{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T10:05:30Z","timestamp":1789207530147,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032373342","type":"print"},{"value":"9783032373359","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026]]},"DOI":"10.1007\/978-3-032-37335-9_34","type":"book-chapter","created":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:09:50Z","timestamp":1789204190000},"page":"623-640","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Dynamic Cluster Data Sampling for\u00a0Efficient and\u00a0Long-Tail-Aware Vision-Language Pre-training"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7129-6799","authenticated-orcid":false,"given":"Mingliang","family":"Liang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0049-7080","authenticated-orcid":false,"given":"Zhuoran","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2888-4202","authenticated-orcid":false,"given":"Arjen P.","family":"de Vries","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-4721","authenticated-orcid":false,"given":"Martha","family":"Larson","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,13]]},"reference":[{"key":"34_CR1","unstructured":"Abbas, A., Tirumala, K., Simig, D., Ganguli, S., Morcos, A.S.: SemDeDup: data-efficient learning at web-scale through semantic deduplication. arXiv preprint arXiv:2303.09540 (2023)"},{"key":"34_CR2","unstructured":"Abbas, A.K.M., Rusak, E., Tirumala, K., Brendel, W., Chaudhuri, K., Morcos, A.S.: Effective pruning of web-scale datasets based on complexity of concept clusters. In: International Conference on Learning Representations (2024)"},{"key":"34_CR3","doi-asserted-by":"crossref","unstructured":"Changpinyo, S., Sharma, P., Ding, N., Soricut, R.: Conceptual 12M: pushing web-scale image-text pre-training to recognize long-tail visual concepts. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"34_CR4","doi-asserted-by":"crossref","unstructured":"Cherti, M., et al.: Reproducible scaling laws for contrastive language-image learning. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"34_CR5","doi-asserted-by":"crossref","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: ImageNet: a large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"34_CR6","doi-asserted-by":"crossref","unstructured":"Desai, K., Johnson, J.: VirTex: learning visual representations from textual annotations. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.01101"},{"key":"34_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"key":"34_CR8","doi-asserted-by":"crossref","unstructured":"Fan, L., Krishnan, D., Isola, P., Katabi, D., Tian, Y.: Improving CLIP training with language rewrites. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1544"},{"key":"34_CR9","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A.T., Shankar, V.: Data filtering networks. In: International Conference on Learning Representations (2024)"},{"key":"34_CR10","unstructured":"Gadre, S.Y., et al.: DataComp: in search of the next generation of multimodal datasets. In: Advances in Neural Information Processing Systems, Datasets and Benchmarks Track (2023)"},{"key":"34_CR11","doi-asserted-by":"publisher","unstructured":"Ilharco, G., et al.: OpenCLIP (2021). https:\/\/doi.org\/10.5281\/zenodo.5143773","DOI":"10.5281\/zenodo.5143773"},{"key":"34_CR12","unstructured":"Jia, C., et al.: Scaling up visual and vision-language representation learning with noisy text supervision. In: International Conference on Machine Learning (2021)"},{"key":"34_CR13","unstructured":"Kaplan, J., et al.: Scaling laws for neural language models. arXiv preprint arXiv:2001.08361 (2020)"},{"key":"34_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: bootstrapping language-image pre-training for unified vision-language understanding and generation. In: International Conference on Machine Learning (2022)"},{"key":"34_CR15","unstructured":"Li, R., Kim, D., Bhanu, B., Kuo, W.: RECLIP: resource-efficient CLIP by training with small images. Trans. Mach. Learn. Res. (2023). ISSN 2835-8856. https:\/\/openreview.net\/forum?id=Ufc5cWhHko"},{"key":"34_CR16","doi-asserted-by":"crossref","unstructured":"Li, X., Liu, Y., Tu, H., Xie, C.: OpenVision: a fully-open, cost-effective family of advanced vision encoders for multimodal learning. In: IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.00379"},{"key":"34_CR17","unstructured":"Li, X., et al.: What if we recaption billions of web images with LLaMA-3? In: International Conference on Machine Learning (2025)"},{"key":"34_CR18","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, Z., Xie, C.: An inverse scaling law for CLIP training. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-2132"},{"key":"34_CR19","doi-asserted-by":"crossref","unstructured":"Li, Y., Fan, H., Hu, R., Feichtenhofer, C., He, K.: Scaling language-image pre-training via masking. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2023)","DOI":"10.1109\/CVPR52729.2023.02240"},{"key":"34_CR20","doi-asserted-by":"crossref","unstructured":"Liang, M., Larson, M.: Centered masking for language-image pre-training. In: Machine Learning and Knowledge Discovery in Databases. Research Track and Demo Track (2024)","DOI":"10.1007\/978-3-031-70371-3_6"},{"key":"34_CR21","doi-asserted-by":"crossref","unstructured":"Liang, M., Larson, M.: Frequency is what you need: considering word frequency when text masking benefits vision-language model pre-training. In: IEEE\/CVF Winter Conference on Applications of Computer Vision (2026)","DOI":"10.1109\/WACV61042.2026.00368"},{"key":"34_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: European Conference on Computer Vision (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"34_CR23","doi-asserted-by":"crossref","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-1516"},{"key":"34_CR24","unstructured":"Mikolov, T., Sutskever, I., Chen, K., Corrado, G.S., Dean, J.: Distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems (2013)"},{"key":"34_CR25","doi-asserted-by":"crossref","unstructured":"Nguyen, T., Gadre, S.Y., Ilharco, G., Oh, S., Schmidt, L.: Improving multimodal datasets with image captioning. In: Advances in Neural Information Processing Systems (2023)","DOI":"10.52202\/075280-0967"},{"key":"34_CR26","doi-asserted-by":"crossref","unstructured":"Nilsback, M.E., Zisserman, A.: Automated flower classification over a large number of classes. In: Indian Conference on Computer Vision, Graphics and Image Processing (2008)","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"34_CR27","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"34_CR28","unstructured":"OpenAI, Achiam, J., Adler, S., et\u00a0al., S.A.: GPT-4 Technical report. arXiv preprint arXiv:2303.08774 (2024)"},{"key":"34_CR29","unstructured":"Oquab, M., et al.: DINOv2: learning robust visual features without supervision. Trans. Mach. Learn. Res. (2024). ISSN 2835-8856. https:\/\/openreview.net\/forum?id=a68SUt6zFt"},{"key":"34_CR30","doi-asserted-by":"crossref","unstructured":"Parashar, S., et al.: The neglected tails in vision-language models. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2024)","DOI":"10.1109\/CVPR52733.2024.01234"},{"key":"34_CR31","doi-asserted-by":"crossref","unstructured":"Pei, G., et al.: Seeing what matters: empowering CLIP with patch generation-to-selection. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2025)","DOI":"10.1109\/CVPR52734.2025.02315"},{"key":"34_CR32","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"34_CR33","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with CLIP latents. arXiv preprint arXiv:2204.06125 (2022)"},{"key":"34_CR34","doi-asserted-by":"crossref","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Advances in Neural Information Processing Systems, Datasets and Benchmarks Track (2022)","DOI":"10.52202\/068431-1833"},{"key":"34_CR35","unstructured":"Schuhmann, C., Vencu, R., Beaumont, R., Kaczmarczyk, R., Mullis, C., Katta, A., Coombes, T., Jitsev, J., Komatsuzaki, A.: LAION-400M: Open dataset of CLIP-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"34_CR36","doi-asserted-by":"crossref","unstructured":"Shao, Y., Li, L., Fei, Z., Yan, H., Lin, D., Qiu, X.: Balanced data sampling for language model training with clustering. In: Findings of the Association for Computational Linguistics: ACL 2024 (2024)","DOI":"10.18653\/v1\/2024.findings-acl.833"},{"key":"34_CR37","doi-asserted-by":"crossref","unstructured":"Sharma, P., Ding, N., Goodman, S., Soricut, R.: Conceptual Captions: A cleaned, hypernymed, image alt-text dataset for automatic image captioning. In: Annual Meeting of the Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/P18-1238"},{"key":"34_CR38","doi-asserted-by":"publisher","unstructured":"Thomee, B., et al.: YFCC100M: the new data in multimedia research. Commun. ACM 59(2), 64\u201373 (2016). https:\/\/doi.org\/10.1145\/2812802","DOI":"10.1145\/2812802"},{"key":"34_CR39","doi-asserted-by":"crossref","unstructured":"Udandarao, V., et al.: No \u201czero-shot\u201d without exponential data: pretraining concept frequency determines multimodal model performance. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-1973"},{"key":"34_CR40","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"34_CR41","unstructured":"Wah, C., Branson, S., Welinder, P., Perona, P., Belongie, S.: The caltech-UCSD birds-200-2011 dataset, Technical report. California Institute of Technology (2011)"},{"key":"34_CR42","unstructured":"Webster, R., Rabin, J., Simon, L., Jurie, F.: On the de-duplication of LAION-2B. arXiv preprint arXiv:2303.12733 (2023)"},{"key":"34_CR43","doi-asserted-by":"crossref","unstructured":"Wei, Z., et al.: HQ-CLIP: leveraging large vision-language models to create high-quality image-text datasets and CLIP models. In: IEEE\/CVF International Conference on Computer Vision (2025)","DOI":"10.1109\/ICCV51701.2025.02084"},{"key":"34_CR44","doi-asserted-by":"crossref","unstructured":"Wen, X., Zhao, B., Chen, Y., Pang, J., QI, X.: What makes CLIP more robust to long-tailed pre-training data? a controlled study for transferable insights. In: Advances in Neural Information Processing Systems (2024)","DOI":"10.52202\/079017-1153"},{"key":"34_CR45","unstructured":"Xu, H., et al.: Demystifying CLIP data. In: International Conference on Learning Representations (2024)"},{"key":"34_CR46","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: Attentive mask CLIP. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"34_CR47","doi-asserted-by":"publisher","unstructured":"Young, P., Lai, A., Hodosh, M., Hockenmaier, J.: From image descriptions to visual denotations: new similarity metrics for semantic inference over event descriptions. Trans. Assoc. Comput. Linguist. 2, 67\u201378 (2014). https:\/\/doi.org\/10.1162\/tacl_a_00166","DOI":"10.1162\/tacl_a_00166"},{"key":"34_CR48","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: IEEE\/CVF International Conference on Computer Vision (2023)","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"34_CR49","unstructured":"Zhang, Y., Jiang, H., Miura, Y., Manning, C.D., Langlotz, C.P.: Contrastive learning of medical visual representations from paired images and text. In: Machine Learning for Healthcare Conference (2022)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37335-9_34","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,12]],"date-time":"2026-09-12T09:10:03Z","timestamp":1789204203000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37335-9_34"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032373342","9783032373359"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37335-9_34","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"13 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}