{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:22:49Z","timestamp":1778048569923,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00712","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7376-7386","source":"Crossref","is-referenced-by-count":0,"title":["MM-TS: Multi-Modal Temperature and Margin Schedules for Contrastive Learning with Long-Tail Data"],"prefix":"10.1109","author":[{"given":"Siarhei","family":"Sheludzko","sequence":"first","affiliation":[{"name":"University of Bonn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dhimitrios","family":"Duka","sequence":"additional","affiliation":[{"name":"MPI for Informatics, SIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bernt","family":"Schiele","sequence":"additional","affiliation":[{"name":"MPI for Informatics, SIC"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hilde","family":"Kuehne","sequence":"additional","affiliation":[{"name":"Tuebingen AI Center\/University of Tuebingen"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anna","family":"Kukleva","sequence":"additional","affiliation":[{"name":"MPI for Informatics, SIC"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-3185"},{"key":"ref2","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International conference on machine learning","author":"Chen"},{"key":"ref3","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01766"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00949"},{"key":"ref7","article-title":"Democratizing contrastive language-image pretraining: A clip benchmark of data, model, and supervision","author":"Cui","year":"2022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01531-2"},{"key":"ref9","author":"Dehghani","year":"2023","journal-title":"Scaling vision transformers to 22 billion parameters"},{"key":"ref10","article-title":"C4. 5, class imbalance, and cost sensitivity: why under-sampling beats over-sampling","volume-title":"Workshop on learning from imbalanced datasets II","author":"Drummond"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0486"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.622"},{"key":"ref13","author":"Guo","year":"2024","journal-title":"M2-encoder: Advancing bilingual image-text understanding by large-scale efficient pretraining"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/11538059_91"},{"issue":"7","key":"ref15","article-title":"Momentum contrast for unsupervised visual representation learning. arxiv e-prints, art","volume":"6","author":"He","year":"2019"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref17","first-page":"21798","article-title":"Hard negative mixing for contrastive learning","volume-title":"Advances in Neural Information Processing Systems","author":"Kalantidis","year":"2020"},{"key":"ref18","article-title":"Exploring balanced feature spaces for representation learning","volume-title":"International Conference on Learning Representations","author":"Kang"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TBIOM.2022.3180591"},{"key":"ref21","article-title":"Temperature-free loss function for contrastive learning","author":"Kim","year":"2025"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01925"},{"key":"ref23","article-title":"Temperature schedules for self-supervised contrastive methods on long-tail data","author":"Kukleva","year":"2023"},{"key":"ref24","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0550"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref28","article-title":"Self-supervised learning is more robust to dataset imbalance","author":"Liu","year":"2021"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02484"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref31","first-page":"328","article-title":"Improving zero-shot generalization for clip with variational adapter","volume-title":"European Conference on Computer Vision","author":"Lu"},{"key":"ref32","article-title":"Univl: A unified video and language pre-training model for multimodal understanding and generation","author":"Luo","year":"2020"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.679"},{"key":"ref34","article-title":"Slip: self-supervision meets language-image pre-training. corr abs\/2112.12750 (2021)","author":"Mu","year":"2021"},{"key":"ref35","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-72664-4_3","article-title":"Silc: Improving vision language pretraining with self-distillation","volume-title":"European Conference on Computer Vision","author":"Naeem"},{"key":"ref36","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00077"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00239"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126658"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref41","article-title":"To cool or not to cool? temperature network meets large foundation models via dro","author":"Qiu","year":"2024"},{"key":"ref42","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref44","article-title":"Distilbert, a distilled version of bert: smaller, faster, cheaper and lighter","author":"Sanh","year":"2019"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"},{"key":"ref48","article-title":"Contextual temperature for language modeling","author":"Wang","year":"2020"},{"key":"ref49","article-title":"Vamos: Versatile action models for video understanding","author":"Wang","year":"2024","journal-title":"ECCV"},{"key":"ref50","first-page":"450","article-title":"Fine-grained action retrieval through multiple partsof-speech embeddings","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Wray"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.370"},{"key":"ref52","first-page":"19290","article-title":"Rethinking the value of labels for improving class-imbalanced learning","volume":"33","author":"Yang","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref53","article-title":"Decoupled contrastive learning. arxiv e-prints, art","author":"Yeh","year":"2021"},{"key":"ref54","first-page":"25760","article-title":"Provable stochastic optimization for global contrastive learning: Small batch does not harm performance","volume-title":"International Conference on Machine Learning","author":"Yuan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01404"},{"key":"ref57","article-title":"Temperature as uncertainty in contrastive learning","author":"Zhang","year":"2021"},{"key":"ref58","article-title":"Training a large video model on a single machine in a day","author":"Zhao","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00637"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492308.pdf?arnumber=11492308","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:07:32Z","timestamp":1778047652000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492308\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00712","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}