{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T19:10:21Z","timestamp":1775329821650,"version":"3.50.1"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"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":["61971106"],"award-info":[{"award-number":["61971106"]}],"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":["62473079"],"award-info":[{"award-number":["62473079"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100018525","name":"Key Research and Development Program of Sichuan Province","doi-asserted-by":"publisher","award":["2021YFS0016"],"award-info":[{"award-number":["2021YFS0016"]}],"id":[{"id":"10.13039\/501100018525","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Medical and Engineering Cross-Disciplinary Joint Fund","award":["ZYGX2021YGLH003"],"award-info":[{"award-number":["ZYGX2021YGLH003"]}]},{"DOI":"10.13039\/100007565","name":"Chengdu Key Research and Development Support Plan","doi-asserted-by":"publisher","award":["2021-YF05-02388-SN"],"award-info":[{"award-number":["2021-YF05-02388-SN"]}],"id":[{"id":"10.13039\/100007565","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":[[2025,3]]},"DOI":"10.1109\/tcsvt.2024.3491176","type":"journal-article","created":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T18:40:24Z","timestamp":1730745624000},"page":"2118-2132","source":"Crossref","is-referenced-by-count":10,"title":["Enhancing Skeleton-Based Action Recognition With Language Descriptions From Pre-Trained Large Multimodal Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-1404-7183","authenticated-orcid":false,"given":"Tian","family":"He","sequence":"first","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-5752-1639","authenticated-orcid":false,"given":"Yang","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Xu","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7007-4740","authenticated-orcid":false,"given":"Ling","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Information and Communication Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]},{"given":"Ting","family":"Hu","sequence":"additional","affiliation":[{"name":"No.1 Orthopedics Hospital of Chengdu, Chengdu, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5532-9530","authenticated-orcid":false,"given":"Hong","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Automation Engineering, University of Electronic Science and Technology of China, Chengdu, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.12.007"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107160"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092403"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICAIIC51459.2021.9415228"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123277"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/109"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00119"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00371"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201186"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3217763"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358836"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413941"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00132"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00544"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3444685.3446289"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"ref20","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref21","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"arXiv:2301.12597","author":"Li","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16430"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177813"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8850-1_15"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.368"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.02.030"},{"key":"ref29","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":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298714"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.391"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.387"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_45"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01955"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/109"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3051495"},{"key":"ref38","first-page":"1","article-title":"Human activity recognition with pose-driven attention to rgb","volume-title":"Proc. BMVC 29th Brit. Mach. Vis. Conf.","author":"Baradel"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00127"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01857"},{"key":"ref43","article-title":"Combined scaling for zero-shot transfer learning","volume-title":"arXiv:2111.10050","author":"Pham","year":"2021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01069"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01629"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00100"},{"key":"ref47","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref48","article-title":"GIT: A generative Image-to-text transformer for vision and language","volume-title":"arXiv:2205.14100","author":"Wang","year":"2022"},{"key":"ref49","article-title":"Grounding DINO: Marrying DINO with grounded pre-training for open-set object detection","volume-title":"arXiv:2303.05499","author":"Liu","year":"2023"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.115"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2916873"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3169976"},{"key":"ref57","article-title":"Why can\u2019t I dance in the mall? Learning to mitigate scene bias in action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Choi"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3085959"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58586-0_32"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413802"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108146"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109854"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.111074"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3240472"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00941"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/187"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681015"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2017.8026283"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2818328"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00096"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2940281"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA60407.2023.00062"},{"key":"ref77","article-title":"UNIK: A unified framework for real-world skeleton-based action recognition","volume-title":"arXiv:2107.08580","author":"Yang","year":"2021"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3230249"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2771306"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.77"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2967577"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2812099"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3127885"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.123061"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00015"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01736"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10916540\/10742343.pdf?arnumber=10742343","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,7]],"date-time":"2025-03-07T18:49:10Z","timestamp":1741373350000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10742343\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":86,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3491176","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}