{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,30]],"date-time":"2025-12-30T09:01:13Z","timestamp":1767085273103,"version":"3.37.3"},"reference-count":57,"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 Research and Development Program of China","award":["2022YFF0712100"],"award-info":[{"award-number":["2022YFF0712100"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276131"],"award-info":[{"award-number":["62276131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation of Jiangsu Province of China","award":["BK20240081","BG2024042"],"award-info":[{"award-number":["BK20240081","BG2024042"]}]},{"DOI":"10.13039\/501100001809","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["30922010317"],"award-info":[{"award-number":["30922010317"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tip.2024.3518759","type":"journal-article","created":{"date-parts":[[2024,12,23]],"date-time":"2024-12-23T19:42:21Z","timestamp":1734982941000},"page":"6881-6892","source":"Crossref","is-referenced-by-count":1,"title":["Rebalanced Vision-Language Retrieval Considering Structure-Aware Distillation"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5245-3584","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-6191-2669","authenticated-orcid":false,"given":"Wenjuan","family":"Xi","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8762-2424","authenticated-orcid":false,"given":"Luping","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Electrical and Information Engineering, The University of Sydney, Sydney, NSW, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2019.102165"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3236837"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICME57554.2024.10688342"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038354"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref8","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. BMVC","author":"Faghri"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2852503"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20235"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3139234"},{"key":"ref13","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":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref15","first-page":"467","article-title":"Co-training with insufficient views","volume-title":"Proc. ACML","author":"Wang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3277791"},{"key":"ref17","first-page":"1033","article-title":"Auxiliary information regularized machine for multiple modality feature learning","volume-title":"Proc. IJCAI","author":"Yang"},{"key":"ref18","first-page":"9226","article-title":"Modality competition: What makes joint training of multi-modal network fail in deep learning? (Provably)","volume-title":"Proc. ICML","author":"Huang"},{"key":"ref19","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL","author":"Devlin"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"86","key":"ref21","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/454"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.2972830"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045530"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3075242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3451390"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref30","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. NeurIPS","author":"Li"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref32","first-page":"1","article-title":"Trusted multi-view classification","volume-title":"Proc. ICLR","author":"Han"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"ref34","first-page":"25994","article-title":"Multi-grained vision language pre-training: Aligning texts with visual concepts","volume-title":"Proc. ICML","author":"Zeng"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref37","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00409"},{"key":"ref39","first-page":"1673","article-title":"Large-margin contrastive learning with distance polarization regularizer","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref40","first-page":"1","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref41","first-page":"140:1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"J. Mach. Learn. Res."},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/1460096.1460104"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref50","first-page":"6704","article-title":"CyCLIP: Cyclic contrastive language-image pretraining","volume-title":"Proc. NeurIPS","author":"Goel"},{"key":"ref51","article-title":"Improving multi-modal learning with uni-modal teachers","author":"Du","year":"2021","journal-title":"arXiv:2106.11059"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2421443"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140606"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2170081"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-017-9318-6"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref57","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10346232\/10812824.pdf?arnumber=10812824","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T19:54:29Z","timestamp":1735674869000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10812824\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":57,"URL":"https:\/\/doi.org\/10.1109\/tip.2024.3518759","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2024]]}}}