{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:08:26Z","timestamp":1785604106193,"version":"3.56.0"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,3,1]],"date-time":"2025-03-01T00:00:00Z","timestamp":1740787200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0118201"],"award-info":[{"award-number":["2022ZD0118201"]}]},{"name":"Shenzhen Medical Research Funds in China","award":["B2302037"],"award-info":[{"award-number":["B2302037"]}]},{"name":"Science Foundation of China","award":["62202014"],"award-info":[{"award-number":["62202014"]}]},{"name":"Science Foundation of China","award":["62332002"],"award-info":[{"award-number":["62332002"]}]},{"name":"Science Foundation of China","award":["62425101"],"award-info":[{"award-number":["62425101"]}]},{"name":"Science Foundation of China","award":["61972217"],"award-info":[{"award-number":["61972217"]}]},{"name":"Science Foundation of China","award":["32071459"],"award-info":[{"award-number":["32071459"]}]},{"name":"Science Foundation of China","award":["62176249"],"award-info":[{"award-number":["62176249"]}]},{"name":"Science Foundation of China","award":["62006133"],"award-info":[{"award-number":["62006133"]}]},{"name":"Science Foundation of China","award":["62271465"],"award-info":[{"award-number":["62271465"]}]},{"name":"AI for Science (AI4S)-Preferred Program"},{"name":"Peking University Shenzhen Graduate School, China"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,3]]},"DOI":"10.1109\/tpami.2024.3522124","type":"journal-article","created":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T19:16:13Z","timestamp":1735067773000},"page":"2125-2139","source":"Crossref","is-referenced-by-count":2,"title":["Hierarchical Banzhaf Interaction for General Video-Language Representation Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9287-6410","authenticated-orcid":false,"given":"Peng","family":"Jin","sequence":"first","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3200-0270","authenticated-orcid":false,"given":"Hao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-5588","authenticated-orcid":false,"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8906-3777","authenticated-orcid":false,"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Skywork AI, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9765-4523","authenticated-orcid":false,"given":"Jie","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2916887"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27896"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref4","first-page":"30291","article-title":"Expectation-maximization contrastive learning for compact video-and-language representations","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Jin"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_15"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s001820050125"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2010.11.027"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019127"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3276570"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00293"},{"key":"ref21","first-page":"7290","article-title":"Fine-grained semantically aligned vision-language pre-training","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00975"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_5"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.195"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00782"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3539225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1142\/10634"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevC.16.80"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.2972956"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02072"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.42"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"ref43","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref44","volume-title":"Information Theory and Statistics","author":"Kullback","year":"1997"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2016.02.001"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00692"},{"key":"ref47","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref52","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Patrick"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref59","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref60","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref64","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref65","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref67","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1016\/S0304-3975(00)00251-6"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/s10458-009-9078-9"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref71","first-page":"124","article-title":"Zero-shot video question answering via frozen bidirectional language models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278492"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00294"},{"key":"ref74","article-title":"Learning to answer visual questions from web videos","author":"Yang","year":"2022","journal-title":"arXiv:2205.05019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317447"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01814"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/116"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01743"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412898"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109906"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359045"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00308"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"issue":"11","key":"ref88","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10873290\/10815073.pdf?arnumber=10815073","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,20]],"date-time":"2025-02-20T20:17:56Z","timestamp":1740082676000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10815073\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,3]]},"references-count":88,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3522124","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,3]]}}}