{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T17:08:25Z","timestamp":1785604105119,"version":"3.56.0"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62202204"],"award-info":[{"award-number":["62202204"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["JUSRP123032"],"award-info":[{"award-number":["JUSRP123032"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664963","type":"journal-article","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T21:07:48Z","timestamp":1771276068000},"page":"5096-5105","source":"Crossref","is-referenced-by-count":2,"title":["Prototype-Based Asymmetric Hierarchical Matching for Text-Video Retrieval"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0716-0918","authenticated-orcid":false,"given":"Donglin","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Rao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0310-5778","authenticated-orcid":false,"given":"Xiao-Jun","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Computer Science, Jiangnan University, Wuxi, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3396272"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3483381"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_26"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_36"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3248873"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3402613"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3387696"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3379096"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3443657"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3099125"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01760"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s13735-024-00335-7"},{"key":"ref15","article-title":"Open-vocabulary object detection via vision and language knowledge distillation","author":"Gu","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref17","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2271746"},{"key":"ref20","article-title":"CLIP2Video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref21","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.46"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/104"},{"key":"ref26","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3446774"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2020.3032017"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-88007-1_43"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3627103"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00244"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s001820050125"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28327"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3416669"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475241"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28475"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_18"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01566"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/97.329844"},{"key":"ref49","first-page":"15509","article-title":"Learning representations by maximizing mutual information across views","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Bachman","year":"2019"},{"key":"ref50","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00379"},{"key":"ref52","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref55","first-page":"1786","article-title":"W2VV++ fully deep learning for ad-hoc video search","volume-title":"Proc. ACM Int. Conf. Multimedia","author":"Li","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref57","article-title":"CLIP-VIP: Adapting pre-trained image-text model to video-language representation alignment","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xue","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3574925"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3227973"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref62","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Chen","year":"2011"},{"key":"ref63","first-page":"6","article-title":"A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","volume":"5","author":"Kinga","year":"2015"},{"key":"ref64","article-title":"Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11397200.pdf?arnumber=11397200","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:37:38Z","timestamp":1782855458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11397200\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664963","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}