{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:15:33Z","timestamp":1765520133183,"version":"3.48.0"},"reference-count":35,"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"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iros60139.2025.11246374","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"20974-20981","source":"Crossref","is-referenced-by-count":0,"title":["ManipGPT: Is Affordance Segmentation by Large Vision Models Enough for Articulated Object Manipulation?"],"prefix":"10.1109","author":[{"given":"Taewhan","family":"Kim","sequence":"first","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hojin","family":"Bae","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeming","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoqi","family":"Li","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Iaroslav","family":"Ponomarenko","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihai","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hao","family":"Dong","sequence":"additional","affiliation":[{"name":"Peking University,CFCS, School of Computer Science"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00674"},{"article-title":"Vat-mart: Learning visual action trajectory proposals for manipulating 3d articulated objects","year":"2021","author":"Wu","key":"ref2"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2022.3142397"},{"article-title":"Voxposer: Composable 3d value maps for robotic manipulation with language models","year":"2023","author":"Huang","key":"ref4"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01710"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2022.XVIII.018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48506.2021.9561132"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IROS47612.2022.9982029"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS51168.2021.9636054"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611073"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00376"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00110"},{"key":"ref15","article-title":"Segment anything in high quality","volume":"36","author":"Ke","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Sam-e: Leveraging visual foundation model with sequence imitation for embodied manipulation","year":"2024","author":"Zhang","key":"ref16"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10801993"},{"key":"ref18","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"article-title":"Llama: Open and efficient foundation language models","year":"2023","author":"Touvron","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10341672"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8206484"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01111"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2020.106268"},{"year":"2010","key":"ref28","article-title":"Pixabay.com"},{"year":"2017","key":"ref29","article-title":"Cvat: Computer vision annotation tool"},{"article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","year":"2020","author":"Dosovitskiy","key":"ref30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160606"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00100"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00358"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01146"}],"event":{"name":"2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2025,10,19]]},"location":"Hangzhou, China","end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11245651\/11245652\/11246374.pdf?arnumber=11246374","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T06:11:08Z","timestamp":1765519868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246374\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246374","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}