{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T15:53:59Z","timestamp":1781193239625,"version":"3.54.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0111902"],"award-info":[{"award-number":["2021ZD0111902"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62172022"],"award-info":[{"award-number":["62172022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62376014"],"award-info":[{"award-number":["62376014"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tcsvt.2023.3324595","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:16:34Z","timestamp":1697220994000},"page":"3368-3382","source":"Crossref","is-referenced-by-count":4,"title":["OASNet: Object Affordance State Recognition Network With Joint Visual Features and Relational Semantic Embeddings"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2011-100X","authenticated-orcid":false,"given":"Dongpan","family":"Chen","sequence":"first","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7722-7172","authenticated-orcid":false,"given":"Dehui","family":"Kong","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6895-6672","authenticated-orcid":false,"given":"Jinghua","family":"Li","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4977-0183","authenticated-orcid":false,"given":"Lichun","family":"Wang","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0804-8688","authenticated-orcid":false,"given":"Junna","family":"Gao","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3121-1823","authenticated-orcid":false,"given":"Baocai","family":"Yin","sequence":"additional","affiliation":[{"name":"Beijing Key Laboratory of Multimedia and Intelligent Software Technology, Beijing Artificial Intelligence Institute, Beijing University of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s43154-020-00021-6"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01414"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126287"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07937-4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103531"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3137605"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119334"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2975566"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3005807"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109203"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00532"},{"key":"ref14","first-page":"1","article-title":"Semi-supervised classification with graph convolutional networks","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Welling"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01621"},{"key":"ref16","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9860016"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108487"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460902"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2015.7139369"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.552"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1177\/0278364913478446"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01642-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00108"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00228"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00182"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00658"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00229"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.58"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32226-7_81"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2019.2952597"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2925615"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01176-2"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107100"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107050"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3079900"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3083978"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_25"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_4"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232797"},{"key":"ref43","article-title":"Efficient self-supervised vision transformers for representation learning","author":"Li","year":"2021","journal-title":"arXiv:2106.09785"},{"key":"ref44","article-title":"RelViT: Concept-guided vision transformer for visual relational reasoning","author":"Ma","year":"2022","journal-title":"arXiv:2204.11167"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00377"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01563"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00611"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00609"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00048"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"issue":"1","key":"ref53","first-page":"3","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. ICML","volume":"30","author":"Maas"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.251"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00139"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00082"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00861"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141886"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i10.17098"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00025"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234993"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00332"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00331"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00269"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00272"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.330"},{"key":"ref72","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.129"},{"key":"ref74","first-page":"1","article-title":"Attentional pooling for action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Girdhar"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00046"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00678"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01790"},{"key":"ref78","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref79","article-title":"LongFormer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref80","first-page":"16857","article-title":"MPNet: Masked and permuted pre-training for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Song"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref82","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. ICLR","author":"Mikolov"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10527423\/10285126.pdf?arnumber=10285126","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,10]],"date-time":"2024-05-10T17:36:10Z","timestamp":1715362570000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10285126\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":82,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3324595","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,5]]}}}