{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,13]],"date-time":"2026-06-13T04:35:03Z","timestamp":1781325303004,"version":"3.54.1"},"reference-count":51,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00430","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"4518-4528","source":"Crossref","is-referenced-by-count":1,"title":["Unlearning the Noisy Correspondence Makes CLIP More Robust"],"prefix":"10.1109","author":[{"given":"Haochen","family":"Han","sequence":"first","affiliation":[{"name":"Peng Cheng Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex Jinpeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peijun","family":"Ye","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fangming","family":"Liu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01594"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SP40001.2021.00019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01344"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00356"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref6","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"Salun: Empowering machine unlearning via gradient-based weight saliency in both image classification and generation","volume-title":"In International Conference on Learning Representations","author":"Fan"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1544"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29092"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i11.29097"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27955"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2606"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0486"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.276"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1089"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00292"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25172"},{"key":"ref20","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume":"34","author":"Huang","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3462996"},{"key":"ref22","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"In International conference on machine learning","author":"Jia"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25974"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00275"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00932"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00629"},{"key":"ref27","article-title":"Zero-shot clip class forgetting via text-image space adaptation","author":"Kravets","year":"2025","journal-title":"Transactions on Machine Learning Research"},{"key":"ref28","first-page":"1973019742","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"In International conference on machine learning","author":"Li"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01665"},{"key":"ref30","article-title":"Multi-granularity correspondence learning from long-term noisy videos","volume-title":"The Twelfth International Conference on Learning Representations","author":"Lin"},{"key":"ref31","article-title":"Large language model unlearning via embeddingcorrupted prompts","volume-title":"In The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Yuhao Liu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01017"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref34","article-title":"Tripletclip: Improving compositional reasoning of clip via synthetic visionlanguage negatives","volume-title":"The Thirty-eighth Annual Conference on Neural Information Processing Systems","author":"Patel"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1078"},{"key":"ref37","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"In International conference on machine learning","author":"Radford"},{"key":"ref38","article-title":"Laion400 m: Open dataset of clip-filtered 400 million image-text pairs","volume-title":"NeurIPS Workshop Datacentric AI, number FZJ-2022\u201300923","author":"Schuhmann","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref40","article-title":"Ot-clip: Understanding and generalizing clip via optimal transport","volume-title":"In Forty-first International Conference on Machine Learning","author":"Shi"},{"key":"ref41","first-page":"894","article-title":"Cliport: What and where pathways for robotic manipulation","volume-title":"In Conference on robot learning","author":"Shridhar"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00173"},{"key":"ref44","article-title":"Eclip: Efficient contrastive language-image pretraining via ensemble confidence learning and masked language modeling","volume-title":"In First Workshop on Pre-training: Perspectives, Pitfalls, and Paths Forward at ICML 2022","author":"Wang","year":"2022"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2688"},{"key":"ref46","article-title":"Data efficient languagesupervised zero-shot recognition with optimal transport distillation","volume-title":"In International Conference on Learning Representations","author":"Wu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01997-w"},{"key":"ref48","article-title":"Filip: Fine-grained interactive language-image pre-training","volume-title":"In International Conference on Learning Representations","author":"Yao"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref50","article-title":"Negative preference optimization: From catastrophic collapse to effective unlearning","author":"Zhang","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"}],"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\/11444160.pdf?arnumber=11444160","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:12:45Z","timestamp":1777612365000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444160\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00430","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}