{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:07:44Z","timestamp":1777889264244,"version":"3.51.4"},"reference-count":34,"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","award":["62473007"],"award-info":[{"award-number":["62473007"]}],"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\/iccv51701.2025.01319","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14218-14227","source":"Crossref","is-referenced-by-count":0,"title":["Recognizing Actions From Robotic View for Natural Human-Robot Interaction"],"prefix":"10.1109","author":[{"given":"Ziyi","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peiming","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhichao","family":"Deng","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Can","family":"Wang","sequence":"additional","affiliation":[{"name":"Kiel University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Liu","sequence":"additional","affiliation":[{"name":"Lancaster University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[{"name":"State University of New York at Buffalo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mengyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of General Artificial Intelligence, Peking University, Shenzhen Graduate School"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00116"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01888"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.iot.2025.101497"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01761-6"},{"key":"ref5","author":"Dosovitskiy","year":"2020","journal-title":"An image is worth 16x16 words: Transformers for image recognition at scale"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01398"},{"key":"ref7","article-title":"Kankanhalli","author":"Fan","year":"2022","journal-title":"Pstnet: Point spatio-temporal convolution on point cloud sequences. Cornell University"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3135117"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3161735"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.53"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3282631"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01049"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref18","author":"Loshchilov","year":"2017","journal-title":"Decoupled weight decay regularization"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11866-6_2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00182"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00123"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01514"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref25","article-title":"Visualizing data using t -sne","author":"Van der Maaten","year":"2008","journal-title":"Journal of machine learning research"},{"key":"ref26","author":"Wang","year":"2024","journal-title":"Yolov10: Real-time end-to-end object detection"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2868668"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref29","author":"Wang","year":"2022","journal-title":"Internvideo: General video foundation models via generative and discriminative learning"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.406"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108282"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.288"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00832"}],"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\/11444260.pdf?arnumber=11444260","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:11Z","timestamp":1777612091000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444260\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01319","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}