{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T21:18:45Z","timestamp":1780607925137,"version":"3.54.1"},"reference-count":73,"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":"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":["62372339"],"award-info":[{"award-number":["62372339"]}],"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":["62371350"],"award-info":[{"award-number":["62371350"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Ministry of Education Industry University Cooperative Education Project","doi-asserted-by":"publisher","award":["220800006041043"],"award-info":[{"award-number":["220800006041043"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Ministry of Education Industry University Cooperative Education Project","doi-asserted-by":"publisher","award":["202102246004"],"award-info":[{"award-number":["202102246004"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Ministry of Education Industry University Cooperative Education Project","doi-asserted-by":"publisher","award":["202002142012"],"award-info":[{"award-number":["202002142012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3542272","type":"journal-article","created":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T18:55:32Z","timestamp":1740164132000},"page":"1412-1426","source":"Crossref","is-referenced-by-count":2,"title":["Who, What, and Where: Composite-Semantics Instance Search for Story Videos"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-6682-7867","authenticated-orcid":false,"given":"Jiahao","family":"Guo","sequence":"first","affiliation":[{"name":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7009-9205","authenticated-orcid":false,"given":"Ankang","family":"Lu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-4258-9581","authenticated-orcid":false,"given":"Zhengqian","family":"Wu","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9796-488X","authenticated-orcid":false,"given":"Zhongyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8287-8655","authenticated-orcid":false,"given":"Chao","family":"Liang","sequence":"additional","affiliation":[{"name":"National Engineering Research Center for Multimedia Software (NERCMS), Hubei Key Laboratory of Multimedia and Network Communication Engineering, and the School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3379337.3415814"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s40692-020-00161-w"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TII.2013.2255616"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3329119"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1101149.1101173"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/PV.2010.5706821"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2016.03.022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.827232"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107567"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3197819"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3143699"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2601493"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2709941"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TSC.2020.2964552"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2540813"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.891352"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/BigData.2018.8622592"},{"key":"ref19","volume-title":"Story: Style, Structure, Substance, and the Principles of Screenwriting","author":"McKee","year":"2010"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3241401"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612838"},{"key":"ref22","volume-title":"TREC Video Retrieval Evaluation","author":"Over","year":"2011"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/MMSP.2015.7340795"},{"key":"ref24","article-title":"TRECVID 2015\u2014An overview of the goals, tasks, data, evaluation mechanisms and metrics","volume-title":"TREC Video Retrieval Evaluation","author":"Over","year":"2015"},{"key":"ref25","article-title":"TRECVID 2016: Evaluating video search, video event detection, localization, and hyperlinking","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2016"},{"key":"ref26","article-title":"TRECVID 2017: Evaluating ad-hoc and instance video search, events detection, video captioning, and hyperlinking","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2017"},{"key":"ref27","article-title":"TRECVID 2018: Benchmarking video activity detection, video captioning and matching, video storytelling linking and video search","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2018"},{"key":"ref28","article-title":"TRECVID 2019: An evaluation campaign to benchmark video activity detection, video captioning and matching, and video search & retrieval","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2019"},{"key":"ref29","article-title":"TRECVID 2020: A comprehensive campaign for evaluating video retrieval tasks across multiple application domains","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2021"},{"key":"ref30","article-title":"Evaluating multiple video understanding and retrieval tasks at TRECVID 2021","volume-title":"TREC Video Retrieval Evaluation","author":"Awad","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3617892"},{"key":"ref32","article-title":"FriendsQA: A new large-scale deep video understanding dataset with fine-grained topic categorization for story videos","volume-title":"Proc. 39th Annu. AAAI Conf. Artif. Intell.","author":"Wu"},{"key":"ref33","article-title":"PKU-ICST at TRECVID 2016: Instance search task","volume-title":"TREC Video Retrieval Evaluation","author":"Peng","year":"2016"},{"key":"ref34","article-title":"WHU-NERCMS at TRECVID 2019: Instance search task","volume-title":"TREC Video Retrieval Evaluation","author":"L Jiang","year":"2019"},{"key":"ref35","article-title":"WHU-NERCMS at TRECVID 2020: Instance search task","volume-title":"TREC Video Retrieval Evaluation","author":"Yang","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3132734.3136609"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01031"},{"key":"ref39","first-page":"1","article-title":"Waseda Meisei SoftBank at TRECVID 2022","volume-title":"Proc. TRECVid Workshop","author":"Ueki"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27077-2_52"},{"key":"ref41","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":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206557"},{"key":"ref43","article-title":"Text proxy: Decomposing retrieval from a 1-to-N relationship into N 1-to-1 relationships for text-video retrieval","author":"Xiao","year":"2024","journal-title":"arXiv:2410.06618"},{"key":"ref44","article-title":"JOANNEUM RESEARCH at TRECVID 2016 instance search task","volume-title":"TREC Video Retrieval Evaluation","author":"H\u00f6ffernig","year":"2016"},{"key":"ref45","article-title":"BUPT-MCPRL at TRECVID 2021","volume-title":"TREC Video Retrieval Evaluation","author":"Song","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-015-5486-4"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3176647"},{"key":"ref48","article-title":"Dublin city university and Partners\u2019 participation in the INS and VTT tracks at TRECVid 2016","volume-title":"TREC Video Retrieval Evaluation","author":"Marsden","year":"2016"},{"key":"ref49","article-title":"IRIM at TRECVID 2017: Instance search","volume-title":"TREC Video Retrieval Evaluation","author":"Mansencal","year":"2017"},{"key":"ref50","article-title":"PKU_ICST at TRECVID 2018: Instance search task","author":"Peng","year":"2018"},{"key":"ref51","article-title":"BUPT-MCPRL at TRECVID 2019: ActEV and INS","volume-title":"TREC Video Retrieval Evaluation","author":"Li","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-59569-6_49"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.4204\/EPTCS.221.8"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_2"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_43"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/springerreference_65277"},{"key":"ref57","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. NeurIPS","author":"Li"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref59","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref60","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":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01231"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050058"},{"key":"ref63","article-title":"RetinaFace: Single-stage dense face localisation in the wild","author":"Deng","year":"2019","journal-title":"arXiv:1905.00641"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.596"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00056"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.122"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107256"},{"key":"ref70","article-title":"WHU-NERCMS at TRECVID2016: Instance search task","volume-title":"TREC Video Retrieval Evaluation","author":"Wang","year":"2016"},{"key":"ref71","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Ming-Wei","year":"2019","journal-title":"arXiv:1810.04805"},{"key":"ref72","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01016"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10899766.pdf?arnumber=10899766","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,5]],"date-time":"2025-03-05T19:02:19Z","timestamp":1741201339000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10899766\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3542272","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}