{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:15:39Z","timestamp":1780535739721,"version":"3.54.1"},"reference-count":50,"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\/iccv51701.2025.01368","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14743-14753","source":"Crossref","is-referenced-by-count":1,"title":["2HandedAfforder: Learning Precise Actionable Bimanual Affordances from Human Videos"],"prefix":"10.1109","author":[{"given":"Marvin","family":"Heidinger","sequence":"first","affiliation":[{"name":"Technische Universit¨at Darmstadt,Computer Science Department,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Snehal","family":"Jauhri","sequence":"additional","affiliation":[{"name":"Technische Universit¨at Darmstadt,Computer Science Department,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vignesh","family":"Prasad","sequence":"additional","affiliation":[{"name":"Technische Universit¨at Darmstadt,Computer Science Department,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Georgia","family":"Chalvatzaki","sequence":"additional","affiliation":[{"name":"Technische Universit¨at Darmstadt,Computer Science Department,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01324"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0938"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_37"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref6","article-title":"Epic-kitchens visor benchmark: Video segmentations and object relations","volume-title":"Proceedings of the Neural Information Processing Systems (NeurIPS) Track on Datasets and Benchmarks","author":"Darkhalil"},{"key":"ref7","volume-title":"Molmo and pixmo: Open weights and open data for state-of-the-art multimodal models","author":"Deitke","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2024.XX.068"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01627"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.4324\/9781315816852-21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8967782"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00329"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01834"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref16","first-page":"550","article-title":"One-shot transfer of affordance regions? affcorrs!","volume-title":"Conference on Robot Learning","author":"Hadjivelichkov"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20074-8_8"},{"key":"ref18","article-title":"Lora: Low-rank adaptation of large language models","author":"Hu","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref19","volume-title":"Toronto annotation suite","author":"Kar","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3196158"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3654777.3676449"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01051"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00298"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00682"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01469"},{"key":"ref29","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02054"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref32","volume-title":"Lang-segment-anything","author":"Medeiros","year":"2024"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2016.79"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206484"},{"key":"ref35","volume-title":"Gpt-4 technical report","author":"Achiam","year":"2024"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/Humanoids58906.2024.10769851"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01143"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01988"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00165"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00754"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref42","article-title":"Sam 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref43","first-page":"2980","article-title":"Focal loss for dense object detection","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Ross"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1177\/1059712319855836"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00674"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00989"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01417"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19818-2_8"}],"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\/11446243.pdf?arnumber=11446243","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:09:17Z","timestamp":1777612157000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446243\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":50,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01368","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}