO 2017 only: True
- Random seed: 42
- Image format: Image paths only (no image data embedded)
Abilities
sealvqa_spatial_spatial: 26,961 samples
Bounding Box Format
Format: absolute_xywh
All bounding boxes use absolute pixel coordinates with the format:
[x, y, width, height]
Usage Example
import json
from PIL import Image, ImageDraw
# Load dataset
with open('spatial_data.json', 'r') as f:
dataset = json.load(f)
sample = dataset[0]
image_path = sample['images'][0]
question = sample['extra_info']['question']
answer = sample['extra_info']['answer']
print(f"Q: {question}")
print(f"A: {answer}")
# Draw bounding boxes
image = Image.open(image_path)
draw = ImageDraw.Draw(image)
for instance in sample['extra_info']['target_instances']:
x, y, w, h = instance['bbox']
draw.rectangle([x, y, x + w, y + h], outline='red', width=2)
draw.text((x, y-15), instance['name'], fill='red')
Generation Command
python build_spatial_dataset.py \
--num_samples 999999 \
--seed 42 \
--coco_only
- Downloads last month
- 10