{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:20:17Z","timestamp":1780536017177,"version":"3.54.1"},"reference-count":65,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01114","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"11980-11990","source":"Crossref","is-referenced-by-count":1,"title":["RAGNet: Large-Scale Reasoning-Based Affordance Segmentation Benchmark Towards General Grasping"],"prefix":"10.1109","author":[{"given":"Dongming","family":"Wu","sequence":"first","affiliation":[{"name":"The Chinese University of Hong Kong"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanping","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Saike","family":"Huang","sequence":"additional","affiliation":[{"name":"Dexmal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingfei","family":"Liu","sequence":"additional","affiliation":[{"name":"Dexmal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Jia","sequence":"additional","affiliation":[{"name":"Dexmal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nian","family":"Liu","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Dai","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tiancai","family":"Wang","sequence":"additional","affiliation":[{"name":"Dexmal"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rao Muhammad","family":"Anwer","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fahad Shahbaz","family":"Khan","sequence":"additional","affiliation":[{"name":"Mohamed bin Zayed University of Artificial Intelligence"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianbing","family":"Shen","sequence":"additional","affiliation":[{"name":"University of Macau,SKL-IOTSC, CIS"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/ciun.1994.1001"},{"key":"ref2","article-title":"Gpt-4 technical report","volume-title":"arXiv preprint","author":"Achiam","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00657"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00228"},{"key":"ref11","article-title":"Learning visual attributes","author":"Ferrari","year":"2007","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref17","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","author":"Huang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Rekep: Spatio-temporal reasoning of relational keypoint constraints for robotic manipulation","author":"Huang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.2974707"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01352"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00014"},{"key":"ref23","author":"Kirillov","year":"2023","journal-title":"In ICCV"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2010.08.002"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"ref28","first-page":"2","article-title":"Learning precise affordances from egocentric videos for robotic manipulation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"In ICML"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01351"},{"key":"ref32","article-title":"Visual instruction tuning","author":"Liu","year":"2024","journal-title":"NeurIPS"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.96"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00658"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref38","article-title":"Pivot: Iterative visual prompting elicits actionable knowledge for vlms","author":"Nasiriany","year":"2024","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206484"},{"key":"ref40","article-title":"Llarva: Vision-action instruction tuning enhances robot learning","author":"Niu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref41","first-page":"2","article-title":"Open x-embodiment: Robotic learning datasets and rt-x models","author":"O\u2019Neill","year":"2023","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01988"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00165"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref45","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"In ICML"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00690"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref48","article-title":"Language embedded radiance fields for zero-shot taskoriented grasping","author":"Rashid","year":"2023","journal-title":"In CoRL"},{"key":"ref49","first-page":"4","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.552"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref52","article-title":"Cliport: What and where pathways for robotic manipulation","author":"Shridhar","year":"2022","journal-title":"In CoRL"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"ref54","article-title":"Grasp-anything: Large-scale grasp dataset from foundation models","author":"Dinh Vuong","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","article-title":"Languagedriven grasp detection","author":"Dinh Vuong","year":"2024","journal-title":"In CVPR"},{"key":"ref56","article-title":"Bridgedata v2: A dataset for robot learning at scale","author":"Rich Walke","year":"2023","journal-title":"In CoRL"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01556"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477095"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01001"},{"key":"ref62","first-page":"2","article-title":"Uniaff: A unified representation of affordances for tool usage and articulation with vision-language models","author":"Yu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00391"},{"key":"ref64","article-title":"Judging llm-as-a-judge with mt-bench and chatbot arena","author":"Zheng","year":"2023","journal-title":"NeurIPS"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01840"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443439.pdf?arnumber=11443439","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:11:37Z","timestamp":1777612297000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443439\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01114","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}