{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T21:56:15Z","timestamp":1769032575027,"version":"3.49.0"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"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":[[2025,10,22]]},"DOI":"10.1109\/cbmi66578.2025.11339344","type":"proceedings-article","created":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T20:38:56Z","timestamp":1768941536000},"page":"1-7","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Vision-Language Model Pre-Training with Image-Text Pair Pruning Based on Word Frequency"],"prefix":"10.1109","author":[{"given":"Mingliang","family":"Liang","sequence":"first","affiliation":[{"name":"Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands"}]},{"given":"Martha","family":"Larson","sequence":"additional","affiliation":[{"name":"Institute for Computing and Information Sciences, Radboud University,Nijmegen,Netherlands"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01759"},{"key":"ref4","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"International Conference on Machine Learning","author":"Jia"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"2","key":"ref6","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2812802"},{"key":"ref10","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":"ref11","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy"},{"key":"ref12","article-title":"Attention is all you need","author":"Vaswani","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref13","article-title":"Efficient estimation of word representations in vector space","volume-title":"International Conference on Learning Representations","author":"Mikolov"},{"key":"ref14","article-title":"Frequency is what you need: Considering word frequency when text masking benefits vision-language model pre-training","volume-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","author":"Liang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5040\/9798881817916.ch-004"},{"key":"ref16","author":"Schuhmann","year":"2021","journal-title":"LAION-400M: Open Dataset of CLIP-Filtered 400 Million Image-Text Pairs"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref18","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"International Conference on Learning Representations","author":"Li"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01511"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00273"},{"key":"ref21","article-title":"CoCa:Contrastive Captioners are Image-Text Foundation Models","author":"Yu","year":"2022","journal-title":"Transactions on Machine Learning Research"},{"key":"ref22","article-title":"Unifying architectures, tasks, and modalities through a simple sequence-to-sequence learning framework","author":"Wang","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.527"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref26","article-title":"Decoupled weight decay regularization","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref27","article-title":"Generative pretraining from pixels","volume-title":"International Conference on Machine Learning","author":"Chen"},{"key":"ref28","article-title":"SGDR: Stochastic Gradient Descent with Warm Restarts","volume-title":"International Conference on Learning Representations","author":"Loshchilov"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.29007\/1mjd"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref34","article-title":"Learning robust global representations by penalizing local predictive power","volume":"32","author":"Wang","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref35","first-page":"5389","article-title":"Do ImageNet Classifiers Generalize to ImageNet?","volume-title":"International Conference on Machine Learning","author":"Recht"},{"key":"ref36","article-title":"ObjectNet: A large-scale bias-controlled dataset for pushing the limits of object recognition models","volume":"32","author":"Barbu","year":"2019","journal-title":"Neural Information Processing Systems"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1405.0312"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"}],"event":{"name":"2025 International Conference on Content-Based Multimedia Indexing (CBMI)","location":"Dublin, Ireland","start":{"date-parts":[[2025,10,22]]},"end":{"date-parts":[[2025,10,24]]}},"container-title":["2025 International Conference on Content-Based Multimedia Indexing (CBMI)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11339229\/11339242\/11339344.pdf?arnumber=11339344","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,21]],"date-time":"2026-01-21T07:11:37Z","timestamp":1768979497000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11339344\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/cbmi66578.2025.11339344","relation":{},"subject":[],"published":{"date-parts":[[2025,10,22]]}}}