{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:32:04Z","timestamp":1777865524891,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2024YFF0507603"],"award-info":[{"award-number":["2024YFF0507603"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00369","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3874-3884","source":"Crossref","is-referenced-by-count":0,"title":["RankCLIP: Ranking-Consistent Language-Image Pretraining"],"prefix":"10.1109","author":[{"given":"Yiming","family":"Zhang","sequence":"first","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhuokai","family":"Zhao","sequence":"additional","affiliation":[{"name":"University of Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhaorun","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Chicago"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhili","family":"Feng","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zenghui","family":"Ding","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yining","family":"Sun","sequence":"additional","affiliation":[{"name":"HFIPS, Chinese Academy of Sciences"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"ref2","article-title":"Poisoning and backdooring contrastive learning","author":"Carlini","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-022-1369-5"},{"key":"ref4","article-title":"Mj-bench: Is your multimodal reward model really a good judge for text-toimage generation?","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref5","article-title":"Halc: Object hallucination reduction via adaptive focal-contrast decoding","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.73"},{"key":"ref7","first-page":"603","article-title":"KR1442 Chowdhary and KR Chowdhary. Natural language processing","year":"2020","journal-title":"Fundamentals of artificial intelligence"},{"key":"ref8","article-title":"Improved probabilistic image-text representations","author":"Chun","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref10","first-page":"215","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"Proceedings of the fourteenth international conference on artificial intelligence and statistics","author":"Coates"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref13","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2606"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref17","article-title":"Hiclip: Contrastive language-image pretraining with hierarchy-aware attention","author":"Geng","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0486"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553423"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref24","article-title":"Openclip","author":"Ilharco","year":"2021","journal-title":"If you use this software, please cite it as below"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3545572"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_27"},{"key":"ref28","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1280"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/773"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1037\/14396-000"},{"key":"ref33","article-title":"Fine-grained visual classification of aircraft","author":"Maji","year":"2013","journal-title":"Technical report"},{"key":"ref34","article-title":"Umap: Uniform manifold approximation and projection for dimension reduction","author":"McInnes","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref35","first-page":"7721","article-title":"Accuracy on the line: on the strong correlation between out-of-distribution and indistribution generalization","volume-title":"International conference on machine learning","author":"Miller"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.2118\/18761-MS"},{"key":"ref38","article-title":"Geodesic multi-modal mixup for robust fine-tuning","volume":"36","author":"Oh","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref39","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.2307\/2346567"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3191696"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref44","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh"},{"key":"ref45","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","volume-title":"International conference on machine learning","author":"Recht"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D13-1170"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00127"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2012.02.016"},{"key":"ref53","article-title":"A fistful of words: Learning transferable visual models from bag-of-words supervision","author":"Tejankar","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/7068349"},{"key":"ref56","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"International conference on machine learning","author":"Wang"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01102"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00273"},{"key":"ref59","article-title":"Filip: Fine-grained interactive language-image pre-training","author":"Yao","year":"2021","journal-title":"arXiv preprint arXiv"},{"key":"ref60","article-title":"Multi-modality guidance network for missing modality inference","author":"Zhao","year":"2023","journal-title":"arXiv preprint arXiv"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444459.pdf?arnumber=11444459","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:46:13Z","timestamp":1777531573000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444459\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00369","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}