{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T20:13:31Z","timestamp":1778530411956,"version":"3.51.4"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB4703200"],"award-info":[{"award-number":["2022YFB4703200"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62261160652"],"award-info":[{"award-number":["62261160652"]}],"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":["52275013"],"award-info":[{"award-number":["52275013"]}],"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":["62206075"],"award-info":[{"award-number":["62206075"]}],"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":["61733011"],"award-info":[{"award-number":["61733011"]}],"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":["62503139"],"award-info":[{"award-number":["62503139"]}],"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":["62573163"],"award-info":[{"award-number":["62573163"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20240813105137049"],"award-info":[{"award-number":["JCYJ20240813105137049"]}]},{"name":"Science and Technology Development Fund (FDCT), Macau, SAR","award":["0095\/2022\/AFJ"],"award-info":[{"award-number":["0095\/2022\/AFJ"]}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2024A1515012028"],"award-info":[{"award-number":["2024A1515012028"]}],"id":[{"id":"10.13039\/501100021171","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":[[2026,5]]},"DOI":"10.1109\/tcsvt.2025.3637737","type":"journal-article","created":{"date-parts":[[2025,11,27]],"date-time":"2025-11-27T18:59:56Z","timestamp":1764269996000},"page":"7236-7249","source":"Crossref","is-referenced-by-count":0,"title":["Topology-Motion Decoupling Framework With Textual Regularization for Skeleton-Based Temporal Action Segmentation"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-0236-6776","authenticated-orcid":false,"given":"Zhihao","family":"Yang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2150-0791","authenticated-orcid":false,"given":"Haoyu","family":"Ji","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-6207","authenticated-orcid":false,"given":"Bowen","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0344-2233","authenticated-orcid":false,"given":"Wenze","family":"Huang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3839-0078","authenticated-orcid":false,"given":"Weihong","family":"Ren","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5546-6666","authenticated-orcid":false,"given":"Zhiyong","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2880-4698","authenticated-orcid":false,"given":"Honghai","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Robotics and Systems, Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-020-01823-z"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.gaitpost.2020.05.026"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8794254"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3624581"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00705"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00369"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.49"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00930"},{"key":"ref9","first-page":"37765","article-title":"Efficient temporal action segmentation via boundary-aware query voting","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","author":"Wang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01721"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref13","article-title":"A decoupled spatio-temporal framework for skeleton-based action segmentation","author":"Li","year":"2023","journal-title":"arXiv:2312.05830"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3334872"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201186"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3285416"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093361"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00237"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00636"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16314"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3132739"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/s20154083"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IROS45743.2020.9341214"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3157033"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021756"},{"key":"ref28","article-title":"TricorNet: A hybrid temporal convolutional and recurrent network for video action segmentation","author":"Ding","year":"2017","journal-title":"arXiv:1705.07818"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/PerComWorkshops56833.2023.10150358"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.216"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2025.3563025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3509434"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TETC.2022.3230912"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.127482"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref36","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3272627"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3402952"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3491176"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3487242"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3617233.3617244"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01926"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3410301"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3417392"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00996"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72949-2_23"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_3"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3265879"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref52","first-page":"4003","article-title":"Cross attention network for few-shot classification","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"32","author":"Hou"},{"key":"ref53","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00943"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.04.121"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2023.103707"},{"key":"ref57","article-title":"Language-assisted human part motion learning for skeleton-based temporal action segmentation","author":"Chen","year":"2024","journal-title":"arXiv:2410.06353"},{"key":"ref58","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"1","author":"Katharopoulos"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3284080"},{"key":"ref60","first-page":"611","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3571770"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d19-1410"},{"key":"ref63","article-title":"Text embeddings by weakly-supervised contrastive pre-training","author":"Wang","year":"2022","journal-title":"arXiv:2212.03533"},{"key":"ref64","article-title":"Towards general text embeddings with multi-stage contrastive learning","author":"Li","year":"2023","journal-title":"arXiv:2308.03281"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657878"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11270846.pdf?arnumber=11270846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:48:48Z","timestamp":1778528928000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11270846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3637737","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}