{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T16:15:06Z","timestamp":1775578506169,"version":"3.50.1"},"reference-count":72,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":["62441232"],"award-info":[{"award-number":["62441232"]}],"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":["62306092"],"award-info":[{"award-number":["62306092"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"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":["62476068"],"award-info":[{"award-number":["62476068"]}],"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":["62236008"],"award-info":[{"award-number":["62236008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Natural Science Foundation of Shandong Province, China","doi-asserted-by":"publisher","award":["ZR2024QF066"],"award-info":[{"award-number":["ZR2024QF066"]}],"id":[{"id":"10.13039\/501100007129","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":[[2025,11]]},"DOI":"10.1109\/tcsvt.2025.3577027","type":"journal-article","created":{"date-parts":[[2025,6,5]],"date-time":"2025-06-05T13:38:57Z","timestamp":1749130737000},"page":"11158-11171","source":"Crossref","is-referenced-by-count":1,"title":["Uncertainty-Aware Mixture of Experts for Video Action Anticipation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9196-9818","authenticated-orcid":false,"given":"Zhaobo","family":"Qi","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0042-7074","authenticated-orcid":false,"given":"Weigang","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Weihai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2430335"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.364"},{"key":"ref3","article-title":"A survey on deep learning techniques for action anticipation","author":"Zhong","year":"2023","journal-title":"arXiv:2309.17257"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00173"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01799"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00635"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01322"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01353"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3113114"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.616"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01016"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413964"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_30"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-11021-5_24"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00151"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_46"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3393730"},{"key":"ref18","first-page":"720","article-title":"Scaling egocentric vision: The epic-kitchens dataset","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Damen"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_38"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3307655"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.18"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.5244\/C.31.92"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.214"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01325"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01240"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00088"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2016.7487478"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_10"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2923712"},{"key":"ref31","article-title":"Higher order recurrent space-time transformer for video action prediction","author":"Tai","year":"2021","journal-title":"arXiv:2104.08665"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248271"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3425598"},{"key":"ref34","article-title":"Forecasting future action sequences with neural memory networks","author":"Gammulle","year":"2019","journal-title":"arXiv:1909.09278"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_41"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3055233"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00601"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00254"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3040521"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475327"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412660"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156058"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3232021"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01764"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73390-1_26"},{"key":"ref46","article-title":"AntGPT: Can large language models help long-term action anticipation from videos?","author":"Zhao","year":"2023","journal-title":"arXiv:2307.16368"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref49","article-title":"GShard: Scaling giant models with conditional computation and automatic sharding","author":"Lepikhin","year":"2020","journal-title":"arXiv:2006.16668"},{"issue":"120","key":"ref50","first-page":"1","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref51","first-page":"6265","article-title":"BASE layers: Simplifying training of large, sparse models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lewis"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611871"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547769"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3580305.3599278"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3577193.3593704"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3583780.3615068"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059923"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref61","first-page":"34600","article-title":"On the representation collapse of sparse mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chi"},{"key":"ref62","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"issue":"63","key":"ref63","first-page":"1909","article-title":"Manifold learning: The price of normalization","volume":"9","author":"Goldberg","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/582415.582418"},{"key":"ref65","first-page":"1883","article-title":"Learning to rank by optimizing NDCG measure","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"22","author":"Valizadegan"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00131"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00565"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00383"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2751607"},{"key":"ref72","article-title":"Smooth loss functions for deep Top-k classification","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Berrada"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11223720\/11025841.pdf?arnumber=11025841","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:40:59Z","timestamp":1767638459000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11025841\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11]]},"references-count":72,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3577027","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11]]}}}