{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T06:40:59Z","timestamp":1776235259051,"version":"3.50.1"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100003661","name":"Korea Institute for Advancement of Technology","doi-asserted-by":"publisher","award":["RS-2025-25460896"],"award-info":[{"award-number":["RS-2025-25460896"]}],"id":[{"id":"10.13039\/501100003661","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2021-II211343-GSAI"],"award-info":[{"award-number":["RS-2021-II211343-GSAI"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2022-II220951-LBA"],"award-info":[{"award-number":["RS-2022-II220951-LBA"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100010418","name":"Institute for Information and Communications Technology Promotion","doi-asserted-by":"publisher","award":["RS-2022-II220953-PICA"],"award-info":[{"award-number":["RS-2022-II220953-PICA"]}],"id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2023-00274280-HEI"],"award-info":[{"award-number":["RS-2023-00274280-HEI"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00353991-SPARC"],"award-info":[{"award-number":["RS-2024-00353991-SPARC"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["RS-2024-00358416-AutoRL"],"award-info":[{"award-number":["RS-2024-00358416-AutoRL"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003662","name":"Korea Evaluation Institute of Industrial Technology","doi-asserted-by":"publisher","award":["RS-2025-25453780"],"award-info":[{"award-number":["RS-2025-25453780"]}],"id":[{"id":"10.13039\/501100003662","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3681732","type":"journal-article","created":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T20:01:14Z","timestamp":1775592074000},"page":"1-1","source":"Crossref","is-referenced-by-count":0,"title":["One-shot 3D Affordance Learning for Multi-stage Robotic Manipulation"],"prefix":"10.1109","author":[{"given":"Hyunseo","family":"Kim","sequence":"first","affiliation":[{"name":"Interdisciplinary Program in Neuroscience, Seoul National University, Seoul, Republic of Korea"}]},{"given":"Yeon-Ji","family":"Song","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Neuroscience, Seoul National University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9601-3863","authenticated-orcid":false,"given":"Minsu","family":"Lee","sequence":"additional","affiliation":[{"name":"School of AI Convergence, Sungshin Women’s University, Seoul, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9890-0389","authenticated-orcid":false,"given":"Byoung-Tak","family":"Zhang","sequence":"additional","affiliation":[{"name":"Interdisciplinary Program in Neuroscience, Seoul National University, Seoul, Republic of Korea"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Affordances in robotic tasks\u2014A survey","author":"Ard\u00f3n","year":"2020","journal-title":"arXiv:2004.07400"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/tcds.2023.3277288"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.4324\/9781315740218"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2019.2894439"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01324"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01351"},{"key":"ref7","article-title":"3D-TAFS: A training-free framework for 3D affordance segmentation","author":"Chu","year":"2024","journal-title":"arXiv:2409.10078"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00298"},{"key":"ref9","first-page":"1541","article-title":"O3Afford: One-shot 3D object-to-object affordance grounding for generalizable robotic manipulation","volume-title":"Proc. 9th Conf. Robot Learn. (Proceedings of Machine Learning Research), vol.","volume":"305","author":"Tian"},{"key":"ref10","first-page":"10581","article-title":"Learning precise affordances from egocentric videos for robotic manipulation","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Li"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3592433"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754778"},{"key":"ref13","article-title":"SeqAffordSplat: Scene-level sequential affordance reasoning on 3D Gaussian splatting","author":"Li","year":"2025","journal-title":"arXiv:2507.23772"},{"key":"ref14","first-page":"1443","article-title":"GraspSplats: Efficient manipulation with 3D feature splatting","volume-title":"Proc. 8th Annu. Conf. Robot Learn. (Proceedings of Machine Learning Research), vol.","volume":"270","author":"Ji"},{"key":"ref15","first-page":"11980","article-title":"RAGNet: Large-scale reasoning-based affordance segmentation benchmark towards general grasping","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wu"},{"key":"ref16","first-page":"7440","article-title":"LUDVIG: Learning-free uplifting of 2D visual features to Gaussian splatting scenes","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Marrie"},{"key":"ref17","first-page":"550","article-title":"One-shot transfer of affordance regions? AffCorrs!","volume-title":"Proc. 6th Conf. Robot Learn. (CoRL)","author":"Hadjivelichkov"},{"key":"ref18","first-page":"4748","article-title":"Splat-MOVER: Multi-stage, open-vocabulary robotic manipulation via editable Gaussian splatting","volume-title":"Proc. 8th Annu. Conf. Robot Learn. (Proceedings of Machine Learning Research), vol.","volume":"270","author":"Shorinwa"},{"key":"ref19","first-page":"90","volume-title":"AdaAfford: Learning to Adapt Manipulation Affordance for 3D Articulated Objects via Few-Shot Interactions","author":"Wang","year":"2022"},{"key":"ref20","article-title":"Agentic scene policies: Unifying space, semantics, and affordances for robot action","author":"Morin","year":"2025","journal-title":"arXiv:2509.19571"},{"key":"ref21","first-page":"540","article-title":"VoxPoser: Composable 3D value maps for robotic manipulation with language models","volume-title":"Proc. 7th Conf. Robot Learn. (Proceedings of Machine Learning Research), vol.","volume":"229","author":"Huang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2019.2933815"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72940-9_13"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/icra55743.2025.11128868"},{"key":"ref25","first-page":"9759","article-title":"Coa-vla: Improving vision-language-action models via visual-text chain-of-affordance","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis. (ICCV)","author":"Li"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref27","first-page":"11818","article-title":"Afforddexgrasp: Open-set language-guided dexterous grasp with generalizable-instructive affordance","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wei"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2024.3432348"},{"key":"ref29","first-page":"178","article-title":"Language embedded radiance fields for zero-shot task-oriented grasping","volume-title":"Proc. 7th Conf. Robot Learn.","author":"Rashid"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00165"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2017.16"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32318"},{"key":"ref33","first-page":"4654","article-title":"Task-aware 3D affordance segmentation via 2D guidance and geometric refinement","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Lian"},{"key":"ref34","article-title":"GLOVER: Generalizable open-vocabulary affordance reasoning for task-oriented grasping","author":"Ma","year":"2024","journal-title":"arXiv:2411.12286"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01001"},{"key":"ref36","article-title":"GauTOAO: Gaussian-based task-oriented affordance of objects","author":"Wang","year":"2024","journal-title":"arXiv:2409.11941"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00164"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/lra.2023.3326001"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"ref40","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref42","first-page":"405","article-title":"Distilled feature fields enable few-shot language-guided manipulation","volume-title":"Proc. 7th Annu. Conf. Robot Learn. (Proceedings of Machine Learning Research), vol.","volume":"229","author":"Shen"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1177\/0278364917735594"},{"key":"ref44","first-page":"28085","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","volume":"2025","author":"Ravi"},{"key":"ref45","volume-title":"Robotic Manipulation","author":"Tedrake","year":"2024"},{"key":"ref46","first-page":"696","volume-title":"Extract Free Dense Labels From CLIP","author":"Zhou","year":"2022"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00182"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/6514899\/11475721.pdf?arnumber=11475721","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T05:41:01Z","timestamp":1776231661000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11475721\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3681732","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}