{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,17]],"date-time":"2026-06-17T13:40:51Z","timestamp":1781703651846,"version":"3.54.5"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["U21B2040"],"award-info":[{"award-number":["U21B2040"]}],"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":["62176171"],"award-info":[{"award-number":["62176171"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["CJ202303"],"award-info":[{"award-number":["CJ202303"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,1]]},"DOI":"10.1109\/tpami.2024.3462996","type":"journal-article","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T17:56:25Z","timestamp":1726682185000},"page":"338-350","source":"Crossref","is-referenced-by-count":13,"title":["Noise-Robust Vision-Language Pre-Training With Positive-Negative Learning"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4161-9427","authenticated-orcid":false,"given":"Zhenyu","family":"Huang","sequence":"first","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8544-6375","authenticated-orcid":false,"given":"Mouxing","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Baidu Inc., Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3868-3997","authenticated-orcid":false,"given":"Peng","family":"Hu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5727-2790","authenticated-orcid":false,"given":"Xi","family":"Peng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Sichuan University, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref2","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref3","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref4","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3076556"},{"key":"ref6","article-title":"Visual entailment: A novel task for fine-grained image understanding","author":"Xie","year":"2019"},{"key":"ref7","first-page":"29 406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref9","article-title":"VisualBERT: A simple and performant baseline for vision and language","author":"Li","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01278"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref12","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01522"},{"key":"ref14","first-page":"12 888","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":"ref15","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25172"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2456899"},{"key":"ref18","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Xia"},{"key":"ref19","first-page":"20 331","article-title":"Early-learning regularization prevents memorization of noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref20","first-page":"8536","article-title":"Co-teaching: Robust training of deep neural networks with extremely noisy labels","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref21","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref22","article-title":"Dividemix: Learning with noisy labels as semi-supervised learning","author":"Li","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00932"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374221"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01391"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-01997-w"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02568"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25974"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00119"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155499"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02135"},{"key":"ref33","article-title":"Multi-granularity correspondence learning from long-term noisy videos","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lin"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref35","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref38","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref41","first-page":"233","article-title":"A closer look at memorization in deep networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arpit"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref46","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref47","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.670"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p19-1644"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref54","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ordonez"},{"key":"ref55","article-title":"Benchmarking robustness under distribution shift of multimodal image-text models","volume-title":"Proc. Workshop Distribution Shifts: Connecting Methods Appl.","author":"Qiu"},{"key":"ref56","article-title":"Benchmarking robustness of adaptation methods on pre-trained vision-language models","author":"Chen","year":"2023"},{"key":"ref57","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref58","article-title":"ImageBERT: Cross-modal pre-training with large-scale weak-supervised image-text data","author":"Qi","year":"2020"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref60","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Gan"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00270"},{"key":"ref62","first-page":"18 123","article-title":"Counterfactual contrastive learning for weakly-supervised vision-language grounding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10777928\/10684058.pdf?arnumber=10684058","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,6]],"date-time":"2024-12-06T18:50:52Z","timestamp":1733511052000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10684058\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,1]]},"references-count":62,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3462996","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,1]]}}}