{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:18:00Z","timestamp":1782836280521,"version":"3.54.5"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100000266","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206137"],"award-info":[{"award-number":["62206137"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206200"],"award-info":[{"award-number":["62206200"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276257"],"award-info":[{"award-number":["62276257"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62036012"],"award-info":[{"award-number":["62036012"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000266","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62066033"],"award-info":[{"award-number":["62066033"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004763","name":"National Natural Science Foundation of Inner Mongolia","doi-asserted-by":"publisher","award":["2022MS06025"],"award-info":[{"award-number":["2022MS06025"]}],"id":[{"id":"10.13039\/501100004763","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013147","name":"Program for Young Talents of Science and Technology in Universities of Inner Mongolia Autonomous Region","doi-asserted-by":"publisher","award":["NJYT23105"],"award-info":[{"award-number":["NJYT23105"]}],"id":[{"id":"10.13039\/501100013147","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Applied Technology Research and Development Program of Inner Mongolia Autonomous Region","award":["2020GG0046"],"award-info":[{"award-number":["2020GG0046"]}]},{"name":"Applied Technology Research and Development Program of Inner Mongolia Autonomous Region","award":["2021GG0158"],"award-info":[{"award-number":["2021GG0158"]}]},{"name":"Applied Technology Research and Development Program of Inner Mongolia Autonomous Region","award":["2020PT0002"],"award-info":[{"award-number":["2020PT0002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1109\/tcsvt.2023.3248873","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T18:47:25Z","timestamp":1677264445000},"page":"5257-5270","source":"Crossref","is-referenced-by-count":13,"title":["Debiased Video-Text Retrieval via Soft Positive Sample Calibration"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3183-9218","authenticated-orcid":false,"given":"Huaiwen","family":"Zhang","sequence":"first","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2690-7180","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fan","family":"Qi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Tianjin University of Technology, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9488-2208","authenticated-orcid":false,"given":"Shengsheng","family":"Qian","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8343-9665","authenticated-orcid":false,"given":"Changsheng","family":"Xu","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref4","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. ICLR","author":"Patrick"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref7","first-page":"1","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","volume":"abs\/2106.11097","author":"Fang","year":"2021","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref10","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. ACL","author":"Chen"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref14","first-page":"279","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. BMVC","author":"Liu"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref18","first-page":"5574","article-title":"What uncertainties do we need in Bayesian deep learning for computer vision?","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","volume":"30","author":"Kendall"},{"key":"ref19","first-page":"1","article-title":"Modeling uncertainty with hedged instance embeddings","volume-title":"Proc. ICLR","author":"Oh"},{"key":"ref20","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","volume":"139","author":"Radford"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00496"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3176866"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00365"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462927"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413911"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892802"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3109084"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3073267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2914765"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2022.3220297"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01395-y"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00896"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3076466"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3174577"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3042219"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3183836"},{"key":"ref41","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. 9th Int. Conf. Learn. Represent. (ICLR)","author":"Dosovitskiy"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref43","first-page":"1","article-title":"Layer normalization","volume":"abs\/1607.06450","author":"Ba","year":"2016","journal-title":"CoRR"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1090\/gsm\/058"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref48","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021","journal-title":"arXiv:2109.04290"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref52","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref58","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Loshchilov"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10241245\/10052692.pdf?arnumber=10052692","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,2]],"date-time":"2024-03-02T22:03:56Z","timestamp":1709417036000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10052692\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9]]},"references-count":59,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2023.3248873","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,9]]}}}