{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T15:58:38Z","timestamp":1780329518773,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"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":["62202499"],"award-info":[{"award-number":["62202499"]}],"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":["62463002"],"award-info":[{"award-number":["62463002"]}],"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":["62473033"],"award-info":[{"award-number":["62473033"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Natural Science Foundation","award":["4242028"],"award-info":[{"award-number":["4242028"]}]},{"name":"Beijing Municipal Natural Science Foundation","award":["L231012"],"award-info":[{"award-number":["L231012"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tcsvt.2025.3548845","type":"journal-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T13:48:34Z","timestamp":1741700914000},"page":"1313-1327","source":"Crossref","is-referenced-by-count":6,"title":["Vision-Semantics-Label: A New Two-Step Paradigm for Action Recognition With Large Language Model"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7673-265X","authenticated-orcid":false,"given":"Xiaoyu","family":"Chen","sequence":"first","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2206-5051","authenticated-orcid":false,"given":"Wanru","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0097-6196","authenticated-orcid":false,"given":"Shichao","family":"Kan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Central South University, Changsha, Hunan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linna","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Mechanical Engineering, Guizhou University, Guiyang, Guizhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8408-3816","authenticated-orcid":false,"given":"Yi","family":"Jin","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6255-9422","authenticated-orcid":false,"given":"Yigang","family":"Cen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2965-6196","authenticated-orcid":false,"given":"Yidong","family":"Li","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Advanced Rail Autonomous Operation, the School of Computer Science and Technology, and the Visual Intelligence +X International Cooperation Joint Laboratory of MOE, Beijing Jiaotong University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref2","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022","journal-title":"arXiv:2205.01068"},{"key":"ref3","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref4","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref5","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01263"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref10","article-title":"InternVid: A large-scale video-text dataset for multimodal understanding and generation","author":"Wang","year":"2023","journal-title":"arXiv:2307.06942"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4321-9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref15","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"arXiv:1705.06950"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-demo.49"},{"key":"ref19","article-title":"MIMIC-IT: Multi-modal in-context instruction tuning","author":"Li","year":"2023","journal-title":"arXiv:2306.05425"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref22","article-title":"A simple LLM framework for long-range video question-answering","author":"Zhang","year":"2023","journal-title":"arXiv:2312.17235"},{"key":"ref23","first-page":"1","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"27","author":"Simonyan"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235522"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207518"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3250646"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117268"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3509691"},{"key":"ref32","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":"ref33","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref35","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":"ref36","article-title":"Actionclip: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv preprint arXiv:2109.08472"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3390133"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01755"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ISCER55570.2022.00042"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3542820"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2022.103707"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_5"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2024.3405079"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref45","article-title":"RegionBLIP: A unified multi-modal pre-training framework for holistic and regional comprehension","author":"Zhou","year":"2023","journal-title":"arXiv:2308.02299"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01871"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref49","first-page":"1","article-title":"Judging llm-AS-a-judge with MT-bench and chatbot arena","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zheng"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01300"},{"key":"ref51","article-title":"Video-LLaVA: Learning united visual representation by alignment before projection","author":"Lin","year":"2023","journal-title":"arXiv:2311.10122"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00467"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611903"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01935"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25386"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00640"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272627"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00633"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.124183"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11392768\/10915651.pdf?arnumber=10915651","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,12]],"date-time":"2026-02-12T21:02:33Z","timestamp":1770930153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10915651\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":59,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3548845","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,2]]}}}