[{"file_name": "COCO_train2014_000000079710.jpg", "question": "What are the signs for?", "label": "ambiguous", "size": {"width": 640, "height": 492}, "focus_areas": ["COCO_train2014_000000079710_ambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 1, "id_source": "coco_data_pos.json"}, "set": "train", "id": 70, "masks_id": "00000070"}, {"file_name": "COCO_train2014_000000168748.jpg", "question": "What is on the man's knees?", "label": "ambiguous", "size": {"width": 640, "height": 427}, "focus_areas": ["COCO_train2014_000000168748_ambiguous_0.png", "COCO_train2014_000000168748_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 2, "id_source": "coco_data_pos.json"}, "set": "train", "id": 71, "masks_id": "00000071"}, {"file_name": "COCO_train2014_000000061740.jpg", "question": "What color is the tree leaves?", "label": "ambiguous", "size": {"width": 426, "height": 640}, "focus_areas": ["COCO_train2014_000000061740_ambiguous_0.png", "COCO_train2014_000000061740_ambiguous_1.png", "COCO_train2014_000000061740_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 5, "id_source": "coco_data_pos.json"}, "set": "train", "id": 72, "masks_id": "00000072"}, {"file_name": "COCO_train2014_000000131170.jpg", "question": "What kind of bus is this in the picture?", "label": "ambiguous", "size": {"width": 640, "height": 479}, "focus_areas": ["COCO_train2014_000000131170_ambiguous_0.png", "COCO_train2014_000000131170_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 16, "id_source": "coco_data_pos.json"}, "set": "train", "id": 73, "masks_id": "00000073"}, {"file_name": "COCO_train2014_000000552444.jpg", "question": "What kind of jacket is she wearing?", "label": "ambiguous", "size": {"width": 640, "height": 401}, "focus_areas": ["COCO_train2014_000000552444_ambiguous_0.png", "COCO_train2014_000000552444_ambiguous_1.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 19, "id_source": "coco_data_pos.json"}, "set": "train", "id": 74, "masks_id": "00000074"}, {"file_name": "COCO_train2014_000000058406.jpg", "question": "What is this for?", "label": "ambiguous", "size": {"width": 479, "height": 640}, "focus_areas": ["COCO_train2014_000000058406_ambiguous_0.png", "COCO_train2014_000000058406_ambiguous_1.png", "COCO_train2014_000000058406_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 36, "id_source": "coco_data_pos.json"}, "set": "train", "id": 75, "masks_id": "00000075"}, {"file_name": "COCO_train2014_000000558401.jpg", "question": "What is behind the screen?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000558401_ambiguous_0.png", "COCO_train2014_000000558401_ambiguous_1.png", "COCO_train2014_000000558401_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 37, "id_source": "coco_data_pos.json"}, "set": "train", "id": 76, "masks_id": "00000076"}, {"file_name": "COCO_train2014_000000169633.jpg", "question": "What is the person doing?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000169633_ambiguous_0.png", "COCO_train2014_000000169633_ambiguous_1.png", "COCO_train2014_000000169633_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 47, "id_source": "coco_data_pos.json"}, "set": "train", "id": 77, "masks_id": "00000077"}, {"file_name": "COCO_train2014_000000073262.jpg", "question": "What is this person riding?", "label": "ambiguous", "size": {"width": 500, "height": 333}, "focus_areas": ["COCO_train2014_000000073262_ambiguous_0.png", "COCO_train2014_000000073262_ambiguous_1.png", "COCO_train2014_000000073262_ambiguous_2.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 70, "id_source": "coco_data_pos.json"}, "set": "train", "id": 78, "masks_id": "00000078"}, {"file_name": "COCO_train2014_000000289212.jpg", "question": "What is the color of the car?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000289212_ambiguous_0.png", "COCO_train2014_000000289212_ambiguous_1.png", "COCO_train2014_000000289212_ambiguous_2.png", "COCO_train2014_000000289212_ambiguous_3.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 85, "id_source": "coco_data_pos.json"}, "set": "train", "id": 79, "masks_id": "00000079"}, {"file_name": "COCO_train2014_000000553501.jpg", "question": "What are the loaves of bread sitting on?", "label": "unambiguous", "size": {"width": 612, "height": 612}, "focus_areas": ["COCO_train2014_000000553501_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 18, "id_source": "coco_data_neg.json"}, "set": "train", "id": 80, "masks_id": "00000080"}, {"file_name": "COCO_train2014_000000572254.jpg", "question": "What color is the dog?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["COCO_train2014_000000572254_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 21, "id_source": "coco_data_neg.json"}, "set": "train", "id": 81, "masks_id": "00000081"}, {"file_name": "COCO_train2014_000000051328.jpg", "question": "What is the hydrant used for?", "label": "unambiguous", "size": {"width": 612, "height": 612}, "focus_areas": ["COCO_train2014_000000051328_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 25, "id_source": "coco_data_neg.json"}, "set": "train", "id": 82, "masks_id": "00000082"}, {"file_name": "COCO_train2014_000000542484.jpg", "question": "What shape is the window?", "label": "unambiguous", "size": {"width": 640, "height": 492}, "focus_areas": ["COCO_train2014_000000542484_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 29, "id_source": "coco_data_neg.json"}, "set": "train", "id": 83, "masks_id": "00000083"}, {"file_name": "COCO_train2014_000000253716.jpg", "question": "What style of architecture is shown?", "label": "unambiguous", "size": {"width": 640, "height": 348}, "focus_areas": ["COCO_train2014_000000253716_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 31, "id_source": "coco_data_neg.json"}, "set": "train", "id": 84, "masks_id": "00000084"}, {"file_name": "COCO_train2014_000000389984.jpg", "question": "What is the horse wearing?", "label": "unambiguous", "size": {"width": 640, "height": 493}, "focus_areas": ["COCO_train2014_000000389984_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 38, "id_source": "coco_data_neg.json"}, "set": "train", "id": 85, "masks_id": "00000085"}, {"file_name": "COCO_train2014_000000468393.jpg", "question": "What is the man holding?", "label": "unambiguous", "size": {"width": 640, "height": 623}, "focus_areas": ["COCO_train2014_000000468393_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 45, "id_source": "coco_data_neg.json"}, "set": "train", "id": 86, "masks_id": "00000086"}, {"file_name": "COCO_train2014_000000003827.jpg", "question": "What is the pattern of the woman's sweater?", "label": "unambiguous", "size": {"width": 640, "height": 401}, "focus_areas": ["COCO_train2014_000000003827_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": true}, "notes": {"index": 46, "id_source": "coco_data_neg.json"}, "set": "train", "id": 87, "masks_id": "00000087"}, {"file_name": "COCO_train2014_000000506290.jpg", "question": "What are they sitting on?", "label": "unambiguous", "size": {"width": 640, "height": 427}, "focus_areas": ["COCO_train2014_000000506290_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 49, "id_source": "coco_data_neg.json"}, "set": "train", "id": 88, "masks_id": "00000088"}, {"file_name": "COCO_train2014_000000308195.jpg", "question": "What brand of gas station is shown in the picture?", "label": "unambiguous", "size": {"width": 640, "height": 431}, "focus_areas": ["COCO_train2014_000000308195_unambiguous_0.png"], "attributes": {"data_source": "coco", "answer_align": false}, "notes": {"index": 71, "id_source": "coco_data_neg.json"}, "set": "train", "id": 89, "masks_id": "00000089"}, {"file_name": "VizWiz_train_00007281.jpg", "question": "What color is this product?", "label": "ambiguous", "size": {"width": 612, "height": 816}, "focus_areas": ["VizWiz_train_00007281_ambiguous_0.png", "VizWiz_train_00007281_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 9, "id_source": "viz_data_pos.json"}, "set": "train", "id": 90, "masks_id": "00000090"}, {"file_name": "VizWiz_train_00016359.jpg", "question": "What is it?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00016359_ambiguous_0.png", "VizWiz_train_00016359_ambiguous_1.png", "VizWiz_train_00016359_ambiguous_2.png", "VizWiz_train_00016359_ambiguous_3.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 13, "id_source": "viz_data_pos.json"}, "set": "train", "id": 91, "masks_id": "00000091"}, {"file_name": "VizWiz_train_00002184.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00002184_ambiguous_0.png", "VizWiz_train_00002184_ambiguous_1.png", "VizWiz_train_00002184_ambiguous_2.png", "VizWiz_train_00002184_ambiguous_3.png", "VizWiz_train_00002184_ambiguous_4.png", "VizWiz_train_00002184_ambiguous_5.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 15, "id_source": "viz_data_pos.json"}, "set": "train", "id": 92, "masks_id": "00000092"}, {"file_name": "VizWiz_train_00014248.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00014248_ambiguous_0.png", "VizWiz_train_00014248_ambiguous_1.png", "VizWiz_train_00014248_ambiguous_2.png", "VizWiz_train_00014248_ambiguous_3.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 19, "id_source": "viz_data_pos.json"}, "set": "train", "id": 93, "masks_id": "00000093"}, {"file_name": "VizWiz_train_00015201.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1536, "height": 2048}, "focus_areas": ["VizWiz_train_00015201_ambiguous_0.png", "VizWiz_train_00015201_ambiguous_1.png", "VizWiz_train_00015201_ambiguous_2.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 20, "id_source": "viz_data_pos.json"}, "set": "train", "id": 94, "masks_id": "00000094"}, {"file_name": "VizWiz_train_00013180.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1936, "height": 2592}, "focus_areas": ["VizWiz_train_00013180_ambiguous_0.png", "VizWiz_train_00013180_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 23, "id_source": "viz_data_pos.json"}, "set": "train", "id": 95, "masks_id": "00000095"}, {"file_name": "VizWiz_train_00012866.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00012866_ambiguous_0.png", "VizWiz_train_00012866_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 27, "id_source": "viz_data_pos.json"}, "set": "train", "id": 96, "masks_id": "00000096"}, {"file_name": "VizWiz_train_00000938.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00000938_ambiguous_0.png", "VizWiz_train_00000938_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 47, "id_source": "viz_data_pos.json"}, "set": "train", "id": 97, "masks_id": "00000097"}, {"file_name": "VizWiz_train_00005383.jpg", "question": "What, what do you see?", "label": "ambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00005383_ambiguous_0.png", "VizWiz_train_00005383_ambiguous_1.png", "VizWiz_train_00005383_ambiguous_2.png", "VizWiz_train_00005383_ambiguous_3.png", "VizWiz_train_00005383_ambiguous_4.png", "VizWiz_train_00005383_ambiguous_5.png", "VizWiz_train_00005383_ambiguous_6.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 52, "id_source": "viz_data_pos.json"}, "set": "train", "id": 98, "masks_id": "00000098"}, {"file_name": "VizWiz_train_00002672.jpg", "question": "What is this?", "label": "ambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00002672_ambiguous_0.png", "VizWiz_train_00002672_ambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 70, "id_source": "viz_data_pos.json"}, "set": "train", "id": 99, "masks_id": "00000099"}, {"file_name": "VizWiz_train_00016163.jpg", "question": "What movie is this?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00016163_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 8, "id_source": "viz_data_neg.json"}, "set": "train", "id": 100, "masks_id": "00000100"}, {"file_name": "VizWiz_train_00015533.jpg", "question": "What's that?", "label": "unambiguous", "size": {"width": 360, "height": 480}, "focus_areas": ["VizWiz_train_00015533_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 29, "id_source": "viz_data_neg.json"}, "set": "train", "id": 101, "masks_id": "00000101"}, {"file_name": "VizWiz_train_00004238.jpg", "question": "What color is this wrapping paper?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00004238_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 30, "id_source": "viz_data_neg.json"}, "set": "train", "id": 102, "masks_id": "00000102"}, {"file_name": "VizWiz_train_00009118.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00009118_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 43, "id_source": "viz_data_neg.json"}, "set": "train", "id": 103, "masks_id": "00000103"}, {"file_name": "VizWiz_train_00023681.jpg", "question": "What color is this device?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00023681_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 50, "id_source": "viz_data_neg.json"}, "set": "train", "id": 104, "masks_id": "00000104"}, {"file_name": "VizWiz_train_00016052.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 768, "height": 1024}, "focus_areas": ["VizWiz_train_00016052_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 53, "id_source": "viz_data_neg.json"}, "set": "train", "id": 105, "masks_id": "00000105"}, {"file_name": "VizWiz_train_00008996.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 968, "height": 1296}, "focus_areas": ["VizWiz_train_00008996_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": true}, "notes": {"index": 58, "id_source": "viz_data_neg.json"}, "set": "train", "id": 106, "masks_id": "00000106"}, {"file_name": "VizWiz_train_00002167.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00002167_unambiguous_0.png", "VizWiz_train_00002167_unambiguous_1.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 72, "id_source": "viz_data_neg.json"}, "set": "train", "id": 107, "masks_id": "00000107"}, {"file_name": "VizWiz_train_00007880.jpg", "question": "what spice is this?", "label": "unambiguous", "size": {"width": 1224, "height": 1632}, "focus_areas": ["VizWiz_train_00007880_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 78, "id_source": "viz_data_neg.json"}, "set": "train", "id": 108, "masks_id": "00000108"}, {"file_name": "VizWiz_train_00018806.jpg", "question": "what kind of can is this?", "label": "unambiguous", "size": {"width": 360, "height": 480}, "focus_areas": ["VizWiz_train_00018806_unambiguous_0.png"], "attributes": {"data_source": "vizwiz", "answer_align": false}, "notes": {"index": 79, "id_source": "viz_data_neg.json"}, "set": "train", "id": 109, "masks_id": "00000109"}, {"file_name": "6_179_179605.jpg", "question": "What is this?", "label": "unambiguous", "size": {"width": 324, "height": 400}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 45, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 110, "masks_id": "00000110"}, {"file_name": "7_188_188631.jpg", "question": "What's this?", "label": "unambiguous", "size": {"width": 400, "height": 266}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 52, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 111, "masks_id": "00000111"}, {"file_name": "0_15_15022.jpg", "question": "What is featured up front?", "label": "unambiguous", "size": {"width": 341, "height": 400}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 78, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 112, "masks_id": "00000112"}, {"file_name": "10_55768641.checkers22.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": 83, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 113, "masks_id": "00000113"}, {"file_name": "4_135_135781.jpg", "question": "What is featured up front?", "label": "unambiguous", "size": {"width": 400, "height": 278}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 248, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 114, "masks_id": "00000114"}, {"file_name": "0_6_6818.jpg", "question": "What is close to the camera?", "label": "unambiguous", "size": {"width": 400, "height": 300}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 286, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 115, "masks_id": "00000115"}, {"file_name": "1_66_66988.jpg", "question": "What is at the front?", "label": "unambiguous", "size": {"width": 400, "height": 247}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 338, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 116, "masks_id": "00000116"}, {"file_name": "6_176_176817.jpg", "question": "What is this thing?", "label": "unambiguous", "size": {"width": 305, "height": 400}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 349, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 117, "masks_id": "00000117"}, {"file_name": "6_181_181933.jpg", "question": "What is in the foreground?", "label": "unambiguous", "size": {"width": 400, "height": 332}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 534, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 118, "masks_id": "00000118"}, {"file_name": "10_98053912_88fec4b17c.jpg", "question": "What's this?", "label": "unambiguous", "size": {"width": 400, "height": 294}, "focus_areas": ["MSRA_VizWiz_train_00008431.png"], "attributes": {"data_source": "msra"}, "notes": {"index": 622, "id_source": "MSRA_RLE_626.json"}, "set": "train", "id": 119, "masks_id": "00000119"}, {"file_name": "train2017_000000306593.jpg", "question": "what is this behind the laptop?", "label": "ambiguous", "size": {"width": 500, "height": 333}, "focus_areas": ["train2017_000000306593_ambiguous_obj_0.png", "train2017_000000306593_ambiguous_obj_1.png", "train2017_000000306593_ambiguous_obj_2.png", "train2017_000000306593_ambiguous_obj_3.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj"]}, "notes": {"index": 124, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 120, "masks_id": "00000120"}, {"file_name": "train2017_000000248337.jpg", "question": "Is a bear touching it?", "label": "ambiguous", "size": {"width": 640, "height": 426}, "focus_areas": ["train2017_000000248337_ambiguous_obj_0.png", "train2017_000000248337_ambiguous_obj_1.png", "train2017_000000248337_ambiguous_obj_2.png", "train2017_000000248337_ambiguous_obj_3.png", "train2017_000000248337_ambiguous_part_0.png", "train2017_000000248337_ambiguous_part_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj", "obj", "part", "part"]}, "notes": {"index": 250, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 121, "masks_id": "00000121"}, {"file_name": "train2017_000000066420.jpg", "question": "What's under the television set?", "label": "ambiguous", "size": {"width": 640, "height": 361}, "focus_areas": ["train2017_000000066420_ambiguous_obj_0.png", "train2017_000000066420_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 880, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 122, "masks_id": "00000122"}, {"file_name": "train2017_000000576939.jpg", "question": "Is the handle made of steel?", "label": "ambiguous", "size": {"width": 640, "height": 426}, "focus_areas": ["train2017_000000576939_ambiguous_part_0.png", "train2017_000000576939_ambiguous_part_1.png", "train2017_000000576939_ambiguous_part_2.png", "train2017_000000576939_ambiguous_part_3.png", "train2017_000000576939_ambiguous_part_4.png", "train2017_000000576939_ambiguous_part_5.png", "train2017_000000576939_ambiguous_part_6.png", "train2017_000000576939_ambiguous_part_7.png", "train2017_000000576939_ambiguous_part_8.png", "train2017_000000576939_ambiguous_part_9.png", "train2017_000000576939_ambiguous_part_10.png"], "attributes": {"data_source": "paco", "paco_types": ["part", "part", "part", "part", "part", "part", "part", "part", "part", "part", "part"]}, "notes": {"index": 958, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 123, "masks_id": "00000123"}, {"file_name": "train2017_000000413626.jpg", "question": "Is the top snowed on?", "label": "ambiguous", "size": {"width": 320, "height": 400}, "focus_areas": ["train2017_000000413626_ambiguous_part_0.png", "train2017_000000413626_ambiguous_part_1.png", "train2017_000000413626_ambiguous_part_2.png", "train2017_000000413626_ambiguous_part_3.png", "train2017_000000413626_ambiguous_part_4.png", "train2017_000000413626_ambiguous_part_5.png"], "attributes": {"data_source": "paco", "paco_types": ["part", "part", "part", "part", "part", "part"]}, "notes": {"index": 985, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 124, "masks_id": "00000124"}, {"file_name": "train2017_000000255889.jpg", "question": "What is attached to the skateboarder's shoe?", "label": "ambiguous", "size": {"width": 375, "height": 500}, "focus_areas": ["train2017_000000255889_ambiguous_obj_0.png", "train2017_000000255889_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 1188, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 125, "masks_id": "00000125"}, {"file_name": "val2017_000000537270.jpg", "question": "What is being held in the hand?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["val2017_000000537270_ambiguous_obj_0.png", "val2017_000000537270_ambiguous_obj_1.png", "val2017_000000537270_ambiguous_obj_2.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj"]}, "notes": {"index": 1253, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 126, "masks_id": "00000126"}, {"file_name": "train2017_000000456443.jpg", "question": "What is next to the chair?", "label": "ambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000456443_ambiguous_obj_0.png", "train2017_000000456443_ambiguous_obj_1.png", "train2017_000000456443_ambiguous_obj_2.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "obj"]}, "notes": {"index": 1285, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 127, "masks_id": "00000127"}, {"file_name": "train2017_000000316298.jpg", "question": "Where is the body placed?", "label": "ambiguous", "size": {"width": 380, "height": 285}, "focus_areas": ["train2017_000000316298_ambiguous_part_0.png", "train2017_000000316298_ambiguous_part_1.png", "train2017_000000316298_ambiguous_part_2.png"], "attributes": {"data_source": "paco", "paco_types": ["part", "part", "part"]}, "notes": {"index": 1427, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 128, "masks_id": "00000128"}, {"file_name": "train2017_000000196299.jpg", "question": "What is written on the cover of the blue book?", "label": "ambiguous", "size": {"width": 427, "height": 640}, "focus_areas": ["train2017_000000196299_ambiguous_obj_0.png", "train2017_000000196299_ambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 1547, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 129, "masks_id": "00000129"}, {"file_name": "val2017_000000296284.jpg", "question": "how many donut are on the second trays from the top?", "label": "unambiguous", "size": {"width": 270, "height": 360}, "focus_areas": ["val2017_000000296284_unambiguous_obj_0.png", "val2017_000000296284_unambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 8, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 130, "masks_id": "00000130"}, {"file_name": "train2017_000000130070.jpg", "question": "How many table backs can be seen?", "label": "unambiguous", "size": {"width": 500, "height": 375}, "focus_areas": ["train2017_000000130070_unambiguous_part_0.png", "train2017_000000130070_unambiguous_part_1.png", "train2017_000000130070_unambiguous_part_2.png", "train2017_000000130070_unambiguous_part_3.png", "train2017_000000130070_unambiguous_part_4.png", "train2017_000000130070_unambiguous_part_5.png"], "attributes": {"data_source": "paco", "paco_types": ["part", "part", "part", "part", "part", "part"]}, "notes": {"index": 318, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 131, "masks_id": "00000131"}, {"file_name": "train2017_000000374042.jpg", "question": "what is inside the plastic bag beside the suitcase?", "label": "unambiguous", "size": {"width": 425, "height": 640}, "focus_areas": ["train2017_000000374042_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 341, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 132, "masks_id": "00000132"}, {"file_name": "train2017_000000222075.jpg", "question": "Which book has a floral cover?", "label": "unambiguous", "size": {"width": 480, "height": 640}, "focus_areas": ["train2017_000000222075_unambiguous_obj_0.png", "train2017_000000222075_unambiguous_obj_1.png", "train2017_000000222075_unambiguous_part_0.png", "train2017_000000222075_unambiguous_part_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj", "part", "part"]}, "notes": {"index": 441, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 133, "masks_id": "00000133"}, {"file_name": "train2017_000000507196.jpg", "question": "What does that lamp do?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000507196_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 1265, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 134, "masks_id": "00000134"}, {"file_name": "train2017_000000175801.jpg", "question": "what color is the first car on the far left?", "label": "unambiguous", "size": {"width": 640, "height": 278}, "focus_areas": ["train2017_000000175801_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 1341, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 135, "masks_id": "00000135"}, {"file_name": "train2017_000000027789.jpg", "question": "How many lamps are in the room? ", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["train2017_000000027789_unambiguous_obj_0.png", "train2017_000000027789_unambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 1518, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 136, "masks_id": "00000136"}, {"file_name": "train2017_000000385795.jpg", "question": "What is the color of the lace on the shoe closest to the soccer ball?", "label": "unambiguous", "size": {"width": 640, "height": 448}, "focus_areas": ["train2017_000000385795_unambiguous_obj_0.png", "train2017_000000385795_unambiguous_part_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "part"]}, "notes": {"index": 1849, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 137, "masks_id": "00000137"}, {"file_name": "val2017_000000036844.jpg", "question": "How many pillows are on the sofa?", "label": "unambiguous", "size": {"width": 640, "height": 480}, "focus_areas": ["val2017_000000036844_unambiguous_obj_0.png", "val2017_000000036844_unambiguous_obj_1.png"], "attributes": {"data_source": "paco", "paco_types": ["obj", "obj"]}, "notes": {"index": 1870, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 138, "masks_id": "00000138"}, {"file_name": "train2017_000000186822.jpg", "question": "What is next to the bowl on the toilet?", "label": "unambiguous", "size": {"width": 480, "height": 640}, "focus_areas": ["train2017_000000186822_unambiguous_obj_0.png"], "attributes": {"data_source": "paco", "paco_types": ["obj"]}, "notes": {"index": 2267, "id_source": ["paco_filtered_ambiguous_results.json", "paco_filtered_unambiguous_results.json"]}, "set": "train", "id": 139, "masks_id": "00000139"}]