{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T20:13:35Z","timestamp":1778184815648,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62576179"],"award-info":[{"award-number":["62576179"]}],"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":["62206137"],"award-info":[{"award-number":["62206137"]}],"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":["62576246"],"award-info":[{"award-number":["62576246"]}],"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":["62532004"],"award-info":[{"award-number":["62532004"]}],"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":["62206200"],"award-info":[{"award-number":["62206200"]}],"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":["62506178"],"award-info":[{"award-number":["62506178"]}],"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":["62276257"],"award-info":[{"award-number":["62276257"]}],"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":["62036012"],"award-info":[{"award-number":["62036012"]}],"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":["62462049"],"award-info":[{"award-number":["62462049"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013147","name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","doi-asserted-by":"publisher","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}],"id":[{"id":"10.13039\/501100013147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Natural Science Foundation of Inner Mongolia","award":["2025JQ012"],"award-info":[{"award-number":["2025JQ012"]}]}],"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.2026.3652634","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:04:02Z","timestamp":1768255442000},"page":"5877-5892","source":"Crossref","is-referenced-by-count":0,"title":["Hierarchical Semantics Interaction for Compressed Video Action Recognition"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9509-0496","authenticated-orcid":false,"given":"Jinxin","family":"Guo","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2690-7180","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.332"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.297"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00631"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00136"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00086"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3287201"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3319140"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/148"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1212.0402"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-006-0450-y"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0594-8"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.441"},{"key":"ref17","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Simonyan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.590"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2818151"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00118"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.207"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3201186"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.167"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2818329"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2016.05.094"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.44"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2830102"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3103677"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3100842"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2791180"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00350"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3422360"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413641"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682450"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412213"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","article-title":"IF-TTN: Information fused temporal transformation network for video action recognition","author":"Yang","year":"2019","journal-title":"arXiv:1902.09928"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888127"},{"key":"ref50","article-title":"Towards scalable modeling of compressed videos for efficient action recognition","author":"Biswas","year":"2025","journal-title":"arXiv:2503.13724"},{"key":"ref51","first-page":"79399","article-title":"CAST: Cross-attention in space and time for video action recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lee"},{"key":"ref52","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref53","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref55","article-title":"Uniformer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022","journal-title":"arXiv:2201.04676"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235522"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00828"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01267"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00219"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096655"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref64","article-title":"Convnet architecture search for spatiotemporal feature learning","author":"Tran","year":"2017","journal-title":"arXiv:1708.05038"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11345241.pdf?arnumber=11345241","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,7]],"date-time":"2026-05-07T19:55:27Z","timestamp":1778183727000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11345241\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2026.3652634","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}