{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:03Z","timestamp":1778048343169,"version":"3.51.4"},"reference-count":47,"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\/wacv61042.2026.00368","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3771-3780","source":"Crossref","is-referenced-by-count":0,"title":["Frequency Is What You Need: Considering Word Frequency When Text Masking Benefits Vision-Language Model Pre-training"],"prefix":"10.1109","author":[{"given":"Mingliang","family":"Liang","sequence":"first","affiliation":[{"name":"Radboud University,Institute for Computing and Information Sciences,Nijmegen,Netherland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martha","family":"Larson","sequence":"additional","affiliation":[{"name":"Radboud University,Institute for Computing and Information Sciences,Nijmegen,Netherland"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"32","article-title":"Objectnet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","author":"Barbu","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref2","volume-title":"Natural language processing with Python: analyzing text with the natural language toolkit","author":"Bird","year":"2009"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref4","article-title":"Generative pre-training from pixels","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref5","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.461"},{"key":"ref7","article-title":"An analysis of single-layer networks in unsupervised feature learning","volume-title":"International Conference on Artificial Intelligence and Statistics","author":"Coates"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"ref9","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref10","article-title":"DeViSE: A Deep Visual-Semantic Embedding Model","author":"Frome","year":"2013","journal-title":"Neural Information Processing Systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref15","author":"Ilharco","year":"2021","journal-title":"Open-CLIP"},{"key":"ref16","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.4159\/harvard.9780674434929"},{"key":"ref18","article-title":"BLIP: Bootstrapping Language-Image Pre-training for Unified Vision-Language Understanding and Generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref19","article-title":"RECLIP: Resource-efficient CLIP by training with small images","author":"Li","year":"2023","journal-title":"Transactions on Machine Learning Research"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2132"},{"key":"ref21","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/3607827.3616843"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref26","article-title":"SGDR: stochastic gradient descent with warm restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref27","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_12"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248092"},{"key":"ref32","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref33","first-page":"5389","article-title":"Do ImageNet Classifiers Generalize to ImageNet?","volume-title":"International Conference on Machine Learning","author":"Recht"},{"key":"ref34","author":"Schuhmann","year":"2021","journal-title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs"},{"key":"ref35","article-title":"LAION-5B: An open large-scale dataset for training next generation image-text models","volume-title":"Conference on Neural Information Processing Systems, Datasets and Benchmarks Track","author":"Schuhmann"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref37","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref39","author":"van den Oord","year":"2019","journal-title":"Representation Learning with Contrastive Predictive Coding"},{"key":"ref40","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Neural Information Processing Systems"},{"key":"ref41","article-title":"Learning robust global representations by penalizing local predictive power","author":"Wang","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539970"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref47","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Machine Learning for Healthcare Conference","author":"Zhang"}],"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\/11492619.pdf?arnumber=11492619","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:58:39Z","timestamp":1778047119000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492619\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00368","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}