{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T17:04:44Z","timestamp":1771952684468,"version":"3.50.1"},"reference-count":82,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key R&D Program of China","award":["2022ZD0115502"],"award-info":[{"award-number":["2022ZD0115502"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62122010"],"award-info":[{"award-number":["62122010"]}],"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":["U23B2010"],"award-info":[{"award-number":["U23B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Zhejiang Provincial Natural Science Foundation of China","award":["LDT23F02022F02"],"award-info":[{"award-number":["LDT23F02022F02"]}]},{"DOI":"10.13039\/100022963","name":"Key Research and Development Program of Zhejiang Province","doi-asserted-by":"publisher","award":["2022C01082"],"award-info":[{"award-number":["2022C01082"]}],"id":[{"id":"10.13039\/100022963","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3402613","type":"journal-article","created":{"date-parts":[[2024,5,17]],"date-time":"2024-05-17T17:41:49Z","timestamp":1715967709000},"page":"9962-9972","source":"Crossref","is-referenced-by-count":5,"title":["MAC: Masked Contrastive Pre-Training for Efficient Video-Text Retrieval"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-9365-5993","authenticated-orcid":false,"given":"Fangxun","family":"Shu","sequence":"first","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2448-5670","authenticated-orcid":false,"given":"Biaolong","family":"Chen","sequence":"additional","affiliation":[{"name":"Alibaba Group, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2671-0655","authenticated-orcid":false,"given":"Yue","family":"Liao","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9118-2780","authenticated-orcid":false,"given":"Jinqiao","family":"Wang","sequence":"additional","affiliation":[{"name":"National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9180-2935","authenticated-orcid":false,"given":"Si","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Artificial Intelligence, Beihang University, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00638"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3231108"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3204444"},{"key":"ref5","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_40"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3193057"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3252176"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref16","first-page":"10 078","article-title":"Videomae: Masked autoencoders are data-efficient learners for self-supervised video pre-training","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Tong","year":"2022"},{"key":"ref17","article-title":"Masked autoencoders as spatiotemporal learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Feichtenhofer","year":"2022"},{"key":"ref18","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3227416"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3181516"},{"key":"ref23","article-title":"VLMAE: Vision-language masked autoencoder","author":"He","year":"2022"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591721"},{"key":"ref25","article-title":"Multimodal masked autoencoders learn transferable representations","author":"Geng","year":"2022"},{"key":"ref26","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Kenton","year":"2019"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475515"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3057503"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3156938"},{"key":"ref34","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Simonyan","year":"2015"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2928491"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref39","first-page":"1","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Su","year":"2019"},{"key":"ref40","first-page":"23634","article-title":"Merlot: Multimodal neural script knowledge models","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Zellers","year":"2021"},{"key":"ref41","article-title":"Violet: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3326851"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref49","first-page":"1","article-title":"Image BERT pre-training with online tokenizer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhou","year":"2021"},{"key":"ref50","article-title":"VIMPAC: Video pre-training via masked token prediction and contrastive learning","author":"Tan","year":"2021"},{"key":"ref51","article-title":"Neural discrete representation learning","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Oord","year":"2017"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref53","article-title":"VL-BEiT: Generative vision-language pretraining","author":"Bao","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01838"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_20"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3124365"},{"key":"ref57","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref59","article-title":"DistilBERT, a distilled version of BERT: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref65","first-page":"190","article-title":"Collecting highly parallel data for paraphrase evaluation","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Chen","year":"2011"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref67","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. British Mach. Vis. Conf.","author":"Liu","year":"2019"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref69","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Int. Conf. Learn. Representations","author":"Patrick","year":"2021"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.29"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref72","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref75","first-page":"1","article-title":"ADAM: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref81","article-title":"Improved regularization of convolutional neural networks with cutout","author":"DeVries","year":"2017"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01426"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10533849.pdf?arnumber=10533849","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T17:43:29Z","timestamp":1729187009000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10533849\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3402613","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}