{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T18:33:24Z","timestamp":1770834804909,"version":"3.50.1"},"reference-count":75,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001348","name":"Agency for Science, Technology and Research","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001348","id-type":"DOI","asserted-by":"publisher"}]},{"name":"AME YIRG","award":["A20E6c0101"],"award-info":[{"award-number":["A20E6c0101"]}]},{"DOI":"10.13039\/501100004735","name":"Natural Science Foundation of Hunan Province","doi-asserted-by":"publisher","award":["2024JJ6435"],"award-info":[{"award-number":["2024JJ6435"]}],"id":[{"id":"10.13039\/501100004735","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.2024.3416669","type":"journal-article","created":{"date-parts":[[2024,6,28]],"date-time":"2024-06-28T18:09:07Z","timestamp":1719598147000},"page":"10924-10936","source":"Crossref","is-referenced-by-count":8,"title":["Efficient Cross-Modal Video Retrieval With Meta-Optimized Frames"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0654-6026","authenticated-orcid":false,"given":"Ning","family":"Han","sequence":"first","affiliation":[{"name":"School of Computer Science, Xiangtan University, Xiangtan, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0065-8665","authenticated-orcid":false,"given":"Ee-Peng","family":"Lim","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5902-1824","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Information Science and Engineering, Hunan University, Changsha, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2689-317X","authenticated-orcid":false,"given":"Qianru","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3121567"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3019714"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475272"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3019710"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042067"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3048680"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168424"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref15","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.05095"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref19","article-title":"Distilbert, a distilled version of bert: Smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_5"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3531950"},{"key":"ref23","article-title":"Self-tuning networks: Bilevel optimization of hyperparameters using structured best-response functions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"MacKay","year":"2019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TEVC.2017.2712906"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref28","first-page":"3826","article-title":"Fine-grained cross-modal alignment network 820\nfor video-text retrieval","volume-title":"ACM MM","author":"Han","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3011288"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090595"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"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. Brit. Mach. Vis. Conf., Nottingham","author":"Liu","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3627103"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1312"},{"key":"ref40","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Patrick","year":"2021"},{"key":"ref41","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref42","article-title":"Improving video-text retrieval by multi-stream corpus alignment and dual softmax loss","author":"Cheng","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547910"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref45","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":"ref46","article-title":"Disentangled representation learning for text-video retrieval","author":"Wang","year":"2022"},{"key":"ref47","volume-title":"The Theory of The Market Economy","author":"Heinrich","year":"1952"},{"key":"ref48","article-title":"Generative adversarial nets","volume":"27","author":"Goodfellow","year":"2014","journal-title":"NIPS"},{"key":"ref49","article-title":"Dataset distillation","author":"Wang","year":"2018"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00257"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01174"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475451"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3079209"},{"key":"ref54","first-page":"1","article-title":"How to train your maml","volume-title":"Proc. ICLR","author":"Antoniou","year":"2019"},{"key":"ref55","first-page":"1540","article-title":"Optimizing millions of hyperparameters by implicit differentiation","volume-title":"Int. Conf. Artif. Intell. Statist.","author":"Lorraine","year":"2020"},{"key":"ref56","article-title":"Cmu-ucr-bosch, trecvid 2017: Video to text retrieval","volume-title":"Proc. TRECVID","author":"Mithun","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01600"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2511748"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.331"},{"key":"ref60","article-title":"Avd: Adversarial video distillation","author":"Tavakolian","year":"2019"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548195"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331217"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3044473"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3073867"},{"key":"ref65","article-title":"Classification is a strong baseline for deep metric learning","author":"Zhai","year":"2018"},{"key":"ref66","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","year":"2011"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.572"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_19"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10576688.pdf?arnumber=10576688","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:29:28Z","timestamp":1732667368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10576688\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":75,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3416669","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}