{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T17:52:38Z","timestamp":1776361958472,"version":"3.51.2"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2023YFC2508704"],"award-info":[{"award-number":["2023YFC2508704"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62022083"],"award-info":[{"award-number":["62022083"]}],"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":["62236008"],"award-info":[{"award-number":["62236008"]}],"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":["U21B2038"],"award-info":[{"award-number":["U21B2038"]}],"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":["61931008"],"award-info":[{"award-number":["61931008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for Central Universities","doi-asserted-by":"publisher","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":[[2024,10]]},"DOI":"10.1109\/tcsvt.2024.3393843","type":"journal-article","created":{"date-parts":[[2024,4,25]],"date-time":"2024-04-25T17:59:38Z","timestamp":1714067978000},"page":"9692-9705","source":"Crossref","is-referenced-by-count":5,"title":["Linguistic Hallucination for Text-Based Video Retrieval"],"prefix":"10.1109","volume":"34","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8904-4082","authenticated-orcid":false,"given":"Sheng","family":"Fang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6653-6893","authenticated-orcid":false,"given":"Tiantian","family":"Dang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5931-0527","authenticated-orcid":false,"given":"Shuhui","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7542-296X","authenticated-orcid":false,"given":"Qingming","family":"Huang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1","article-title":"NII-HITACHI-UIT at TRECVID 2016","volume-title":"Proc. TRECVID","volume":"25","author":"Le"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079041"},{"key":"ref3","first-page":"1","article-title":"Waseda_meisei at TRECVID 2017: Ad-hoc video search","volume-title":"Proc. TRECVID","author":"Ueki"},{"key":"ref4","first-page":"1","article-title":"Vireo@trecvid 2017: Video-to-text, ad-hoc video search, and video hyperlinking","volume-title":"Proc. TRECVID","author":"Nguyen"},{"key":"ref5","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref9","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval","author":"Luo","year":"2021","journal-title":"arXiv:2104.08860"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00234"},{"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":"10.1109\/ICCV.2019.00468"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547976"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_14"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_15"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_27"},{"issue":"12","key":"ref19","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3571730","article-title":"Survey of hallucination in natural language generation","volume":"55","author":"Ji","year":"2023","journal-title":"ACM Comput. Surv."},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46604-0_46"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350906"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref24","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018","journal-title":"arXiv:1804.02516"},{"key":"ref25","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00054"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref35","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":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref37","first-page":"1","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. 9th Int. Conf. Learn. Represent.","author":"Patrick"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207910"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref40","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3257193"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3235523"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01038"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2009.06.042"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.96"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_11"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00515"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01611-x"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553380"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.168"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299188"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.237"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_26"},{"key":"ref60","first-page":"18408","article-title":"FlexMatch: Boosting semi-supervised learning with curriculum pseudo labeling","volume-title":"Proc. NIPS","author":"Zhang"},{"key":"ref61","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv:1710.10196"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.383"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013470"},{"key":"ref64","first-page":"21653","article-title":"Curriculum by smoothing","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Sinha"},{"key":"ref65","first-page":"4308","article-title":"Superloss: A generic loss for robust curriculum learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Castells"},{"key":"ref66","first-page":"482","article-title":"Reverse curriculum generation for reinforcement learning","volume-title":"Proc. Conf. Robot Learn.","author":"Florensa"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_20"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2017.306"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2934906"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16447"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462874"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.563"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"issue":"11","key":"ref76","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref80","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":"ref81","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref82","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/10739868\/10508586.pdf?arnumber=10508586","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:09:13Z","timestamp":1732666153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10508586\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":82,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2024.3393843","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}