{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,9]],"date-time":"2026-01-09T21:16:26Z","timestamp":1767993386315,"version":"3.49.0"},"reference-count":53,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62125207"],"award-info":[{"award-number":["62125207"]}],"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":["62102400"],"award-info":[{"award-number":["62102400"]}],"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":["62272436"],"award-info":[{"award-number":["62272436"]}],"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":["U1936203"],"award-info":[{"award-number":["U1936203"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012152","name":"National Postdoctoral Program for Innovative Talents","doi-asserted-by":"publisher","award":["BX20200338"],"award-info":[{"award-number":["BX20200338"]}],"id":[{"id":"10.13039\/501100012152","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3283916","type":"journal-article","created":{"date-parts":[[2023,7,12]],"date-time":"2023-07-12T17:26:33Z","timestamp":1689182793000},"page":"4073-4087","source":"Crossref","is-referenced-by-count":6,"title":["MemBridge: Video-Language Pre-Training With Memory-Augmented Inter-Modality Bridge"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4245-4911","authenticated-orcid":false,"given":"Jiahao","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3944-4704","authenticated-orcid":false,"given":"Xiangyang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mao","family":"Zheng","sequence":"additional","affiliation":[{"name":"Department of Machine Learning Platform, Tencent Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zihan","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0092-5743","authenticated-orcid":false,"given":"Yongqing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-6018-2833","authenticated-orcid":false,"given":"Xiaoqian","family":"Guo","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Yuan","sequence":"additional","affiliation":[{"name":"Department of Machine Learning Platform, Tencent Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zifeng","family":"Chai","sequence":"additional","affiliation":[{"name":"Department of Machine Learning Platform, Tencent Company Ltd., Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1596-4326","authenticated-orcid":false,"given":"Shuqiang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Information Processing, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16301"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00171"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.544"},{"key":"ref7","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref9","article-title":"VIOLET: End-to-end video-language transformers with masked visual-token modeling","author":"Fu","year":"2021","journal-title":"arXiv:2111.12681"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00331"},{"key":"ref12","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy"},{"key":"ref13","first-page":"23634","article-title":"MERLOT: Multimodal neural script knowledge models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Zellers"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00490"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02193"},{"key":"ref16","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.545"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01569"},{"key":"ref20","first-page":"14200","article-title":"Attention bottlenecks for multimodal fusion","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Nagrani"},{"key":"ref21","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Jaegle"},{"key":"ref22","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00495"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01136"},{"key":"ref26","article-title":"CLIP2TV: Align, match and distill for video-text retrieval","author":"Gao","year":"2021","journal-title":"arXiv:2111.05610"},{"key":"ref27","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref28","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref29","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref31","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":"ref32","article-title":"Use what you have: Video retrieval using representations from collaborative experts","author":"Liu","year":"2019","journal-title":"arXiv:1907.13487"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i8.16822"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01138"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref36","article-title":"Support-set bottlenecks for video-text representation learning","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Patrick"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00374"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref39","article-title":"CLIP2Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00971"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00157"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3389\/frobt.2020.475767"},{"key":"ref44","article-title":"Delving deeper into the decoder for video captioning","author":"Chen","year":"2020","journal-title":"arXiv:2001.05614"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00999"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01660"},{"key":"ref47","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref49","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":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24947-6_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.618"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123427"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10181136.pdf?arnumber=10181136","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,13]],"date-time":"2024-04-13T04:13:17Z","timestamp":1712981597000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10181136\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3283916","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}