{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:50:28Z","timestamp":1766055028770,"version":"3.48.0"},"reference-count":21,"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\/100006190","name":"Research and Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006190","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012492","name":"Youth Innovation Promotion Association","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012492","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\/iros60139.2025.11246263","type":"proceedings-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:54:45Z","timestamp":1764269685000},"page":"11599-11606","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Action Localization and Recognition for Intelligent Perception of Surgical Robots"],"prefix":"10.1109","author":[{"given":"Yaqin","family":"Peng","sequence":"first","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gui-Bin","family":"Bian","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhen","family":"Li","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruichen","family":"Ma","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qiang","family":"Ye","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,Institute of Automation,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9340816"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41746-022-00707-5"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41588-024-01831-6"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1002\/aisy.202300268"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02493-z"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2493100"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CBMS58004.2023.00187"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s00464-024-11486-3"},{"key":"ref11","first-page":"6827","article-title":"What makes for good views for contrastive learning?","volume":"33","author":"Tian","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11548-021-02382-5"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"ref14","first-page":"2010","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Alexey","year":"2020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330925"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref17","first-page":"5679","article-title":"Self-supervised co-training for video representation learning","volume":"33","author":"Han","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00092"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01562"},{"key":"ref20","first-page":"10078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume":"35","author":"Tong","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref21","first-page":"2211.10636","article-title":"Everest: Efficient masked video autoencoder by removing redundant spatiotemporal tokens","author":"Hwang","year":"2022"}],"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\/11246263.pdf?arnumber=11246263","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T10:46:17Z","timestamp":1766054777000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11246263\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":21,"URL":"https:\/\/doi.org\/10.1109\/iros60139.2025.11246263","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}