Physical AI
Collection
Collection of open, commercial-grade datasets for physical AI developers • 54 items • Updated • 174
id stringlengths 15 18 | task stringclasses 1
value | category stringclasses 1
value | media stringlengths 34 34 | conversations listlengths 1 1 | _meta dict |
|---|---|---|---|---|---|
refdrone_test_0 | referring_expressions | Transportation | images/0000189_00297_d_0000198.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white vans parked on the left side of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 0,
"sentence": "The white vans parked on the left side of the road.",
"object_category": "truck",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_1 | referring_expressions | Transportation | images/0000189_00297_d_0000198.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars traveling on the right side of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 1,
"sentence": "The black cars traveling on the right side of the road.",
"object_category": "van",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_2 | referring_expressions | Transportation | images/9999938_00000_d_0000273.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars in the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 2,
"sentence": "The red cars in the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_3 | referring_expressions | Transportation | images/9999938_00000_d_0000273.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white vans parked in the parking lot adjacent to the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 3,
"sentence": "The white vans parked in the parking lot adjacent to the road.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_4 | referring_expressions | Transportation | images/9999938_00000_d_0000273.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars moving on the main road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 4,
"sentence": "The black cars moving on the main road.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_5 | referring_expressions | Transportation | images/9999963_00000_d_0000059.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars at the left side of the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 5,
"sentence": "The cars at the left side of the intersection.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_6 | referring_expressions | Transportation | images/9999963_00000_d_0000059.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses near the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 6,
"sentence": "The buses near the intersection.",
"object_category": "motor",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_7 | referring_expressions | Transportation | images/9999963_00000_d_0000026.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars park near the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 7,
"sentence": "The black cars park near the intersection.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_8 | referring_expressions | Transportation | images/9999952_00000_d_0000205.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses on the elevated highway.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 8,
"sentence": "The buses on the elevated highway.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_9 | referring_expressions | Transportation | images/9999952_00000_d_0000205.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars and buses below the elevated highway in a well-lit area.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 9,
"sentence": "The cars and buses below the elevated highway in a well-lit area.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_10 | referring_expressions | Transportation | images/9999952_00000_d_0000089.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus is located near the top right of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 10,
"sentence": "The bus is located near the top right of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_11 | referring_expressions | Transportation | images/9999952_00000_d_0000089.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The van is positioned near the middle section of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 11,
"sentence": "The van is positioned near the middle section of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_12 | referring_expressions | Transportation | images/9999979_00000_d_0000034.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars are scattered throughout the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 12,
"sentence": "The red cars are scattered throughout the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_13 | referring_expressions | Transportation | images/9999979_00000_d_0000034.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The blue van is located on right sides of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 13,
"sentence": "The blue van is located on right sides of the road.",
"object_category": "truck",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_14 | referring_expressions | Transportation | images/9999952_00000_d_0000250.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car on the bridge.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 14,
"sentence": "The car on the bridge.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_15 | referring_expressions | Transportation | images/9999952_00000_d_0000250.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car traveling below the bridge.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 15,
"sentence": "The car traveling below the bridge.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_16 | referring_expressions | Transportation | images/9999952_00000_d_0000250.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car near the center-left corner of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 16,
"sentence": "The car near the center-left corner of the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_17 | referring_expressions | Transportation | images/9999952_00000_d_0000250.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car in the bottom right quadrant of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 17,
"sentence": "The car in the bottom right quadrant of the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_18 | referring_expressions | Transportation | images/9999952_00000_d_0000315.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses parked in rows.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 18,
"sentence": "The buses parked in rows.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_19 | referring_expressions | Transportation | images/9999952_00000_d_0000315.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians near the bottom left of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 19,
"sentence": "The pedestrians near the bottom left of the image.",
"object_category": "people",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_21 | referring_expressions | Transportation | images/9999938_00000_d_0000255.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The people gathered in the seating area near the building.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 21,
"sentence": "The people gathered in the seating area near the building.",
"object_category": "bicycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_22 | referring_expressions | Transportation | images/9999938_00000_d_0000255.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars driving on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 22,
"sentence": "The black cars driving on the road.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_23 | referring_expressions | Transportation | images/0000074_08777_d_0000017.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus is located in the middle of the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 23,
"sentence": "The bus is located in the middle of the street.",
"object_category": "motor",
"image_width": 1920,
"image_height": 1080,
"is_no_target": false
} |
refdrone_test_24 | referring_expressions | Transportation | images/9999973_00000_d_0000109.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars park at the bottom right and top right of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 24,
"sentence": "The red cars park at the bottom right and top right of the image.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_25 | referring_expressions | Transportation | images/9999938_00000_d_0000484.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus is located near the bottom center of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 25,
"sentence": "The bus is located near the bottom center of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_26 | referring_expressions | Transportation | images/9999938_00000_d_0000484.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car is moving near the bottom right corner of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 26,
"sentence": "The car is moving near the bottom right corner of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_27 | referring_expressions | Transportation | images/0000302_03866_d_0000117.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park on both sides of the main road and at the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 27,
"sentence": "The white cars park on both sides of the main road and at the intersection.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_28 | referring_expressions | Transportation | images/0000302_03866_d_0000117.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars are scattered around the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 28,
"sentence": "The red cars are scattered around the intersection.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_31 | referring_expressions | Transportation | images/9999952_00000_d_0000040.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The truck is located near the center bottom of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 31,
"sentence": "The truck is located near the center bottom of the image.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_32 | referring_expressions | Transportation | images/9999952_00000_d_0000040.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus is in the middle lane near the right side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 32,
"sentence": "The bus is in the middle lane near the right side of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_33 | referring_expressions | Transportation | images/9999952_00000_d_0000040.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The van is parked near the left of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 33,
"sentence": "The van is parked near the left of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_34 | referring_expressions | Transportation | images/9999938_00000_d_0000431.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus is located near the right edge of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 34,
"sentence": "The bus is located near the right edge of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_35 | referring_expressions | Transportation | images/9999938_00000_d_0000431.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The van is parked on the left side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 35,
"sentence": "The van is parked on the left side of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_36 | referring_expressions | Transportation | images/9999952_00000_d_0000131.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses on the curved road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 36,
"sentence": "The buses on the curved road.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_37 | referring_expressions | Transportation | images/9999952_00000_d_0000131.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The trucks near the center right of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 37,
"sentence": "The trucks near the center right of the image.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_38 | referring_expressions | Transportation | images/9999952_00000_d_0000339.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars navigating the roundabout.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 38,
"sentence": "The cars navigating the roundabout.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_39 | referring_expressions | Transportation | images/9999952_00000_d_0000339.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars on the road to the right of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 39,
"sentence": "The cars on the road to the right of the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_40 | referring_expressions | Transportation | images/9999952_00000_d_0000264.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The trucks are located near the bottom left corner of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 40,
"sentence": "The trucks are located near the bottom left corner of the image.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_41 | referring_expressions | Transportation | images/9999938_00000_d_0000365.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars travel on the elevated highways.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 41,
"sentence": "The red cars travel on the elevated highways.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_42 | referring_expressions | Transportation | images/9999938_00000_d_0000365.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black vans are located near the bottom of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 42,
"sentence": "The black vans are located near the bottom of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_43 | referring_expressions | Transportation | images/9999938_00000_d_0000365.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white van is positioned at the top center of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 43,
"sentence": "The white van is positioned at the top center of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_44 | referring_expressions | Transportation | images/0000337_04362_d_0000045.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars moving on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 44,
"sentence": "The red cars moving on the road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_45 | referring_expressions | Transportation | images/0000337_04362_d_0000045.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars parked along the sides of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 45,
"sentence": "The black cars parked along the sides of the road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_46 | referring_expressions | Transportation | images/9999938_00000_d_0000199.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 46,
"sentence": "The red cars on the road.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_47 | referring_expressions | Transportation | images/9999938_00000_d_0000199.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white buses and trucks.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 47,
"sentence": "The white buses and trucks.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_48 | referring_expressions | Transportation | images/9999973_00000_d_0000001.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park along the street in front of the buildings.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 48,
"sentence": "The white cars park along the street in front of the buildings.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_49 | referring_expressions | Transportation | images/9999976_00000_d_0000031.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The people driving bicycle is near the crosswalk.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 49,
"sentence": "The people driving bicycle is near the crosswalk.",
"object_category": "bicycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_50 | referring_expressions | Transportation | images/9999976_00000_d_0000031.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black pedestrian is walking along the sidewalk.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 50,
"sentence": "The black pedestrian is walking along the sidewalk.",
"object_category": "people",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_51 | referring_expressions | Transportation | images/9999973_00000_d_0000061.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The green trucks park near the center of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 51,
"sentence": "The green trucks park near the center of the image.",
"object_category": "tricycle",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_52 | referring_expressions | Transportation | images/9999973_00000_d_0000061.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park in the central parking area.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 52,
"sentence": "The white cars park in the central parking area.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_53 | referring_expressions | Transportation | images/9999938_00000_d_0000116.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians on the left sidewalk.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 53,
"sentence": "The pedestrians on the left sidewalk.",
"object_category": "people",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_54 | referring_expressions | Transportation | images/9999938_00000_d_0000116.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrian in the overpass.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 54,
"sentence": "The pedestrian in the overpass.",
"object_category": "people",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_55 | referring_expressions | Transportation | images/9999963_00000_d_0000044.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars are driving on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 55,
"sentence": "The red cars are driving on the road.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_56 | referring_expressions | Transportation | images/9999963_00000_d_0000044.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians walk near each other along the sidewalks.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 56,
"sentence": "The pedestrians walk near each other along the sidewalks.",
"object_category": "people",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_57 | referring_expressions | Transportation | images/0000321_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars in the parking lot.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 57,
"sentence": "The red cars in the parking lot.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_58 | referring_expressions | Transportation | images/0000321_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The blue cars parked near the shopping center.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 58,
"sentence": "The blue cars parked near the shopping center.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_59 | referring_expressions | Transportation | images/0000321_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars on the main road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 59,
"sentence": "The black cars on the main road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_60 | referring_expressions | Transportation | images/0000321_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red buses on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 60,
"sentence": "The red buses on the road.",
"object_category": "motor",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_61 | referring_expressions | Transportation | images/9999952_00000_d_0000047.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars in the parking lot.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 61,
"sentence": "The cars in the parking lot.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_62 | referring_expressions | Transportation | images/9999952_00000_d_0000047.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The trucks parked near the bottom center of the parking area.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 62,
"sentence": "The trucks parked near the bottom center of the parking area.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_63 | referring_expressions | Transportation | images/0000074_13875_d_0000027.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars on the right street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 63,
"sentence": "The cars on the right street.",
"object_category": "van",
"image_width": 1920,
"image_height": 1080,
"is_no_target": false
} |
refdrone_test_66 | referring_expressions | Transportation | images/9999976_00000_d_0000005.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park near the multi-story buildings.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 66,
"sentence": "The white cars park near the multi-story buildings.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_67 | referring_expressions | Transportation | images/0000183_00031_d_0000176.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars on the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 67,
"sentence": "The black cars on the road.",
"object_category": "van",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_68 | referring_expressions | Transportation | images/0000183_00031_d_0000176.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black car moving through the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 68,
"sentence": "The black car moving through the intersection.",
"object_category": "van",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_69 | referring_expressions | Transportation | images/0000183_00031_d_0000176.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The motorcycles moving through the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 69,
"sentence": "The motorcycles moving through the intersection.",
"object_category": "others",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_70 | referring_expressions | Transportation | images/9999952_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The truck near the bottom left of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 70,
"sentence": "The truck near the bottom left of the image.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_71 | referring_expressions | Transportation | images/9999952_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car parked at the top side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 71,
"sentence": "The car parked at the top side of the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_72 | referring_expressions | Transportation | images/9999952_00000_d_0000058.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses are located on the top right corner of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 72,
"sentence": "The buses are located on the top right corner of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_73 | referring_expressions | Transportation | images/9999952_00000_d_0000058.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The cars are spread out along the highway.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 73,
"sentence": "The cars are spread out along the highway.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_74 | referring_expressions | Transportation | images/0000074_07297_d_0000014.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The blue cars park on the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 74,
"sentence": "The blue cars park on the street.",
"object_category": "van",
"image_width": 1920,
"image_height": 1080,
"is_no_target": false
} |
refdrone_test_75 | referring_expressions | Transportation | images/0000272_00000_d_0000001.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars park on the left side of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 75,
"sentence": "The red cars park on the left side of the road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_76 | referring_expressions | Transportation | images/0000272_00000_d_0000001.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars travel along the main road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 76,
"sentence": "The white cars travel along the main road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_77 | referring_expressions | Transportation | images/9999938_00000_d_0000334.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars in the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 77,
"sentence": "The red cars in the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_78 | referring_expressions | Transportation | images/9999938_00000_d_0000334.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars on the highway.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 78,
"sentence": "The black cars on the highway.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_79 | referring_expressions | Transportation | images/9999938_00000_d_0000334.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The blue vehicles near the top left corner.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 79,
"sentence": "The blue vehicles near the top left corner.",
"object_category": "tricycle",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_80 | referring_expressions | Transportation | images/9999993_00000_d_0000011.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The blue vehicle is scattered along the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 80,
"sentence": "The blue vehicle is scattered along the street.",
"object_category": "motor",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_81 | referring_expressions | Transportation | images/9999993_00000_d_0000011.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red car is positioned towards the bottom right.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 81,
"sentence": "The red car is positioned towards the bottom right.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_82 | referring_expressions | Transportation | images/9999973_00000_d_0000074.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars parked along the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 82,
"sentence": "The red cars parked along the street.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_83 | referring_expressions | Transportation | images/9999973_00000_d_0000074.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white vans on right side of the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 83,
"sentence": "The white vans on right side of the road.",
"object_category": "truck",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_84 | referring_expressions | Transportation | images/9999941_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The green vans are on the left side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 84,
"sentence": "The green vans are on the left side of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_85 | referring_expressions | Transportation | images/9999941_00000_d_0000015.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white vans are moving through the crosswalk.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 85,
"sentence": "The white vans are moving through the crosswalk.",
"object_category": "van",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_86 | referring_expressions | Transportation | images/9999973_00000_d_0000048.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars park along the road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 86,
"sentence": "The red cars park along the road.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_87 | referring_expressions | Transportation | images/9999973_00000_d_0000048.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park on both sides of the main road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 87,
"sentence": "The white cars park on both sides of the main road.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_88 | referring_expressions | Transportation | images/9999973_00000_d_0000051.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars are parked and moving along the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 88,
"sentence": "The red cars are parked and moving along the street.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_89 | referring_expressions | Transportation | images/9999963_00000_d_0000075.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars in the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 89,
"sentence": "The red cars in the image.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_90 | referring_expressions | Transportation | images/9999963_00000_d_0000075.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus in the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 90,
"sentence": "The bus in the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_91 | referring_expressions | Transportation | images/9999963_00000_d_0000075.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians near the brightly lit storefronts on the right side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 91,
"sentence": "The pedestrians near the brightly lit storefronts on the right side of the image.",
"object_category": "people",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_92 | referring_expressions | Transportation | images/9999973_00000_d_0000058.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The white cars park on the upper side of the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 92,
"sentence": "The white cars park on the upper side of the street.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_93 | referring_expressions | Transportation | images/9999973_00000_d_0000058.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars park on the upper side of the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 93,
"sentence": "The black cars park on the upper side of the street.",
"object_category": "van",
"image_width": 1916,
"image_height": 1078,
"is_no_target": false
} |
refdrone_test_94 | referring_expressions | Transportation | images/0000087_00009_d_0000001.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians in green are scattered throughout the area.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 94,
"sentence": "The pedestrians in green are scattered throughout the area.",
"object_category": "bicycle",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_95 | referring_expressions | Transportation | images/0000087_00009_d_0000001.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrian in yellow is near the center of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 95,
"sentence": "The pedestrian in yellow is near the center of the image.",
"object_category": "people",
"image_width": 960,
"image_height": 540,
"is_no_target": false
} |
refdrone_test_96 | referring_expressions | Transportation | images/9999952_00000_d_0000334.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The buses navigating the roundabout.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 96,
"sentence": "The buses navigating the roundabout.",
"object_category": "motor",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_97 | referring_expressions | Transportation | images/9999952_00000_d_0000334.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The van near the top center of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 97,
"sentence": "The van near the top center of the image.",
"object_category": "truck",
"image_width": 1400,
"image_height": 788,
"is_no_target": false
} |
refdrone_test_98 | referring_expressions | Transportation | images/0000320_00900_d_0000008.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The yellow cars in the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 98,
"sentence": "The yellow cars in the image.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_99 | referring_expressions | Transportation | images/0000320_00900_d_0000008.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars navigating through the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 99,
"sentence": "The black cars navigating through the intersection.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_100 | referring_expressions | Transportation | images/0000320_00900_d_0000008.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The pedestrians crossing the street.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 100,
"sentence": "The pedestrians crossing the street.",
"object_category": "people",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_101 | referring_expressions | Transportation | images/0000272_01500_d_0000004.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The red cars park on the left side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 101,
"sentence": "The red cars park on the left side of the image.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_102 | referring_expressions | Transportation | images/0000272_01500_d_0000004.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The black cars park along the main road.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 102,
"sentence": "The black cars park along the main road.",
"object_category": "van",
"image_width": 1360,
"image_height": 765,
"is_no_target": false
} |
refdrone_test_103 | referring_expressions | Transportation | images/9999963_00000_d_0000057.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The bus on the bottom left side of the image.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 103,
"sentence": "The bus on the bottom left side of the image.",
"object_category": "motor",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
refdrone_test_104 | referring_expressions | Transportation | images/9999963_00000_d_0000057.jpg | [
{
"from": "human",
"value": "<image>\nLocate every instance described by the following expression: \"The car in the center of the intersection.\". Output the bounding box coordinates of each instance in JSON format as a list of [x1, y1, x2, y2] values."
}
] | {
"source": "RefDrone",
"split": "test",
"expression_id": 104,
"sentence": "The car in the center of the intersection.",
"object_category": "van",
"image_width": 1400,
"image_height": 1050,
"is_no_target": false
} |
End of preview. Expand in Data Studio
VANTAGE-BENCH
Video ANalysis Tasks Across Generalized Environments
Dataset Description
VANTAGE-BENCH is the first public benchmark purpose-built for evaluating visual understanding on video captured by fixed infrastructure cameras. It spans three real-world domains — warehouse, smart city / Intelligent Transportation Systems (ITS), and smart spaces — across six spatio-temporal video understanding tasks including video question answering (VQA), temporal grounding, dense video captioning, event verification, spatial grounding, and spatio-temporal tracking.
This dataset is for evaluation purposes only.
Dataset Owner(s)
NVIDIA Corporation
Dataset Creation Date
April 24, 2026
License/Terms of Use
This dataset is released under the NVIDIA Evaluation Data License.
Dataset Characterization
Data Collection Method
Hybrid: Human, Synthetic, Automated. Video data is sourced from vendor-provided footage (GoPro captures of warehouse and smart space environments), synthetic generation (DriveSim collision and multi-camera scenarios), and publicly scraped sources (Dubuque highway/ITS footage).
Labeling Method
Hybrid: Human, Synthetic, Pseudolabeled. Annotations for VQA, dense video captions, and temporal localization are primarily human-authored. Spatial grounding labels (2D/3D bounding boxes, referring expressions) use a combination of human annotation and pseudolabeling pipelines (detection + SAM for spatial pointing). Event verification labels are human-curated. Annotations are held server-side for evaluation only.
Directory Structure
VANTAGE-BENCH/
├── vqa/ # Video question answering
├── dense_captioning/ # Dense video captioning
├── temporal_localization/ # Temporal localization
├── event_verification/ # Event verification
├── 2dbbox/ # 2D object localization
├── referring/ # 2D referring expressions
├── pointing/ # 2D spatial pointing
├── tracking/ # Spatio-temporal tracking
└── README.md # Dataset documentation and submission instructions
Evaluation
Tasks and Submission Formats
| Category | Task | Metric |
|---|---|---|
| Semantic | VQA | Accuracy |
| Semantic | Event Verification | Macro F1 |
| Temporal | Dense Video Captioning | SODA-c |
| Temporal | Temporal Localization | mIoU |
| Spatial | 2D Object Localization | F1@0.5 |
| Spatial | 2D Referring Expressions | mIoU |
| Spatial | 2D Spatial Pointing | Accuracy |
| Spatio-Temporal | Single Object Tracking | AUC |
Submit predictions via the VANTAGE-Bench submission portal and track results on the official leaderboard.
Metric Notes
- Accuracy: Percentage of correct predictions.
- SODA-c: Metric for dense video captioning quality across event coverage and language quality.
- Macro F1: Unweighted mean of per-class F1 scores.
- F1@0.5: F1 score at an IoU threshold of 0.5.
- mIoU: Mean Intersection over Union — average overlap between predicted and ground-truth regions (spatial bounding boxes or temporal segments, depending on the task).
- AUC: Area under the ROC curve, measuring the model's ability to distinguish correct detections or tracks from incorrect ones across varying confidence thresholds.
Evaluation Server
The VANTAGE-Bench GitHub repository provides a sample evaluation pipeline for generating model predictions. Predictions are submitted through the submission portal and scored on the official leaderboard.
Dataset Format
Video (mp4) and Images (jpg).
Dataset Quantification
| Category | Task | Media | Entries |
|---|---|---|---|
| Semantic | VQA | 282 videos | 1,195 QAs (MCQ) |
| Semantic | Event Verification | 163 videos | 163 QAs (BCQ) |
| Temporal | Dense Video Captioning | 104 videos | 717 Events |
| Temporal | Temporal Localization | 203 videos | 1,067 Segments / Spans |
| Spatial | 2D Object Localization | 628 images (3 video sequences) | 27,404 Bboxes |
| Spatial | 2D Referring Expressions | 1,503 images | 3,276 Expressions |
| Spatial | 2D Spatial Pointing | 361 images | 1,005 QAs (MCQ) |
| Spatio-Temporal | Single Object Tracking | 102 video clips | 200 Trajectories |
Total Entries (Annotations): 35,027 Total Media Samples (across tasks, with overlaps): 3,346 Total Data Storage: 42 GB
Potential Known Risks
- Ground truth annotations are not publicly released. All evaluation is performed server-side.
- Some warehouse videos are concatenated clips from longer recording sessions.
Citations
@inproceedings{Fujita2020SODA,
author = {Soichiro Fujita and Tsutomu Hirao and Hidetaka Kamigaito and Manabu Okumura and Masaaki Nagata},
title = {{SODA}: Story Oriented Dense Video Captioning Evaluation Framework},
booktitle = {Proc. ECCV},
year = {2020}
}
@inproceedings{Fu2024BLINK,
author = {Xingyu Fu and Yushi Hu and Bangzheng Li and Yu Feng and Haoyu Wang and Xudong Lin and Dan Roth and Noah A. Smith and Wei-Chiu Ma and Ranjay Krishna},
title = {{BLINK}: Multimodal Large Language Models Can See but Not Perceive},
booktitle = {Proc. ECCV},
year = {2024}
}
@article{Sun2025RefDrone,
author = {Zhichao Sun and Yuda Zou and Xian Sun and Yingchao Feng and Wenhui Diao and Menglong Yan and Kun Fu},
title = {{RefDrone}: A Challenging Benchmark for Referring Expression Comprehension in Drone Scenes},
journal = {arXiv preprint arXiv:2502.00392},
year = {2025}
}
References
- HuggingFace dataset: nvidia/PhysicalAI-VANTAGE-Bench
- Project website: vantage-bench.org
Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal developer teams to ensure this dataset meets requirements for the relevant industry and use case and addresses unforeseen product misuse. Please report quality, risk, security vulnerabilities or NVIDIA AI Concerns here.
Changelog
See CHANGELOG.md for release history.
- Downloads last month
- 1,332