{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T17:42:55Z","timestamp":1783964575113,"version":"3.55.0"},"reference-count":62,"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\/iccv51701.2025.00985","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10581-10591","source":"Crossref","is-referenced-by-count":3,"title":["Learning Precise Affordances From Egocentric Videos for Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Gen","family":"Li","sequence":"first","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nikolaos","family":"Tsagkas","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jifei","family":"Song","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruaridh","family":"Mon-Williams","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sethu","family":"Vijayakumar","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Shao","sequence":"additional","affiliation":[{"name":"Huawei Noah's Ark Lab"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Laura","family":"Sevilla-Lara","sequence":"additional","affiliation":[{"name":"University of Edinburgh"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Deep vit features as dense visual descriptors","author":"Amir","year":"2022","journal-title":"ECCVW What is Motion For"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref5","article-title":"Vision transformer adapter for dense predictions","volume-title":"The Eleventh International Conference on Learning Representations","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"ref7","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"In Proceedings of the European conference on computer vision","author":"Damen"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2991965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610923"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3349832"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2023.3281153"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00228"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref16","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"International Conference on Learning Representations","author":"Hu"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801352"},{"key":"ref18","article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","volume-title":"7th Annual Conference on Robot Learning","author":"Huang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222906"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_41"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00328"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02034"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-025-01005-x"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00483"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00878"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206484"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341553"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00932"},{"key":"ref40","year":"2023","journal-title":"arXiv preprint"},{"key":"ref41","year":"2023","journal-title":"OpenAI. Gpt-4v(ision) system card"},{"key":"ref42","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Transactions on Machine Learning Research"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref44","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"7th Annual Conference on Robot Learning","author":"Rashid"},{"key":"ref45","article-title":"Grounded sam: Assembling open-world models for diverse visual tasks","author":"Ren","year":"2024","journal-title":"arXiv preprint"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref48","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"7th Annual Conference on Robot Learning","author":"Shen"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561877"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1561\/0600000009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_30"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801488"},{"key":"ref53","article-title":"D3fields: Dynamic 3d descriptor fields for zero-shot generalizable robotic manipulation","volume-title":"ICRA 2024 Workshop on 3D Visual Representations for Robot Manipulation","author":"Wang","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2105.15203"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01525"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02028"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2025.2535676"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00219"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00050"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01075"}],"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\/11445413.pdf?arnumber=11445413","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:23:05Z","timestamp":1777612985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445413\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00985","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}