{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T14:07:44Z","timestamp":1768313264221,"version":"3.49.0"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62471013"],"award-info":[{"award-number":["62471013"]}],"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":["61971016"],"award-info":[{"award-number":["61971016"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Municipal Education Commission Cooperation Beijing Natural Science Foundation","award":["KZ201910005007"],"award-info":[{"award-number":["KZ201910005007"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2025.3632629","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:01:50Z","timestamp":1768255310000},"page":"772-785","source":"Crossref","is-referenced-by-count":0,"title":["HMS\n                    <sup>2<\/sup>\n                    Net: Heterogeneous Multimodal State Space Network via CLIP for Dynamic Scene Classification in Livestreaming"],"prefix":"10.1109","volume":"28","author":[{"given":"Wensheng","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1290-0738","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9937-2669","authenticated-orcid":false,"given":"Li","family":"Zhuo","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing University of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Huawei Inc., Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3207580"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3303711"},{"key":"ref3","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":"ref4","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Alec"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00523"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3428317"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73347-5_14"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2024.3409707"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.hcc.2024.100211"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2308950121"},{"key":"ref12","article-title":"Clip-ViP: Adapting pre-trained image-text model to video-language representation alignment","author":"Xue","year":"2023","journal-title":"Proc. Int. Conf. Learn. Represent"},{"key":"ref13","first-page":"11","article-title":"PandaGPT: One model to instruction-follow them all","volume-title":"Proc. Workshop Taming Large Lang. Models.","author":"Su"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3294977"},{"key":"ref16","first-page":"79570","article-title":"One-for-all: Bridge the gap between heterogeneous architectures in knowledge distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Hao"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.09.027"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2958871"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-022-01031-4"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19987"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00087"},{"key":"ref22","first-page":"2491","article-title":"Associating objects with Transformers for video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2024.3385849"},{"key":"ref24","article-title":"YOLO by ultralytics (version 8.0.0)","author":"Jocher","year":"2023"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref30","article-title":"Co-training transformer with videos and images improves action recognition","author":"Zhang","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3264976"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00157"},{"key":"ref35","volume-title":"Vision Science: Photons to Phenomenology","author":"Palmer","year":"1999"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11342318.pdf?arnumber=11342318","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,13]],"date-time":"2026-01-13T08:56:32Z","timestamp":1768294592000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11342318\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3632629","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}