{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T06:53:42Z","timestamp":1785135222483,"version":"3.55.0"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"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":["62032006"],"award-info":[{"award-number":["62032006"]}],"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","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"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":[[2025,6]]},"DOI":"10.1109\/tcsvt.2025.3527312","type":"journal-article","created":{"date-parts":[[2025,1,8]],"date-time":"2025-01-08T20:39:21Z","timestamp":1736368761000},"page":"5912-5924","source":"Crossref","is-referenced-by-count":2,"title":["Semantic-Aware Late-Stage Supervised Contrastive Learning for Fine-Grained Action Recognition"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-4526-3858","authenticated-orcid":false,"given":"Yijun","family":"Pan","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Data Science, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3897-3049","authenticated-orcid":false,"given":"Quan","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0788-8826","authenticated-orcid":false,"given":"Yueyi","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1822-3731","authenticated-orcid":false,"given":"Zilei","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3638-5566","authenticated-orcid":false,"given":"Xiaoyan","family":"Sun","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7266-5579","authenticated-orcid":false,"given":"Feng","family":"Wu","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Brain-Inspired Intelligence Technology and Application, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP49819.2020.9301827"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00912"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00651"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_9"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00226"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_23"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127027"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01346"},{"key":"ref11","first-page":"1","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref13","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Khosla"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00100"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01025"},{"key":"ref16","first-page":"720","article-title":"Scaling egocentric vision: The EPIC-KITCHENS dataset","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Damen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref19","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","author":"Simonyan"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6836"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref31","article-title":"Uniformer: Unified transformer for efficient spatial\u2013temporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref33","article-title":"UniFormerV2: Spatiotemporal learning by arming image ViTs with video UniFormer","author":"Li","year":"2022","journal-title":"arXiv:2211.09552"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20062-5_36"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01792"},{"key":"ref36","first-page":"1","article-title":"AIM: Adapting image models for efficient video understanding","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yang"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19772-7_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_23"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref41","first-page":"10078","article-title":"VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Zhan"},{"key":"ref42","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Alayrac"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73013-9_23"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00269"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00315"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00233"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00113"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859982"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235522"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3363042"},{"key":"ref52","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104013","article-title":"CTM: Cross-time temporal module for fine-grained action recognition","volume":"244","author":"Qian","year":"2024","journal-title":"Comput. Vis. Image Understand."},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612206"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995353"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1099"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00365"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3141051"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207174"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/SMC53654.2022.9945500"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00075"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00678"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00338"},{"key":"ref64","article-title":"Balanced supervised contrastive learning for few-shot class-incremental learning","author":"Yoon","year":"2023","journal-title":"arXiv:2305.16687"},{"key":"ref65","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref66","first-page":"6704","article-title":"CyCLIP: Cyclic contrastive language-image pretraining","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"35","author":"Goel"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2024.3524979"},{"key":"ref68","first-page":"28389","article-title":"Not all semantics are created equal: Contrastive self-supervised learning with automatic temperature individualization","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Qiu"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i15.29619"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01616"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00732"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02016-8"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref75","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref76","first-page":"8046","article-title":"Relational self-attention: What\u2019s missing in attention for video understanding","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Kim"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_49"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3180585"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00043"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01261"},{"key":"ref82","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11027896\/10833697.pdf?arnumber=10833697","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,10]],"date-time":"2025-06-10T05:09:43Z","timestamp":1749532183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10833697\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6]]},"references-count":82,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3527312","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6]]}}}