{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:33:27Z","timestamp":1770834807191,"version":"3.50.1"},"reference-count":58,"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\/501100014219","name":"National Science Fund for Excellent Young Scholars of China","doi-asserted-by":"publisher","award":["62122042"],"award-info":[{"award-number":["62122042"]}],"id":[{"id":"10.13039\/501100014219","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Technology Research and Industrialization Demonstration Projects of Qingdao","award":["23-1-2-qljh-8-gx"],"award-info":[{"award-number":["23-1-2-qljh-8-gx"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3527369","type":"journal-article","created":{"date-parts":[[2025,1,15]],"date-time":"2025-01-15T20:27:19Z","timestamp":1736972839000},"page":"581-593","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing Text-Video Retrieval Performance With Low-Salient but Discriminative Objects"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-2115-6237","authenticated-orcid":false,"given":"Yanwei","family":"Zheng","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Institute of Intelligent Computing, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7920-8524","authenticated-orcid":false,"given":"Bowen","family":"Huang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Intelligent Computing, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5564-137X","authenticated-orcid":false,"given":"Zekai","family":"Chen","sequence":"additional","affiliation":[{"name":"StandardModel Bio, Inc., Philadelphia, PA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6835-5981","authenticated-orcid":false,"given":"Dongxiao","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Institute of Intelligent Computing, Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3239229"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00277"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3381347"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00264"},{"key":"ref8","first-page":"279","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. 30th Brit. Mach. Vis. Conf.","author":"Liu"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref17","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018","journal-title":"arXiv:1804.02516"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref21","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020","journal-title":"arXiv:2002.06353"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00379"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01262"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6964"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref33","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref34","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Harold Li","year":"2019","journal-title":"arXiv:1908.03557"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref36","first-page":"13","article-title":"ViLBERT: Pretraining taskagnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00970"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref40","first-page":"14476","article-title":"Look at what i\u2019m doing: Self-supervised spatial grounding of narrations in instructional videos","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Tan"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.512"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00446"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref46","article-title":"Layer normalization","author":"Lei Ba","year":"2016","journal-title":"arXiv:1607.06450"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","first-page":"91","article-title":"Classification is a strong baseline for deep metric learning","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhai"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref50","first-page":"38655","article-title":"Text-adaptive multiple visual prototype matching for video-text retrieval","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","author":"Lin"},{"key":"ref51","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref54","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TBDATA.2019.2921572"},{"key":"ref56","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Patrick"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/10841928.pdf?arnumber=10841928","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T06:31:05Z","timestamp":1737441065000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10841928\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3527369","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}