{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T10:32:45Z","timestamp":1763202765132,"version":"3.37.3"},"reference-count":62,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea (NRF) Grant funded by the Korea Government","doi-asserted-by":"publisher","award":["2021R1F1A1060117"],"award-info":[{"award-number":["2021R1F1A1060117"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002611","name":"Institute of Information and Communications Technology Planning and Evaluation Grant funded by the Korea Government","doi-asserted-by":"publisher","award":["2021-0-02067"],"award-info":[{"award-number":["2021-0-02067"]}],"id":[{"id":"10.13039\/501100002611","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003569","name":"Ministry of Food and Drug Safety, in 2022","doi-asserted-by":"publisher","award":["22183MFDS431"],"award-info":[{"award-number":["22183MFDS431"]}],"id":[{"id":"10.13039\/501100003569","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100002611","name":"2021 Research Fund of the University of Seoul","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002611","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3286931","type":"journal-article","created":{"date-parts":[[2023,6,16]],"date-time":"2023-06-16T17:30:39Z","timestamp":1686936639000},"page":"60211-60222","source":"Crossref","is-referenced-by-count":1,"title":["Robust Contrastive Learning With Dynamic Mixed Margin"],"prefix":"10.1109","volume":"11","author":[{"given":"Junhyuk","family":"So","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Pohang University of Science and Technology, Nam-gu, Gyeongsangbuk-do, Pohang-si, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2056-8176","authenticated-orcid":false,"given":"Yongtaek","family":"Lim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Dongdaemun-gu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1902-6262","authenticated-orcid":false,"given":"Yewon","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Dongdaemun-gu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changdae","family":"Oh","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Dongdaemun-gu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0082-4280","authenticated-orcid":false,"given":"Kyungwoo","family":"Song","sequence":"additional","affiliation":[{"name":"Department of Artificial Intelligence, University of Seoul, Seoul, Dongdaemun-gu, Republic of Korea"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"22605","article-title":"COOT: Cooperative hierarchical transformer for video-text representation learning","volume-title":"Proc. NeurIPS","volume":"33","author":"Ging"},{"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","article-title":"Perceiver IO: A general architecture for structured inputs & outputs","author":"Jaegle","year":"2021","journal-title":"arXiv:2107.14795"},{"key":"ref4","article-title":"Graph perceiver IO: A general architecture for graph structured data","author":"Bae","year":"2022","journal-title":"arXiv:2209.06418"},{"key":"ref5","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-97982-3_16"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.29322\/IJSRP.9.10.2019.p9420"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref12","article-title":"Rethinking supervised pre-training for better downstream transferring","author":"Feng","year":"2021","journal-title":"arXiv:2110.06014"},{"key":"ref13","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref14","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Kalantidis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00089"},{"key":"ref18","article-title":"CLEAR: Contrastive learning for sentence representation","author":"Wu","year":"2020","journal-title":"arXiv:2012.15466"},{"key":"ref19","article-title":"Contrastive learning for fair representations","author":"Shen","year":"2021","journal-title":"arXiv:2109.10645"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539232"},{"key":"ref21","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv:1807.03748"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_28"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.1710.09412"},{"key":"ref25","first-page":"6438","article-title":"Manifold mixup: Better representations by interpolating hidden states","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Verma"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref28","first-page":"1","article-title":"Improved deep metric learning with multi-class n-Pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Sohn"},{"key":"ref29","first-page":"2012","article-title":"Analyzing and improving representations with the soft nearest neighbor loss","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Frosst"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref32","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"Kiros","year":"2014","journal-title":"arXiv:1411.2539"},{"key":"ref33","article-title":"Order-embeddings of images and language","author":"Vendrov","year":"2015","journal-title":"arXiv:1511.06361"},{"key":"ref34","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2797921"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref37","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref38","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"34","author":"Li"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref40","article-title":"HiVLP: Hierarchical vision-language pre-training for fast image-text retrieval","author":"Chen","year":"2022","journal-title":"arXiv:2205.12105"},{"key":"ref41","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"Venugopalan","year":"2014","journal-title":"arXiv:1412.4729"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_23"},{"key":"ref44","article-title":"CLIP4Clip: An empirical study of CLIP for end to end video clip retrieval","author":"Luo","year":"2021","journal-title":"arXiv:2104.08860"},{"key":"ref45","article-title":"CLIP2 Video: Mastering video-text retrieval via image CLIP","author":"Fang","year":"2021","journal-title":"arXiv:2106.11097"},{"key":"ref46","article-title":"Geometric multimodal contrastive representation learning","author":"Poklukar","year":"2022","journal-title":"arXiv:2202.03390"},{"key":"ref47","article-title":"BPR: Bayesian personalized ranking from implicit feedback","author":"Rendle","year":"2012","journal-title":"arXiv:1205.2618"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3038912.3052639"},{"key":"ref49","article-title":"Next item recommendation with self-attention","author":"Zhang","year":"2018","journal-title":"arXiv:1808.06414"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219890"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512106"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330873"},{"key":"ref53","article-title":"Deep ranking with adaptive margin triplet loss","author":"Ha","year":"2021","journal-title":"arXiv:2107.06187"},{"key":"ref54","article-title":"Geodesic multi-modal mixup for robust fine-tuning","author":"So","year":"2022","journal-title":"arXiv:2203.03897"},{"key":"ref55","article-title":"Mind the gap: Domain gap control for single shot domain adaptation for generative adversarial networks","author":"Zhu","year":"2021","journal-title":"arXiv:2110.08398"},{"key":"ref56","first-page":"11834","article-title":"Intriguing properties of contrastive losses","volume":"34","author":"Chen","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00751"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10154052.pdf?arnumber=10154052","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T10:41:59Z","timestamp":1709289719000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10154052\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3286931","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2023]]}}}