[{"file_name": "COCO_train2014_000000423710.jpg", "question": "Where is the tissue?", "label": "ambiguous", "size": {"width": 375, "height": 500}, "focus_areas": ["COCO_train2014_000000423710_ambiguous_0.png", "COCO_train2014_000000423710_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 6, "id_source": "coco_data_pos.json"}, "set": "train", "id": 0, "masks_id": "00000000"}, {"file_name": "COCO_train2014_000000539535.jpg", "question": "What are on?", "label": "ambiguous", "size": {"width": 640, "height": 427}, "focus_areas": ["COCO_train2014_000000539535_ambiguous_0.png", "COCO_train2014_000000539535_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 7, "id_source": "coco_data_pos.json"}, "set": "train", "id": 1, "masks_id": "00000001"}, {"file_name": "COCO_train2014_000000488135.jpg", "question": "What time does the clock say?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000488135_ambiguous_0.png", "COCO_train2014_000000488135_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 9, "id_source": "coco_data_pos.json"}, "set": "train", "id": 2, "masks_id": "00000002"}, {"file_name": "COCO_train2014_000000208594.jpg", "question": "What is the man in the image's job?", "label": "ambiguous", "size": {"width": 640, "height": 426}, "focus_areas": ["COCO_train2014_000000208594_ambiguous_0.png", "COCO_train2014_000000208594_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 18, "id_source": "coco_data_pos.json"}, "set": "train", "id": 3, "masks_id": "00000003"}, {"file_name": "COCO_train2014_000000442686.jpg", "question": "What color is the umbrella?", "label": "ambiguous", "size": {"width": 640, "height": 426}, "focus_areas": ["COCO_train2014_000000442686_ambiguous_0.png", "COCO_train2014_000000442686_ambiguous_1.png", "COCO_train2014_000000442686_ambiguous_2.png", "COCO_train2014_000000442686_ambiguous_3.png", "COCO_train2014_000000442686_ambiguous_4.png", "COCO_train2014_000000442686_ambiguous_5.png", "COCO_train2014_000000442686_ambiguous_6.png", "COCO_train2014_000000442686_ambiguous_7.png", "COCO_train2014_000000442686_ambiguous_8.png", "COCO_train2014_000000442686_ambiguous_9.png", "COCO_train2014_000000442686_ambiguous_10.png", "COCO_train2014_000000442686_ambiguous_11.png", "COCO_train2014_000000442686_ambiguous_12.png", "COCO_train2014_000000442686_ambiguous_13.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 20, "id_source": "coco_data_pos.json"}, "set": "train", "id": 4, "masks_id": "00000004"}, {"file_name": "COCO_train2014_000000320386.jpg", "question": "What else is visible?", "label": "ambiguous", "size": {"width": 640, "height": 462}, "focus_areas": ["COCO_train2014_000000320386_ambiguous_0.png", "COCO_train2014_000000320386_ambiguous_1.png", "COCO_train2014_000000320386_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 30, "id_source": "coco_data_pos.json"}, "set": "train", "id": 5, "masks_id": "00000005"}, {"file_name": "COCO_train2014_000000510531.jpg", "question": "What kind of scarf is the girl wearing?", "label": "ambiguous", "size": {"width": 500, "height": 375}, "focus_areas": ["COCO_train2014_000000510531_ambiguous_0.png", "COCO_train2014_000000510531_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 58, "id_source": "coco_data_pos.json"}, "set": "train", "id": 6, "masks_id": "00000006"}, {"file_name": "COCO_train2014_000000466890.jpg", "question": "What is the design of the woman's shirt?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000466890_ambiguous_0.png", "COCO_train2014_000000466890_ambiguous_1.png", "COCO_train2014_000000466890_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 66, "id_source": "coco_data_pos.json"}, "set": "train", "id": 7, "masks_id": "00000007"}, {"file_name": "COCO_train2014_000000160535.jpg", "question": "What color is his kite?", "label": "ambiguous", "size": {"width": 640, "height": 426}, "focus_areas": ["COCO_train2014_000000160535_ambiguous_0.png", "COCO_train2014_000000160535_ambiguous_1.png", "COCO_train2014_000000160535_ambiguous_2.png", "COCO_train2014_000000160535_ambiguous_3.png", "COCO_train2014_000000160535_ambiguous_4.png", "COCO_train2014_000000160535_ambiguous_5.png", "COCO_train2014_000000160535_ambiguous_6.png", "COCO_train2014_000000160535_ambiguous_7.png", "COCO_train2014_000000160535_ambiguous_8.png", "COCO_train2014_000000160535_ambiguous_9.png", "COCO_train2014_000000160535_ambiguous_10.png", "COCO_train2014_000000160535_ambiguous_11.png", "COCO_train2014_000000160535_ambiguous_12.png", "COCO_train2014_000000160535_ambiguous_13.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 74, "id_source": "coco_data_pos.json"}, "set": "train", "id": 8, "masks_id": "00000008"}, {"file_name": "COCO_train2014_000000215298.jpg", "question": "What type of tree is on the right?", "label": "ambiguous", "size": {"width": 640, "height": 424}, "focus_areas": ["COCO_train2014_000000215298_ambiguous_0.png", "COCO_train2014_000000215298_ambiguous_1.png", "COCO_train2014_000000215298_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 82, "id_source": "coco_data_pos.json"}, "set": "train", "id": 9, "masks_id": "00000009"}, {"file_name": "COCO_train2014_000000051434.jpg", "question": "How many pieces of broccoli are there in the dinner?", "label": "unambiguous", "size": {"width": 612, "height": 612}, "focus_areas": ["COCO_train2014_000000051434_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 13, "id_source": "coco_data_neg.json"}, "set": "train", "id": 10, "masks_id": "00000010"}, {"file_name": "COCO_train2014_000000063875.jpg", "question": "What is the giraffe being fed?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000063875_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 15, "id_source": "coco_data_neg.json"}, "set": "train", "id": 11, "masks_id": "00000011"}, {"file_name": "COCO_train2014_000000178637.jpg", "question": "What sort of bread is this?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000178637_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 23, "id_source": "coco_data_neg.json"}, "set": "train", "id": 12, "masks_id": "00000012"}, {"file_name": "COCO_train2014_000000038213.jpg", "question": "What color is the animal?", "label": "unambiguous", "size": {"width": 500, "height": 375}, "focus_areas": ["COCO_train2014_000000038213_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 32, "id_source": "coco_data_neg.json"}, "set": "train", "id": 13, "masks_id": "00000013"}, {"file_name": "COCO_train2014_000000076802.jpg", "question": "Where is the house located?", "label": "unambiguous", "size": {"width": 640, "height": 427}, "focus_areas": ["COCO_train2014_000000076802_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 36, "id_source": "coco_data_neg.json"}, "set": "train", "id": 14, "masks_id": "00000014"}, {"file_name": "COCO_train2014_000000480059.jpg", "question": "What is being held?", "label": "unambiguous", "size": {"width": 500, "height": 375}, "focus_areas": ["COCO_train2014_000000480059_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 40, "id_source": "coco_data_neg.json"}, "set": "train", "id": 15, "masks_id": "00000015"}, {"file_name": "COCO_train2014_000000171967.jpg", "question": "What type of hat is the batter wearing?", "label": "unambiguous", "size": {"width": 640, "height": 448}, "focus_areas": ["COCO_train2014_000000171967_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 48, "id_source": "coco_data_neg.json"}, "set": "train", "id": 16, "masks_id": "00000016"}, {"file_name": "COCO_train2014_000000428018.jpg", "question": "What is on the counter?", "label": "unambiguous", "size": {"width": 640, "height": 424}, "focus_areas": ["COCO_train2014_000000428018_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 54, "id_source": "coco_data_neg.json"}, "set": "train", "id": 17, "masks_id": "00000017"}, {"file_name": "COCO_train2014_000000163715.jpg", "question": "What color is the cat?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000163715_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 58, "id_source": "coco_data_neg.json"}, "set": "train", "id": 18, "masks_id": "00000018"}, {"file_name": "COCO_train2014_000000033649.jpg", "question": "What are the animals standing on?", "label": "unambiguous", "size": {"width": 500, "height": 376}, "focus_areas": ["COCO_train2014_000000033649_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 75, "id_source": "coco_data_neg.json"}, "set": "train", "id": 19, "masks_id": "00000019"}, {"file_name": "VizWiz_train_00018132.jpg", "question": "What is that?", "label": "ambiguous", "size": {"width": 360, "height": 480}, "focus_areas": ["VizWiz_train_00018132_ambiguous_0.png", "VizWiz_train_00018132_ambiguous_1.png", "VizWiz_train_00018132_ambiguous_2.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 10, "id_source": "viz_data_pos.json"}, "set": "train", "id": 20, "masks_id": "00000020"}, {"file_name": "VizWiz_train_00001924.jpg", "question": "What's this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00001924_ambiguous_0.png", "VizWiz_train_00001924_ambiguous_1.png", "VizWiz_train_00001924_ambiguous_2.png", "VizWiz_train_00001924_ambiguous_3.png", "VizWiz_train_00001924_ambiguous_4.png", "VizWiz_train_00001924_ambiguous_5.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 12, "id_source": "viz_data_pos.json"}, "set": "train", "id": 21, "masks_id": "00000021"}, {"file_name": "VizWiz_train_00011025.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00011025_ambiguous_0.png", "VizWiz_train_00011025_ambiguous_1.png", "VizWiz_train_00011025_ambiguous_2.png", "VizWiz_train_00011025_ambiguous_3.png", "VizWiz_train_00011025_ambiguous_4.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 29, "id_source": "viz_data_pos.json"}, "set": "train", "id": 22, "masks_id": "00000022"}, {"file_name": "VizWiz_train_00016173.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00016173_ambiguous_0.png", "VizWiz_train_00016173_ambiguous_1.png", "VizWiz_train_00016173_ambiguous_2.png", "VizWiz_train_00016173_ambiguous_3.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 35, "id_source": "viz_data_pos.json"}, "set": "train", "id": 23, "masks_id": "00000023"}, {"file_name": "VizWiz_train_00012617.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00012617_ambiguous_0.png", "VizWiz_train_00012617_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 43, "id_source": "viz_data_pos.json"}, "set": "train", "id": 24, "masks_id": "00000024"}, {"file_name": "VizWiz_train_00018905.jpg", "question": "What color is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00018905_ambiguous_0.png", "VizWiz_train_00018905_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 45, "id_source": "viz_data_pos.json"}, "set": "train", "id": 25, "masks_id": "00000025"}, {"file_name": "VizWiz_train_00009305.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 360, "height": 480}, "focus_areas": ["VizWiz_train_00009305_ambiguous_0.png", "VizWiz_train_00009305_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 50, "id_source": "viz_data_pos.json"}, "set": "train", "id": 26, "masks_id": "00000026"}, {"file_name": "VizWiz_train_00008436.jpg", "question": "What is this cleaning product?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00008436_ambiguous_0.png", "VizWiz_train_00008436_ambiguous_1.png", "VizWiz_train_00008436_ambiguous_2.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 58, "id_source": "viz_data_pos.json"}, "set": "train", "id": 27, "masks_id": "00000027"}, {"file_name": "VizWiz_val_00001165.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_val_00001165_ambiguous_0.png", "VizWiz_val_00001165_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 66, "id_source": "viz_data_pos.json"}, "set": "train", "id": 28, "masks_id": "00000028"}, {"file_name": "VizWiz_train_00023916.jpg", "question": "What is in this photo?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00023916_ambiguous_0.png", "VizWiz_train_00023916_ambiguous_1.png", "VizWiz_train_00023916_ambiguous_2.png", "VizWiz_train_00023916_ambiguous_3.png", "VizWiz_train_00023916_ambiguous_4.png", "VizWiz_train_00023916_ambiguous_5.png", "VizWiz_train_00023916_ambiguous_6.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 72, "id_source": "viz_data_pos.json"}, "set": "train", "id": 29, "masks_id": "00000029"}, {"file_name": "VizWiz_train_00018582.jpg", "question": "What is that?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00018582_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 7, "id_source": "viz_data_neg.json"}, "set": "train", "id": 30, "masks_id": "00000030"}, {"file_name": "VizWiz_train_00006839.jpg", "question": "What is in this? What is the label on this container please?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00006839_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 11, "id_source": "viz_data_neg.json"}, "set": "train", "id": 31, "masks_id": "00000031"}, {"file_name": "VizWiz_train_00007617.jpg", "question": "What is in this box?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00007617_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 17, "id_source": "viz_data_neg.json"}, "set": "train", "id": 32, "masks_id": "00000032"}, {"file_name": "VizWiz_train_00011131.jpg", "question": "who is in this box?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00011131_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 37, "id_source": "viz_data_neg.json"}, "set": "train", "id": 33, "masks_id": "00000033"}, {"file_name": "VizWiz_train_00007215.jpg", "question": "What color is this?", "label": "unambiguous", "size": {"width": 1936, "height": 2592}, "focus_areas": ["VizWiz_train_00007215_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 48, "id_source": "viz_data_neg.json"}, "set": "train", "id": 34, "masks_id": "00000034"}, {"file_name": "VizWiz_train_00012664.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00012664_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 51, "id_source": "viz_data_neg.json"}, "set": "train", "id": 35, "masks_id": "00000035"}, {"file_name": "VizWiz_train_00009178.jpg", "question": "Is this laundry detergent or fabric softener?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00009178_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 59, "id_source": "viz_data_neg.json"}, "set": "train", "id": 36, "masks_id": "00000036"}, {"file_name": "VizWiz_train_00010700.jpg", "question": "If possible, can you tell me what is in this can, please?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00010700_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 67, "id_source": "viz_data_neg.json"}, "set": "train", "id": 37, "masks_id": "00000037"}, {"file_name": "VizWiz_train_00013966.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00013966_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 68, "id_source": "viz_data_neg.json"}, "set": "train", "id": 38, "masks_id": "00000038"}, {"file_name": "VizWiz_train_00014351.jpg", "question": "How much money is this?", "label": "unambiguous", "size": {"width": 360, "height": 480}, "focus_areas": ["VizWiz_train_00014351_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 71, "id_source": "viz_data_neg.json"}, "set": "train", "id": 39, "masks_id": "00000039"}, {"file_name": "2_70_70132.jpg", "question": "What is that?", "label": "unambiguous", "size": {"width": 400, "height": 296}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 65, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 40, "masks_id": "00000040"}, {"file_name": "7_196_196631.jpg", "question": "What is this thing?", "label": "unambiguous", "size": {"width": 400, "height": 267}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 110, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 41, "masks_id": "00000041"}, {"file_name": "1_66_66053.jpg", "question": "What is at the front?", "label": "unambiguous", "size": {"width": 400, "height": 300}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 119, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 42, "masks_id": "00000042"}, {"file_name": "10_267976432_b4e9429cff.jpg", "question": "What stands out?", "label": "unambiguous", "size": {"width": 400, "height": 266}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 142, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 43, "masks_id": "00000043"}, {"file_name": "7_204_204227.jpg", "question": "What stands out?", "label": "unambiguous", "size": {"width": 391, "height": 400}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 172, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 44, "masks_id": "00000044"}, {"file_name": "7_200_200012.jpg", "question": "What is prominent?", "label": "unambiguous", "size": {"width": 400, "height": 348}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 242, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 45, "masks_id": "00000045"}, {"file_name": "2_75_75665.jpg", "question": "What stands out?", "label": "unambiguous", "size": {"width": 400, "height": 324}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 362, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 46, "masks_id": "00000046"}, {"file_name": "2_74_74172.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 400, "height": 284}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 469, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 47, "masks_id": "00000047"}, {"file_name": "4_135_135402.jpg", "question": "What's that?", "label": "unambiguous", "size": {"width": 400, "height": 267}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 477, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 48, "masks_id": "00000048"}, {"file_name": "3_107_107745.jpg", "question": "What's that?", "label": "unambiguous", "size": {"width": 400, "height": 267}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 526, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 49, "masks_id": "00000049"}, {"file_name": "val2017_000000551822.jpg", "question": "Is the cup full?", "label": "ambiguous", "size": {"width": 640, "height": 453}, "focus_areas": ["val2017_000000551822_ambiguous_obj_0.png", "val2017_000000551822_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 125, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 50, "masks_id": "00000050"}, {"file_name": "train2017_000000382564.jpg", "question": "Is the chair occupied?", "label": "ambiguous", "size": {"width": 333, "height": 500}, "focus_areas": ["train2017_000000382564_ambiguous_obj_0.png", "train2017_000000382564_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 694, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 51, "masks_id": "00000051"}, {"file_name": "train2017_000000065806.jpg", "question": "What's inside the mug?", "label": "ambiguous", "size": {"width": 480, "height": 640}, "focus_areas": ["train2017_000000065806_ambiguous_obj_0.png", "train2017_000000065806_ambiguous_obj_1.png", "train2017_000000065806_ambiguous_obj_2.png", "train2017_000000065806_ambiguous_obj_3.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj"]}, "notes": {"index": 719, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 52, "masks_id": "00000052"}, {"file_name": "train2017_000000288921.jpg", "question": "What is inside the plastic bag?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000288921_ambiguous_obj_0.png", "train2017_000000288921_ambiguous_obj_1.png", "train2017_000000288921_ambiguous_obj_2.png", "train2017_000000288921_ambiguous_obj_3.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj"]}, "notes": {"index": 839, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 53, "masks_id": "00000053"}, {"file_name": "train2017_000000546242.jpg", "question": "Is the support stable?", "label": "ambiguous", "size": {"width": 426, "height": 640}, "focus_areas": ["train2017_000000546242_ambiguous_part_0.png", "train2017_000000546242_ambiguous_part_1.png"], "attributes": {"data_source": "paco", "paco_types": ["part", "part"]}, "notes": {"index": 1132, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 54, "masks_id": "00000054"}, {"file_name": "val2017_000000450303.jpg", "question": "What is inside the plastic bag?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["val2017_000000450303_ambiguous_obj_0.png", "val2017_000000450303_ambiguous_part_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "part"]}, "notes": {"index": 1138, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 55, "masks_id": "00000055"}, {"file_name": "train2017_000000413704.jpg", "question": "Which direction is the dog facing?", "label": "ambiguous", "size": {"width": 500, "height": 375}, "focus_areas": ["train2017_000000413704_ambiguous_obj_0.png", "train2017_000000413704_ambiguous_obj_1.png", "train2017_000000413704_ambiguous_obj_2.png", "train2017_000000413704_ambiguous_obj_3.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj"]}, "notes": {"index": 1250, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 56, "masks_id": "00000056"}, {"file_name": "train2017_000000111489.jpg", "question": "What time does the clock show?", "label": "ambiguous", "size": {"width": 425, "height": 640}, "focus_areas": ["train2017_000000111489_ambiguous_obj_0.png", "train2017_000000111489_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 1611, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 57, "masks_id": "00000057"}, {"file_name": "train2017_000000230727.jpg", "question": "What is underneath the hat?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000230727_ambiguous_obj_0.png", "train2017_000000230727_ambiguous_obj_1.png", "train2017_000000230727_ambiguous_obj_2.png", "train2017_000000230727_ambiguous_obj_3.png", "train2017_000000230727_ambiguous_obj_4.png", "train2017_000000230727_ambiguous_obj_5.png", "train2017_000000230727_ambiguous_obj_6.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj", "obj", "obj", "obj"]}, "notes": {"index": 1712, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 58, "masks_id": "00000058"}, {"file_name": "val2017_000000153229.jpg", "question": "Who is wearing the hat?", "label": "ambiguous", "size": {"width": 640, "height": 457}, "focus_areas": ["val2017_000000153229_ambiguous_obj_0.png", "val2017_000000153229_ambiguous_obj_1.png", "val2017_000000153229_ambiguous_obj_2.png", "val2017_000000153229_ambiguous_obj_3.png", "val2017_000000153229_ambiguous_obj_4.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj", "obj"]}, "notes": {"index": 2185, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 59, "masks_id": "00000059"}, {"file_name": "train2017_000000054218.jpg", "question": "What is in the food cup of the blender?", "label": "unambiguous", "size": {"width": 375, "height": 500}, "focus_areas": ["train2017_000000054218_unambiguous_obj_0.png", "train2017_000000054218_unambiguous_part_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "part"]}, "notes": {"index": 91, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 60, "masks_id": "00000060"}, {"file_name": "train2017_000000312682.jpg", "question": "Is the knife on a plastic bag?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000312682_unambiguous_obj_0.png", "train2017_000000312682_unambiguous_obj_1.png", "train2017_000000312682_unambiguous_obj_2.png", "train2017_000000312682_unambiguous_obj_3.png", "train2017_000000312682_unambiguous_obj_4.png", "train2017_000000312682_unambiguous_obj_5.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj", "obj", "obj"]}, "notes": {"index": 108, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 61, "masks_id": "00000061"}, {"file_name": "train2017_000000534252.jpg", "question": "Which dog's face is deepest in the sandal?", "label": "unambiguous", "size": {"width": 640, "height": 640}, "focus_areas": ["train2017_000000534252_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 230, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 62, "masks_id": "00000062"}, {"file_name": "train2017_000000035045.jpg", "question": "What's in the person's hand?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000035045_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 322, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 63, "masks_id": "00000063"}, {"file_name": "train2017_000000112480.jpg", "question": "Is that book wet from rain?", "label": "unambiguous", "size": {"width": 640, "height": 478}, "focus_areas": ["train2017_000000112480_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 1301, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 64, "masks_id": "00000064"}, {"file_name": "train2017_000000529829.jpg", "question": "What's inside the basket placed on top of the sack?", "label": "unambiguous", "size": {"width": 425, "height": 640}, "focus_areas": ["train2017_000000529829_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 1355, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 65, "masks_id": "00000065"}, {"file_name": "train2017_000000502286.jpg", "question": "What is on the chair?", "label": "unambiguous", "size": {"width": 480, "height": 640}, "focus_areas": ["train2017_000000502286_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 1606, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 66, "masks_id": "00000066"}, {"file_name": "train2017_000000410554.jpg", "question": "what is the knife blade the man is holding about to cut?", "label": "unambiguous", "size": {"width": 478, "height": 640}, "focus_areas": ["train2017_000000410554_unambiguous_part_0.png"], "attributes": {"data_source": "paco", "paco_types": ["part"]}, "notes": {"index": 1986, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 67, "masks_id": "00000067"}, {"file_name": "train2017_000000158861.jpg", "question": "Is someone sitting on the bench?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000158861_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 2087, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 68, "masks_id": "00000068"}, {"file_name": "train2017_000000018317.jpg", "question": "What is the ladder leaning against?", "label": "unambiguous", "size": {"width": 612, "height": 612}, "focus_areas": ["train2017_000000018317_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 2211, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 69, "masks_id": "00000069"}]