{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:54:27Z","timestamp":1783526067878,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","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":"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":["62402023"],"award-info":[{"award-number":["62402023"]}],"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":["62476181"],"award-info":[{"award-number":["62476181"]}],"id":[{"id":"10.13039\/501100001809","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":[[2025,1]]},"DOI":"10.1109\/tcsvt.2024.3462433","type":"journal-article","created":{"date-parts":[[2024,9,17]],"date-time":"2024-09-17T14:55:24Z","timestamp":1726584924000},"page":"300-314","source":"Crossref","is-referenced-by-count":21,"title":["Surveillance Video-and-Language Understanding: From Small to Large Multimodal Models"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8224-9891","authenticated-orcid":false,"given":"Tongtong","family":"Yuan","sequence":"first","affiliation":[{"name":"School of Computer, Beijing University of Technology (BJUT), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8562-6071","authenticated-orcid":false,"given":"Xuange","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer, Beijing University of Technology (BJUT), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3482-6930","authenticated-orcid":false,"given":"Bo","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer, Beijing University of Technology (BJUT), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8398-6369","authenticated-orcid":false,"given":"Kun","family":"Liu","sequence":"additional","affiliation":[{"name":"JD.COM., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Jin","sequence":"additional","affiliation":[{"name":"China Academy of Information and Communications Technology (CAICT), Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-5940-6445","authenticated-orcid":false,"given":"Zhenzhen","family":"Jiao","sequence":"additional","affiliation":[{"name":"Beijing Teleinfo Technology Company., Ltd., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325451"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3148392"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.111"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3335338"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3524137"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105469"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.338"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.45"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00678"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3134410"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3321235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3221622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00207"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298940"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3532626"},{"key":"ref17","article-title":"A review of deep learning for video captioning","author":"Abdar","year":"2023","journal-title":"arXiv:2304.11431"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70825"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01953"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00587"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02082"},{"key":"ref23","article-title":"SAVCHOI: Detecting suspicious activities using dense video captioning with human object interactions","author":"Mittal","year":"2022","journal-title":"arXiv:2207.11838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/877"},{"key":"ref25","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. 49th Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.340"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00497"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2894161"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3556537"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TETCI.2019.2892755"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014491"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2984569"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/app13084956"},{"key":"ref38","article-title":"Temporal sentence grounding in videos: A survey and future directions","author":"Zhang","year":"2022","journal-title":"arXiv:2201.08071"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01257"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28516"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2921655"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01742"},{"key":"ref43","first-page":"200","article-title":"Multimodal few-shot learning with frozen language models","volume-title":"Proc. NeurIPS","volume":"34","author":"Tsimpoukelli"},{"key":"ref44","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","volume":"35","author":"Alayrac"},{"key":"ref45","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. ICML","author":"Li"},{"key":"ref46","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref47","article-title":"VideoChat: Chat-centric video understanding","author":"Li","year":"2023","journal-title":"arXiv:2305.06355"},{"key":"ref48","article-title":"Video-ChatGPT: Towards detailed video understanding via large vision and language models","author":"Maaz","year":"2023","journal-title":"arXiv:2306.05424"},{"key":"ref49","article-title":"Valley: Video assistant with large language model enhanced abilitY","author":"Luo","year":"2023","journal-title":"arXiv:2306.07207"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02095"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2020.3038993"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3120745"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018393"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6984"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01082"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20163"},{"key":"ref58","article-title":"MomentDiff: Generative video moment retrieval from random to real","author":"Li","year":"2023","journal-title":"arXiv:2307.02869"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref63","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Workshop Text Summarization ACL","author":"Lin"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00795"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01426"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref70","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref75","article-title":"A short note about kinetics-600","author":"Carreira","year":"2018","journal-title":"arXiv:1808.01340"},{"key":"ref76","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00677"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_21"},{"key":"ref80","article-title":"GRiT: A generative region-to-text transformer for object understanding","author":"Wu","year":"2022","journal-title":"arXiv:2212.00280"},{"key":"ref81","article-title":"Tag2Text: Guiding vision-language model via image tagging","author":"Huang","year":"2023","journal-title":"arXiv:2303.05657"},{"key":"ref82","article-title":"MOSS: Training conversational language models from synthetic data","author":"Sun","year":"2023","journal-title":"arXiv:2307.15020"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW50321.2020.9096929"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00110"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/10857816\/10681489.pdf?arnumber=10681489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:41:29Z","timestamp":1767638489000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10681489\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":84,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3462433","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}