{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,9]],"date-time":"2026-06-09T23:36:48Z","timestamp":1781048208339,"version":"3.54.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,30]],"date-time":"2024-06-30T00:00:00Z","timestamp":1719705600000},"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","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006180","name":"Technology Development","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006180","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004106","name":"East China Normal University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004106","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,6,30]]},"DOI":"10.1109\/ijcnn60899.2024.10650723","type":"proceedings-article","created":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:35:05Z","timestamp":1725903305000},"page":"1-8","source":"Crossref","is-referenced-by-count":1,"title":["A Lightweight and Effective Multi-View Knowledge Distillation Framework for Text-Image Retrieval"],"prefix":"10.1109","author":[{"given":"Yuxiang","family":"Song","sequence":"first","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuxuan","family":"Zheng","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shangqing","family":"Zhao","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shu","family":"Liu","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinlin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaoguang","family":"Long","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Changzhi","family":"Sun","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aimin","family":"Zhou","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Man","family":"Lan","sequence":"additional","affiliation":[{"name":"East China Normal University,School of Computer Science and Technology,Shanghai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"key":"ref2","first-page":"12 888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on Machine Learning","author":"Li"},{"key":"ref3","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume":"34","author":"Li","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref4","first-page":"23 318","article-title":"Ofa: Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","volume-title":"International Conference on Machine Learning","author":"Wang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570481"},{"key":"ref6","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref8","first-page":"32 897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume":"35","author":"Bao","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","first-page":"10 183","article-title":"Synthesizer: Rethinking self-attention for transformer models","volume-title":"International conference on machine learning","author":"Tay"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00077"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref12","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref13","article-title":"Loopitr: Combining dual and cross encoder architectures for image-text retrieval","author":"Lei","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref15","first-page":"25 278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00775"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539173"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref19","article-title":"Fitnets: Hints for thin deep nets","author":"Romero","year":"2014"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013779"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00726"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_2"},{"key":"ref24","article-title":"Transferring knowledge to smaller network with class-distance loss","author":"Kim","year":"2017"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-industry.8"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref27","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International conference on machine learning","author":"Jia"},{"key":"ref28","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021"},{"key":"ref29","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01838"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00553"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00473"},{"key":"ref35","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref37","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume":"33","author":"Gan","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"}],"event":{"name":"2024 International Joint Conference on Neural Networks (IJCNN)","location":"Yokohama, Japan","start":{"date-parts":[[2024,6,30]]},"end":{"date-parts":[[2024,7,5]]}},"container-title":["2024 International Joint Conference on Neural Networks (IJCNN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10649807\/10649898\/10650723.pdf?arnumber=10650723","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,10]],"date-time":"2024-09-10T05:59:45Z","timestamp":1725947985000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10650723\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,30]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/ijcnn60899.2024.10650723","relation":{},"subject":[],"published":{"date-parts":[[2024,6,30]]}}}