id
unknown
images
listlengths
3
3
⌀
conversations
listlengths
2
2
source_dataset
stringclasses
7 values
image
listlengths
1
8
⌀
relative_point
listlengths
1
812
⌀
"region_ref/1104622922-d5b363c_cam03_obj13-oven-heater_0_0_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane delineated by a red rectangular border. Locate several points within a vacant area on the outlined plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fi...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1104622922-d5b363c_cam03_obj13-oven-heater_0_0_on/image_0.png" ]
[ "<tag_name name=\"countertop\" img_idx=\"0\" point=\"[480, 716]\">" ]
"object_ref/1091347530-4fb8b7b_cam07_obj24-obj25_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red square. Locate at least one point on a separate item that is situated to the right side of the object encased by the red rectangle. The answer should be presented in JSON format. Provide your thinking process between the <th...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1091347530-4fb8b7b_cam07_obj24-obj25_right/image_0.png" ]
[ "<tag_name name=\"knife with wooden handle\" img_idx=\"0\" point=\"[840, 650]\">" ]
"region_ref/1125653284-502d64c_cam00_obj27-obj29_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several spots on the vacant area next to the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1125653284-502d64c_cam00_obj27-obj29_beside/image_0.png" ]
[ "<tag_name name=\"white figurine\" img_idx=\"0\" point=\"[597, 148]\">" ]
"object_ref/1313474689-9b5268c_cam06_obj36-oven-door_0_1_door_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Locate several points on any item that is situated on the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final an...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1313474689-9b5268c_cam06_obj36-oven-door_0_1_door_on/image_0.png" ]
[ "<tag_name name=\"white sculpture\" img_idx=\"0\" point=\"[486, 630]\">", "<tag_name name=\"elephant figurine\" img_idx=\"0\" point=\"[640, 658]\">" ]
"region_ref/1324679663-502d64c_cam02_obj12-oven-corpus_inside"
null
[ { "from": "human", "value": "<image>\nThe image includes a container demarcated by a red rectangular border. Locate several points within the unoccupied space that lies within the boundaries of the marked container. The answer should be presented in JSON format. Provide your thinking process between the <th...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1324679663-502d64c_cam02_obj12-oven-corpus_inside/image_0.png" ]
[ "<tag_name name=\"container demarcated by a red rectangular border\" img_idx=\"0\" point=\"[357, 494]\">" ]
"region_ref/1070318233-f53019d_cam02_obj5-obj17_beside"
null
[ { "from": "human", "value": "<image>\nThe image includes an item encased within a red rectangular border. Locate several spots within a vacant area beside the item that is bordered. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then g...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1070318233-f53019d_cam02_obj5-obj17_beside/image_0.png" ]
[ "<tag_name name=\"metallic circular scale\" img_idx=\"0\" point=\"[561, 306]\">" ]
"refcoco_12392"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: taller giraffe. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and ...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_12392/image_0.jpg" ]
[ "<tag_name name=\"taller giraffe\" img_idx=\"0\" point=\"[148, 576]\">" ]
"object_ref/105639660-ab687ea_cam07_obj19-obj14_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate a few points on an item that is situated to the right-hand side of the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/105639660-ab687ea_cam07_obj19-obj14_right/image_0.png" ]
[ "<tag_name name=\"bread\" img_idx=\"0\" point=\"[415, 378]\">", "<tag_name name=\"yellow ring\" img_idx=\"0\" point=\"[679, 406]\">" ]
"object_ref/1247457856-d5b363c_cam02_obj7-obj5_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate one or more spots on an item beside the one that is highlighted by the rectangle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1247457856-d5b363c_cam02_obj7-obj5_beside/image_0.png" ]
[ "<tag_name name=\"highlighted item\" img_idx=\"0\" point=\"[301, 158]\">", "<tag_name name=\"item beside the highlighted item\" img_idx=\"0\" point=\"[406, 143]\">" ]
"roborefit_25405"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: grasp the red cone. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> ...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_25405/image_0.png" ]
[ "<tag_name name=\"red cone\" img_idx=\"0\" point=\"[680, 347]\">" ]
"region_ref/1118904728-63bd2a7_cam04_obj9-oven-heater_0_1_on"
null
[ { "from": "human", "value": "<image>\nIn the image, there's an area bordered by a red rectangle. Locate several points within an unoccupied space on the area that's been marked. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1118904728-63bd2a7_cam04_obj9-oven-heater_0_1_on/image_0.png" ]
[ "<tag_name name=\"blue circular object\" img_idx=\"0\" point=\"[953, 410]\">", "<tag_name name=\"sunglasses\" img_idx=\"0\" point=\"[968, 357]\">" ]
"refcoco_19319"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: a woman in a white shirt. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <an...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_19319/image_0.jpg" ]
[ "<tag_name name=\"woman in a white shirt\" img_idx=\"0\" point=\"[107, 458]\">" ]
"roborefit_2818"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I would like to grasp the white and green bottled laundry detergent with a white handy pump on the middle shelf. The answer should be presented in JSON format. Provide your thinking process...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_2818/image_0.png" ]
[ "<tag_name name=\"white and green bottled laundry detergent with a white handy pump on the middle shelf\" img_idx=\"0\" point=\"[548, 496]\">" ]
"refcoco_14131"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: A small child in a pink suit.. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between th...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_14131/image_0.jpg" ]
[ "<tag_name name=\"small child in a pink suit\" img_idx=\"0\" point=\"[601, 538]\">" ]
"fsd_pointrtx_3013"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move green rice chip bag near sponge. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer should be...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointrtx_3013/image_0.jpg" ]
[ "<tag_name name=\"green rice chip bag\" img_idx=\"0\" point=\"[640, 217]\">", "<tag_name name=\"sponge\" img_idx=\"0\" point=\"[395, 507]\">" ]
"roborefit_20490"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: fetch me the black and white panda. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer betwe...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_20490/image_0.png" ]
[ "<tag_name name=\"black and white panda\" img_idx=\"0\" point=\"[640, 458]\">" ]
"region_ref/1053957308-ab687ea_cam05_obj29-sink_cabinet-sink_countertop_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area demarcated by a red rectangle. Locate several points within a vacant space on the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1053957308-ab687ea_cam05_obj29-sink_cabinet-sink_countertop_on/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[301, 586]\">" ]
"object_ref/1146005996-4fb8b7b_cam02_obj12-base_cabinet-top_on-left"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Locate a few points on an item that is situated on the left side of the area marked by the rectangle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> ta...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1146005996-4fb8b7b_cam02_obj12-base_cabinet-top_on-left/image_0.png" ]
[ "<tag_name name=\"cabinet\" img_idx=\"0\" point=\"[206, 714]\">", "<tag_name name=\"countertop\" img_idx=\"0\" point=\"[398, 805]\">" ]
"roborefit_25551"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: give me the blue cone. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answe...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_25551/image_0.png" ]
[ "<tag_name name=\"blue cone\" img_idx=\"0\" point=\"[328, 576]\">" ]
"roborefit_15410"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you please fetch me the bright red tomato at the top. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_15410/image_0.png" ]
[ "<tag_name name=\"bright red tomato at the top\" img_idx=\"0\" point=\"[694, 428]\">" ]
"roborefit_16974"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: will you please bring me the cylindrical clear glass. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your ...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_16974/image_0.png" ]
[ "<tag_name name=\"cylindrical clear glass\" img_idx=\"0\" point=\"[468, 239]\">" ]
"roborefit_564"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: please bring me the Nestle canned coffee. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_564/image_0.png" ]
[ "<tag_name name=\"Nestle canned coffee\" img_idx=\"0\" point=\"[573, 540]\">" ]
"fsd_pointbridge_26673"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: pick up green mug. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer should be presented in JSON ...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_26673/image_0.jpg" ]
[ "<tag_name name=\"green mug\" img_idx=\"0\" point=\"[371, 708]\">" ]
"region_ref/1153669374-502d64c_cam01_obj7-obj26_front"
null
[ { "from": "human", "value": "<image>\nThe image depicts an item encircled by a red rectangle. Locate and identify several points within the vacant area that lies before the encased object. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1153669374-502d64c_cam01_obj7-obj26_front/image_0.png" ]
[ "<tag_name name=\"encased object\" img_idx=\"0\" point=\"[546, 579]\">" ]
"roborefit_25468"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: could you give me the red cone. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between t...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_25468/image_0.png" ]
[ "<tag_name name=\"red cone\" img_idx=\"0\" point=\"[564, 500]\">" ]
"object_ref/1155377858-502d64c_cam02_obj0-obj18_behind"
null
[ { "from": "human", "value": "<image>\nIn the image, there is an item encircled by a red rectangle. Locate several points on any item that is situated behind the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give y...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1155377858-502d64c_cam02_obj0-obj18_behind/image_0.png" ]
[ "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[480, 535]\">", "<tag_name name=\"cabinet\" img_idx=\"0\" point=\"[476, 107]\">" ]
"object_ref/1258632793-f53019d_cam05_obj5-obj13_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several points on an item that is situated to the right of the object with the red outline. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1258632793-f53019d_cam05_obj5-obj13_right/image_0.png" ]
[ "<tag_name name=\"white rectangular object to the right of the outlined object\" img_idx=\"0\" point=\"[640, 489]\">" ]
"roborefit_35869"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: fetch me the shampoo in a cylindrical bottle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final an...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_35869/image_0.png" ]
[ "<tag_name name=\"shampoo in a cylindrical bottle\" img_idx=\"0\" point=\"[438, 619]\">", "<tag_name name=\"shampoo in a cylindrical bottle\" img_idx=\"0\" point=\"[390, 517]\">" ]
"region_ref/1052220959-fe2f065_cam09_obj11-oven-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Locate a few points within an unoccupied space on the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1052220959-fe2f065_cam09_obj11-oven-top_on/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[153, 540]\">" ]
"fsd_pointbridge_91326"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: Place the can in front of the blue fork and against the wall.. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be mo...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_91326/image_0.jpg" ]
[ "<tag_name name=\"can\" img_idx=\"0\" point=\"[406, 517]\">", "<tag_name name=\"blue fork\" img_idx=\"0\" point=\"[593, 683]\">", "<tag_name name=\"wall\" img_idx=\"0\" point=\"[509, 148]\">" ]
"refcoco_9084"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: boy in red. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and </an...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_9084/image_0.jpg" ]
[ "<tag_name name=\"boy in red\" img_idx=\"0\" point=\"[250, 417]\">" ]
"roborefit_33492"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you give me the white bottled body milk with a red cap. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then gi...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_33492/image_0.png" ]
[ "<tag_name name=\"white bottled body milk with a red cap\" img_idx=\"0\" point=\"[240, 351]\">" ]
"roborefit_23080"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: could you fetch me the mint candy jar. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer be...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_23080/image_0.png" ]
[ "<tag_name name=\"mint candy jar\" img_idx=\"0\" point=\"[530, 647]\">" ]
"object_ref/1138559102-9b5268c_cam05_obj8-obj19_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several spots on an item that is adjacent to the one marked by the rectangle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then giv...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1138559102-9b5268c_cam05_obj8-obj19_beside/image_0.png" ]
[ "<tag_name name=\"chair\" img_idx=\"0\" point=\"[450, 341]\">", "<tag_name name=\"desk\" img_idx=\"0\" point=\"[537, 361]\">", "<tag_name name=\"white chair\" img_idx=\"0\" point=\"[450, 341]\">", "<tag_name name=\"gray desk\" img_idx=\"0\" point=\"[510, 367]\">", "<tag_name name=\"brown block\" img_idx=\"0...
"roborefit_35240"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you pass me the bottled facial cleanser. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final a...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_35240/image_0.png" ]
[ "<tag_name name=\"bottled facial cleanser\" img_idx=\"0\" point=\"[789, 516]\">" ]
"roborefit_20088"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I would like to get the yellow screwdriver. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answ...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_20088/image_0.png" ]
[ "<tag_name name=\"yellow screwdriver\" img_idx=\"0\" point=\"[417, 658]\">" ]
"roborefit_30203"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you bring me the baking soda toothpaste in a big cyan conical bottle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tag...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_30203/image_0.png" ]
[ "<tag_name name=\"baking soda toothpaste in a big cyan conical bottle\" img_idx=\"0\" point=\"[618, 450]\">" ]
"region_ref/1091671392-f2789f5_cam06_obj9-obj17_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item enclosed within a red rectangular border. Pinpoint several spots within the vacant area located to the object's right-hand side. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1091671392-f2789f5_cam06_obj9-obj17_right/image_0.png" ]
[ "<tag_name name=\"red rectangular border\" img_idx=\"0\" point=\"[375, 438]\">" ]
"region_ref/1074619429-bf915d8_cam03_obj22-obj21_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several spots on the vacant area next to the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1074619429-bf915d8_cam03_obj22-obj21_beside/image_0.png" ]
[ "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[107, 548]\">" ]
"fsd_pointrtx_2225"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move blue chip bag near green jalapeno chip bag. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answe...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointrtx_2225/image_0.jpg" ]
[ "<tag_name name=\"blue chip bag\" img_idx=\"0\" point=\"[403, 580]\">", "<tag_name name=\"green jalapeno chip bag\" img_idx=\"0\" point=\"[461, 257]\">" ]
"region_ref/1214099381-bf915d8_cam09_obj40-base_cabinet-top_on"
null
[ { "from": "human", "value": "<image>\nThe image depicts an area outlined by a red rectangle. Pinpoint any number of locations within a vacant space situated on the outlined area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1214099381-bf915d8_cam09_obj40-base_cabinet-top_on/image_0.png" ]
[ "<tag_name name=\"tabletop\" img_idx=\"0\" point=\"[480, 196]\">" ]
"region_ref/1253585543-502d64c_cam06_obj18-base_cabinet-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area demarcated by a red rectangle. Locate several points within a vacant space on the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1253585543-502d64c_cam06_obj18-base_cabinet-top_on/image_0.png" ]
[ "<tag_name name=\"vacant space\" img_idx=\"0\" point=\"[456, 701]\">", "<tag_name name=\"vacant space\" img_idx=\"0\" point=\"[385, 609]\">", "<tag_name name=\"vacant space\" img_idx=\"0\" point=\"[488, 511]\">" ]
"roborefit_22328"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: please hand me the black and gray wireless mouse. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fina...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_22328/image_0.png" ]
[ "<tag_name name=\"black and gray wireless mouse\" img_idx=\"0\" point=\"[341, 489]\">" ]
"refcoco_19714"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: The spoon the left.. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer>...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_19714/image_0.jpg" ]
[ "<tag_name name=\"spoon\" img_idx=\"0\" point=\"[195, 908]\">" ]
"object_ref/1136468115-8db35a4_cam00_obj0-base_cabinet-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area delineated by a red rectangle. Pinpoint one or several locations upon an item that is situated upon the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then g...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1136468115-8db35a4_cam00_obj0-base_cabinet-top_on/image_0.png" ]
[ "<tag_name name=\"black console\" img_idx=\"0\" point=\"[186, 548]\">", "<tag_name name=\"white box\" img_idx=\"0\" point=\"[507, 479]\">" ]
"roborefit_15516"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I want to get the tomato. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <an...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_15516/image_0.png" ]
[ "<tag_name name=\"tomato\" img_idx=\"0\" point=\"[593, 431]\">" ]
"region_ref/1148442062-8db35a4_cam01_obj8-obj1_left"
null
[ { "from": "human", "value": "<image>\nThe image features an item encased within a red rectangular border. Locate a few spots within a vacant area situated to the left of the item with the red outline. The answer should be presented in JSON format. Provide your thinking process between the <think> and </thin...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1148442062-8db35a4_cam01_obj8-obj1_left/image_0.png" ]
[ "<tag_name name=\"item with the red outline\" img_idx=\"0\" point=\"[456, 479]\">" ]
"object_ref/1165026169-1cd1792_cam05_obj39-refrigerator-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane outlined by a red rectangle. Locate a few points on an item that rests upon the outlined plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1165026169-1cd1792_cam05_obj39-refrigerator-top_on/image_0.png" ]
[ "<tag_name name=\"remote control\" img_idx=\"0\" point=\"[648, 538]\">", "<tag_name name=\"apple\" img_idx=\"0\" point=\"[550, 476]\">", "<tag_name name=\"toy structure\" img_idx=\"0\" point=\"[419, 507]\">", "<tag_name name=\"banana\" img_idx=\"0\" point=\"[163, 609]\">" ]
"roborefit_22204"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: will you please fetch me the black television remote control. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then gi...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_22204/image_0.png" ]
[ "<tag_name name=\"black television remote control\" img_idx=\"0\" point=\"[618, 619]\">" ]
"refcoco_10146"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: The medium sized giraffe eating.. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_10146/image_0.jpg" ]
[ "<tag_name name=\"medium sized giraffe\" img_idx=\"0\" point=\"[278, 744]\">", "<tag_name name=\"eating giraffe\" img_idx=\"0\" point=\"[195, 806]\">" ]
"roborefit_34379"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I want to grasp the silvery and red bottled facial cleanser on the right. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags,...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_34379/image_0.png" ]
[ "<tag_name name=\"silvery and red bottled facial cleanser on the right\" img_idx=\"0\" point=\"[534, 489]\">" ]
"roborefit_3052"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: find the can of coca cola on the top right shelf. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fina...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_3052/image_0.png" ]
[ "<tag_name name=\"coca cola can\" img_idx=\"0\" point=\"[573, 148]\">" ]
"roborefit_35870"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: fetch the white and green bottled mouthwash. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final ans...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_35870/image_0.png" ]
[ "<tag_name name=\"white bottle with red cap\" img_idx=\"0\" point=\"[394, 517]\">", "<tag_name name=\"white bottle with red cap\" img_idx=\"0\" point=\"[438, 601]\">" ]
"region_ref/1117908810-d5b363c_cam01_obj1-dishwasher-corpus_inside"
null
[ { "from": "human", "value": "<image>\nThe image depicts a vessel delineated by a red rectangular border. Locate any number of spots within a vacant area encompassed by the container's outline. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags,...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1117908810-d5b363c_cam01_obj1-dishwasher-corpus_inside/image_0.png" ]
[ "<tag_name name=\"vessel\" img_idx=\"0\" point=\"[408, 395]\">" ]
"fsd_pointbridge_26612"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move the silver pot right the burner. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer should b...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_26612/image_0.jpg" ]
[ "<tag_name name=\"silver pot\" img_idx=\"0\" point=\"[640, 451]\">", "<tag_name name=\"burner\" img_idx=\"0\" point=\"[419, 398]\">" ]
"region_ref/1212724557-ab687ea_cam06_obj4-obj3_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item enclosed within a red rectangle. Pinpoint several spots within the vacant area situated to the right side of the enclosed item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags,...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1212724557-ab687ea_cam06_obj4-obj3_right/image_0.png" ]
[ "<tag_name name=\"bench\" img_idx=\"0\" point=\"[357, 601]\">" ]
"region_ref/1172548560-ab687ea_cam00_obj22-obj21_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Determine one or more locations within a vacant area next to the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give yo...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1172548560-ab687ea_cam00_obj22-obj21_beside/image_0.png" ]
[ "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[846, 596]\">" ]
"fsd_pointrtx_8297"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move apple near orange can. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer should be presented...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointrtx_8297/image_0.jpg" ]
[ "<tag_name name=\"apple\" img_idx=\"0\" point=\"[716, 658]\">", "<tag_name name=\"orange can\" img_idx=\"0\" point=\"[304, 390]\">" ]
"region_ref/117870037-f53019d_cam02_obj24-sink_cabinet-corpus_inside"
null
[ { "from": "human", "value": "<image>\nThe image depicts a vessel delineated by a red rectangular border. Locate any number of spots within a vacant area encompassed by the container's outline. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags,...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/117870037-f53019d_cam02_obj24-sink_cabinet-corpus_inside/image_0.png" ]
[ "<tag_name name=\"vessel\" img_idx=\"0\" point=\"[540, 798]\">" ]
"region_ref/130507889-d5d1346_cam01_obj20-obj5_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several spots within a vacant area next to the circumscribed item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fina...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/130507889-d5d1346_cam01_obj20-obj5_beside/image_0.png" ]
[ "<tag_name name=\"white sculpture\" img_idx=\"0\" point=\"[234, 870]\">", "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[196, 805]\">" ]
"region_ref/1336036009-3cf4623_cam00_obj40-dishwasher-door_0_1_door_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Locate several points in the vacant space on the delineated area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1336036009-3cf4623_cam00_obj40-dishwasher-door_0_1_door_on/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[910, 874]\">" ]
"refcoco_9329"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: bird closest to rock. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_9329/image_0.jpg" ]
[ "<tag_name name=\"bird closest to rock\" img_idx=\"0\" point=\"[607, 351]\">" ]
"region_ref/1225913720-502d64c_cam08_obj21-obj1_behind"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate a few spots within a vacant area situated beyond the encased item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fina...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1225913720-502d64c_cam08_obj21-obj1_behind/image_0.png" ]
[ "<tag_name name=\"encased item\" img_idx=\"0\" point=\"[751, 466]\">" ]
"region_ref/1327314657-d5d1346_cam04_obj40-obj18_beside"
null
[ { "from": "human", "value": "<image>\nThe image features an item encased within a red rectangular border. Determine one or more locations within the neighboring vacant space beside the bordered item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1327314657-d5d1346_cam04_obj40-obj18_beside/image_0.png" ]
[ "<tag_name name=\"yellow folding chair\" img_idx=\"0\" point=\"[658, 173]\">" ]
"region_ref/1135270756-858c02c_cam02_obj44-sink_cabinet-sink_countertop_on"
null
[ { "from": "human", "value": "<image>\nIn the image, there's a region outlined by a red rectangle. Locate several points within the vacant area on this marked surface. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1135270756-858c02c_cam02_obj44-sink_cabinet-sink_countertop_on/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[341, 489]\">" ]
"fsd_pointbridge_52696"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move the silver pot from the left side to the right side of the burner. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimat...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_52696/image_0.jpg" ]
[ "<tag_name name=\"silver pot\" img_idx=\"0\" point=\"[710, 538]\">", "<tag_name name=\"burner\" img_idx=\"0\" point=\"[640, 359]\">" ]
"region_ref/1133246886-0d5e33c_cam02_obj42-wall_cabinet_1-surface_2_0_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Select one or more points within a vacant space on the outlined area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final ans...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1133246886-0d5e33c_cam02_obj42-wall_cabinet_1-surface_2_0_on/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[278, 194]\">" ]
"refcoco_11948"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: dude doing handstand. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_11948/image_0.jpg" ]
[ "<tag_name name=\"dude doing handstand\" img_idx=\"0\" point=\"[507, 496]\">" ]
"roborefit_13754"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: will you please give me the sweet strawberry. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final an...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_13754/image_0.png" ]
[ "<tag_name name=\"strawberry\" img_idx=\"0\" point=\"[546, 208]\">" ]
"object_ref/1185667664-d5b363c_cam09_obj11-base_cabinet-drawer_0_0_inside"
null
[ { "from": "human", "value": "<image>\nThe image features a container delineated by a red rectangular border. Locate and pinpoint several spots on an item that is situated within the bounds of the container highlighted in red. The answer should be presented in JSON format. Provide your thinking process betwe...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1185667664-d5b363c_cam09_obj11-base_cabinet-drawer_0_0_inside/image_0.png" ]
[ "<tag_name name=\"wooden box\" img_idx=\"0\" point=\"[234, 410]\">", "<tag_name name=\"black stand\" img_idx=\"0\" point=\"[339, 406]\">", "<tag_name name=\"white electronic device\" img_idx=\"0\" point=\"[305, 658]\">" ]
"refcoco_7849"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: top right cat. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and <...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_7849/image_0.jpg" ]
[ "<tag_name name=\"top right cat\" img_idx=\"0\" point=\"[817, 354]\">" ]
"fsd_pointbridge_94651"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: remove the green rectangle from the blue rectangle and put it back to the top of the blue rectangle.. Use 2D points to mark the target location where the object you need to manipul...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_94651/image_0.jpg" ]
[ "<tag_name name=\"green rectangle\" img_idx=\"0\" point=\"[587, 130]\">", "<tag_name name=\"blue rectangle\" img_idx=\"0\" point=\"[593, 206]\">" ]
"refcoco_4076"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: first banana closest to us. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_4076/image_0.jpg" ]
[ "<tag_name name=\"banana\" img_idx=\"0\" point=\"[458, 371]\">" ]
"region_ref/1241470817-bf915d8_cam10_obj40-dishwasher-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area delineated by a red rectangle. Locate a few points within an unoccupied area on the outlined surface. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1241470817-bf915d8_cam10_obj40-dishwasher-top_on/image_0.png" ]
[ "<tag_name name=\"gray countertop\" img_idx=\"0\" point=\"[573, 640]\">" ]
"object_ref/123573258-efbbcd9_cam02_obj24-obj0_left"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several spots on an item that is situated to the left of the item enclosed by the rectangle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tag...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/123573258-efbbcd9_cam02_obj24-obj0_left/image_0.png" ]
[ "<tag_name name=\"white chair\" img_idx=\"0\" point=\"[640, 489]\">", "<tag_name name=\"black countertop\" img_idx=\"0\" point=\"[451, 507]\">", "<tag_name name=\"oven drawer\" img_idx=\"0\" point=\"[339, 861]\">" ]
"object_ref/1084918816-63bd2a7_cam01_obj14-oven-heater_1_1_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area delineated by a red rectangle. Pinpoint one or several locations upon an item that is situated upon the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then g...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1084918816-63bd2a7_cam01_obj14-oven-heater_1_1_on/image_0.png" ]
[ "<tag_name name=\"white rectangular block\" img_idx=\"0\" point=\"[375, 194]\">" ]
"refcoco_6182"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: child rigth. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and </a...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_6182/image_0.jpg" ]
[ "<tag_name name=\"child\" img_idx=\"0\" point=\"[675, 640]\">", "<tag_name name=\"pizza box\" img_idx=\"0\" point=\"[318, 750]\">", "<tag_name name=\"glass of drink\" img_idx=\"0\" point=\"[934, 648]\">" ]
"refcoco_19811"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: a male spectator in a blue shirt. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_19811/image_0.jpg" ]
[ "<tag_name name=\"male spectator, blue shirt\" img_idx=\"0\" point=\"[850, 634]\">" ]
"roborefit_8872"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I need the purple cylindrical vitamin bottle on the middle shelf. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and the...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_8872/image_0.png" ]
[ "<tag_name name=\"purple cylindrical vitamin bottle, middle shelf\" img_idx=\"0\" point=\"[598, 731]\">" ]
"roborefit_32050"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: I want to grab the facial cleanser with a blue cap on the left. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then ...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_32050/image_0.png" ]
[ "<tag_name name=\"facial cleanser with a blue cap on the left\" img_idx=\"0\" point=\"[875, 806]\">" ]
"object_ref/1307552506-9b5268c_cam08_obj30-oven-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features an area outlined by a red rectangle. Locate several spots on an item that rests upon the marked area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer b...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1307552506-9b5268c_cam08_obj30-oven-top_on/image_0.png" ]
[ "<tag_name name=\"white rectangular object\" img_idx=\"0\" point=\"[507, 494]\">", "<tag_name name=\"yellow round object\" img_idx=\"0\" point=\"[339, 481]\">", "<tag_name name=\"knife\" img_idx=\"0\" point=\"[361, 478]\">", "<tag_name name=\"small white stand\" img_idx=\"0\" point=\"[185, 507]\">" ]
"object_ref/1321205230-fe2f065_cam04_obj29-base_cabinet-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane outlined by a red rectangular border. Locate any number of spots situated on an item that rests on the marked plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then g...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1321205230-fe2f065_cam04_obj29-base_cabinet-top_on/image_0.png" ]
[ "<tag_name name=\"wooden countertop\" img_idx=\"0\" point=\"[480, 658]\">", "<tag_name name=\"yellow donut\" img_idx=\"0\" point=\"[496, 531]\">", "<tag_name name=\"red chair\" img_idx=\"0\" point=\"[630, 471]\">", "<tag_name name=\"white table\" img_idx=\"0\" point=\"[597, 548]\">", "<tag_name name=\"metal...
"roborefit_312"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: could you fetch me the rubik's cube. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer betw...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_312/image_0.png" ]
[ "<tag_name name=\"rubik's cube\" img_idx=\"0\" point=\"[430, 601]\">" ]
"refcoco_703"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: guy blue. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and </answ...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_703/image_0.jpg" ]
[ "<tag_name name=\"guy blue\" img_idx=\"0\" point=\"[816, 304]\">" ]
"region_ref/1210605065-4fb8b7b_cam05_obj33-obj14_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangular border. Locate several points within the vacant area situated to the right of the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1210605065-4fb8b7b_cam05_obj33-obj14_right/image_0.png" ]
[ "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[410, 183]\">" ]
"region_ref/109988666-4fb8b7b_cam04_obj2-oven-heater_1_1_on"
null
[ { "from": "human", "value": "<image>\nThe image depicts an area outlined by a red rectangle. Locate any number of points situated in a vacant space on the outlined area. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your fin...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/109988666-4fb8b7b_cam04_obj2-oven-heater_1_1_on/image_0.png" ]
[ "<tag_name name=\"countertop\" img_idx=\"0\" point=\"[605, 548]\">", "<tag_name name=\"countertop\" img_idx=\"0\" point=\"[614, 576]\">" ]
"refcoco_19411"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: The black honda. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_19411/image_0.jpg" ]
[ "<tag_name name=\"black honda\" img_idx=\"0\" point=\"[154, 130]\">" ]
"object_ref/1057228867-1ed231c_cam09_obj31-obj14_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate several points on an item that is situated to the right of the object with the red outline. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1057228867-1ed231c_cam09_obj31-obj14_right/image_0.png" ]
[ "<tag_name name=\"wooden cabinet\" img_idx=\"0\" point=\"[853, 194]\">" ]
"roborefit_16920"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you please fetch me the facial cleanser with a black handy pump. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, an...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_16920/image_0.png" ]
[ "<tag_name name=\"facial cleanser with a black handy pump\" img_idx=\"0\" point=\"[496, 431]\">" ]
"fsd_pointbridge_50585"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: move the cloth from bottom to top on the table. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_50585/image_0.jpg" ]
[ "<tag_name name=\"yellow cloth\" img_idx=\"0\" point=\"[740, 517]\">" ]
"roborefit_32931"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: would you pass me the large bottled shampoo. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final ans...
er1_with_xml
[ "images/datasets/er1/images/roborefit/roborefit_32931/image_0.png" ]
[ "<tag_name name=\"large bottled shampoo\" img_idx=\"0\" point=\"[464, 250]\">" ]
"fsd_pointbridge_5545"
null
[ { "from": "human", "value": "<image>\nYou are currently a robot performing robotic manipulation tasks. The task instruction is: pick up scissors and put into drawer. Use 2D points to mark the target location where the object you need to manipulate in the task should ultimately be moved. The answer should be...
er1_with_xml
[ "images/datasets/er1/images/FSD_points/fsd_pointbridge_5545/image_0.jpg" ]
[ "<tag_name name=\"scissors\" img_idx=\"0\" point=\"[601, 437]\">", "<tag_name name=\"drawer\" img_idx=\"0\" point=\"[589, 670]\">" ]
"region_ref/1312454043-b55b742_cam00_obj30-obj11_front"
null
[ { "from": "human", "value": "<image>\nIn the image, an item is enclosed within a red rectangle. Select one or more locations on a vacant space that is in front of the demarcated item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1312454043-b55b742_cam00_obj30-obj11_front/image_0.png" ]
[ "<tag_name name=\"red rectangle\" img_idx=\"0\" point=\"[430, 375]\">" ]
"region_ref/1230222740-1ed231c_cam04_obj26-refrigerator-shelf_1_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane outlined by a red rectangle. Locate a few points within a vacant area on the delineated plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1230222740-1ed231c_cam04_obj26-refrigerator-shelf_1_on/image_0.png" ]
[ "<tag_name name=\"shelf\" img_idx=\"0\" point=\"[450, 716]\">" ]
"object_ref/1200754856-b55b742_cam09_obj18-obj10_right"
null
[ { "from": "human", "value": "<image>\nThe image features an item encircled by a red rectangle. Locate at least one point on an item situated to the right of the item encased by the rectangle. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1200754856-b55b742_cam09_obj18-obj10_right/image_0.png" ]
[ "<tag_name name=\"item situated to the right of the item encased by the rectangle\" img_idx=\"0\" point=\"[546, 517]\">" ]
"object_ref/1282516607-f53019d_cam04_obj35-obj4_left"
null
[ { "from": "human", "value": "<image>\nThe image displays an item encircled by a red rectangle. Locate several points on an item situated to the left side of the encircled item. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give y...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1282516607-f53019d_cam04_obj35-obj4_left/image_0.png" ]
[ "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[456, 473]\">", "<tag_name name=\"item situated to the left side of the encircled item\" img_idx=\"0\" point=\"[380, 471]\">", "<tag_name name=\"encircled item\" img_idx=\"0\" point=\"[458, 461]\">", "<tag_name name=\"item situated to the left side of t...
"region_ref/1176629282-f53019d_cam07_obj24-obj14_front"
null
[ { "from": "human", "value": "<image>\nThe image depicts an item encircled by a red rectangle. Locate and identify several points within the vacant area that lies before the encased object. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1176629282-f53019d_cam07_obj24-obj14_front/image_0.png" ]
[ "<tag_name name=\"encased object\" img_idx=\"0\" point=\"[274, 461]\">" ]
"object_ref/1253565281-858c02c_cam09_obj45-wall_cabinet_2-surface_1_0_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane outlined by a red rectangular border. Locate any number of spots situated on an item that rests on the marked plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then g...
er1_with_xml
[ "images/datasets/er1/images/robopoint/object_ref/1253565281-858c02c_cam09_obj45-wall_cabinet_2-surface_1_0_on/image_0.png" ]
[ "<tag_name name=\"item that rests on the marked plane\" img_idx=\"0\" point=\"[640, 194]\">" ]
"region_ref/1085811993-9b5268c_cam00_obj27-base_cabinet-top_on"
null
[ { "from": "human", "value": "<image>\nThe image features a plane outlined by a red rectangle. Locate a few points within a vacant area on the delineated plane. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer ...
er1_with_xml
[ "images/datasets/er1/images/robopoint/region_ref/1085811993-9b5268c_cam00_obj27-base_cabinet-top_on/image_0.png" ]
[ "<tag_name name=\"countertop\" img_idx=\"0\" point=\"[513, 548]\">" ]
"refcoco_5402"
null
[ { "from": "human", "value": "<image>\nProvide one or more points coordinate of objects region this sentence describes: right guy. The answer should be presented in JSON format. Provide your thinking process between the <think> and </think> tags, and then give your final answer between the <answer> and </ans...
er1_with_xml
[ "images/datasets/er1/images/refcoco/refcoco_5402/image_0.jpg" ]
[ "<tag_name name=\"right guy\" img_idx=\"0\" point=\"[875, 240]\">", "<tag_name name=\"motorcycle\" img_idx=\"0\" point=\"[693, 481]\">" ]