{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,10]],"date-time":"2026-02-10T18:49:57Z","timestamp":1770749397643,"version":"3.50.0"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U22A2095"],"award-info":[{"award-number":["U22A2095"]}],"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":["6247072922"],"award-info":[{"award-number":["6247072922"]}],"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":["62476296"],"award-info":[{"award-number":["62476296"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Natural Science Funds","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong NSF for Distinguished Young Scholar","award":["2022B1515020009"],"award-info":[{"award-number":["2022B1515020009"]}]},{"name":"Guangdong Provincial Science and Technology Program","award":["2024A1111120017"],"award-info":[{"award-number":["2024A1111120017"]}]},{"name":"Guangdong Provincial Key Laboratory of Information Security Technology","award":["2023B1212060026"],"award-info":[{"award-number":["2023B1212060026"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3543031","type":"journal-article","created":{"date-parts":[[2025,2,17]],"date-time":"2025-02-17T13:36:16Z","timestamp":1739799376000},"page":"5077-5091","source":"Crossref","is-referenced-by-count":2,"title":["Rethinking Temporal Context in Video-QA: A Comprehensive Study of Single-Frame Static Bias"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0558-954X","authenticated-orcid":false,"given":"Tianming","family":"Liang","sequence":"first","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7036-9238","authenticated-orcid":false,"given":"Linhui","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2678-5373","authenticated-orcid":false,"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}]},{"given":"Xiangyang","family":"Yu","sequence":"additional","affiliation":[{"name":"Department of Physics, Sun Yat-Sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3883-2024","authenticated-orcid":false,"given":"Jianhuang","family":"Lai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Sun Yat-sen University, Guangzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3323878"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2746267"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2022.3173208"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3292266"},{"key":"ref6","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang","year":"2022"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref8","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00769"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_32"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.778"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/492"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11238"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.149"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240563"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00965"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_3"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120544"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6767"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6737"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097171"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3345172"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.501"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00688"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2017\/280"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.80"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2935678"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-66415-2_33"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00173"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018658"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_5"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref39","first-page":"26462","article-title":"Learning from inside: Self-driven siamese sampling and reasoning for video question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu","year":"2021"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00980"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00058"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00373"},{"key":"ref43","first-page":"853","article-title":"Why can\u2019t i dance in the mall? Learning to mitigate scene bias in action recognition","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Choi","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475472"},{"key":"ref45","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref46","article-title":"FitNets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref47","first-page":"2765","article-title":"Paraphrasing complex network: Network compression via factor transfer","volume-title":"Proc. 32nd Int. Conf. Neural Inf. Process. Syst.","author":"Kim","year":"2018"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_17"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.372"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00968"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00700"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00656"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547990"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00089"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01165"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"ref58","article-title":"Paying more attention to attention: Improving the performance of convolutional neural networks via attention transfer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zagoruyko","year":"2016"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.754"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098135"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref62","article-title":"The modality focusing hypothesis: Towards understanding crossmodal knowledge distillation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01514-3"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25296"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01426"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref70","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby","year":"2019"},{"key":"ref71","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref72","article-title":"Deberta: Decoding-enhanced bert with disentangled attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"He","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00489"},{"key":"ref74","article-title":"Understanding and improving knowledge distillation","author":"Tang","year":"2020"},{"key":"ref75","first-page":"6906","article-title":"Does knowledge distillation really work?","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Stanton","year":"2021"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01627"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02221"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.01113"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01826"},{"key":"ref80","first-page":"38728","article-title":"mPLUG-2: A modularized multi-modal foundation model across text, image and video","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xu","year":"2023"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01113"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/6046\/10844992\/10891555-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10891555.pdf?arnumber=10891555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,28]],"date-time":"2025-08-28T18:10:31Z","timestamp":1756404631000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10891555\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":81,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3543031","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}