{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:40:59Z","timestamp":1777128059930,"version":"3.51.4"},"reference-count":86,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Shenzhen Science and Technology Program","award":["JSGG20220831093004008"],"award-info":[{"award-number":["JSGG20220831093004008"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20220818102012025"],"award-info":[{"award-number":["JCYJ20220818102012025"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3227416","type":"journal-article","created":{"date-parts":[[2022,12,7]],"date-time":"2022-12-07T20:38:55Z","timestamp":1670445535000},"page":"7772-7785","source":"Crossref","is-referenced-by-count":31,"title":["Transferring Image-CLIP to Video-Text Retrieval via Temporal Relations"],"prefix":"10.1109","volume":"25","author":[{"given":"Han","family":"Fang","sequence":"first","affiliation":[{"name":"China Telecom Corporation Ltd. Digital Intelligence Technology Company, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pengfei","family":"Xiong","sequence":"additional","affiliation":[{"name":"Tencent Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2478-1978","authenticated-orcid":false,"given":"Luhui","family":"Xu","sequence":"additional","affiliation":[{"name":"Tencent Technology, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5697-4168","authenticated-orcid":false,"given":"Wenhan","family":"Luo","sequence":"additional","affiliation":[{"name":"Shenzhen Campus of Sun Yat-sen University, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref4","first-page":"1","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu","year":"2019"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3206025.3206064"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01170"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref11","first-page":"813","article-title":"IS space-time attention all you need for video understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bertasius","year":"2021"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref18","first-page":"1","article-title":"S3D: Single shot multi-span detector via fully 3D convolutional networks","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Zhang","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00879"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00498"},{"key":"ref24","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":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-77004-4_1"},{"key":"ref26","first-page":"1","article-title":"CLIP4CLip: An empirical study of clip for end to end video clip retrieval","author":"Luo","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0987-1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00359"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3024822"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3002177"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2558463"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3141603"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957948"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3132163"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2985540"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2722687"},{"key":"ref40","first-page":"2021","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref41","first-page":"1","article-title":"An image is worth 16x16 words what is a video worth?","author":"Sharir","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01232"},{"key":"ref44","first-page":"1","article-title":"Learning video representations from textual web supervision","author":"Stroud","year":"2020"},{"key":"ref45","first-page":"1","article-title":"Learning spatiotemporal features via video and text pair discrimination","author":"Li","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1183"},{"key":"ref47","first-page":"1","article-title":"Look closer to ground better: Weakly-supervised temporal grounding of sentence in video","author":"Chen","year":"2020"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3120545"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3063631"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2957854"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3023339"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2969792"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3019710"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2930041"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3091882"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00756"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475703"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011288"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3149716"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042067"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00513"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref67","first-page":"1","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref68","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vaswani","year":"2017"},{"key":"ref69","first-page":"1","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00099"},{"issue":"8","key":"ref71","first-page":"1","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00504"},{"key":"ref75","first-page":"1","article-title":"UniVL: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref77","first-page":"1","article-title":"Learning a text-video embedding from incomplete and heterogeneous data","author":"Miech","year":"2018"},{"key":"ref78","first-page":"2021","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Patrick"},{"key":"ref79","first-page":"1","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref82","article-title":"Pytorch image models","author":"Wightman","year":"2019"},{"key":"ref83","first-page":"1","article-title":"Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter","volume-title":"Proc. Neural Inf. Process. Syst. Workshop Energy Efficient Mach. Learn. Cogn. Comput.","author":"Sanh","year":"2019"},{"key":"ref84","first-page":"1","article-title":"CLIP2TV: An empirical study on transformer-based methods for video-text retrieval","author":"Gao","year":"2021"},{"key":"ref85","first-page":"1","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09973385.pdf?arnumber=9973385","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T23:44:10Z","timestamp":1703029450000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9973385\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3227416","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}