{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T19:52:53Z","timestamp":1757620373713,"version":"3.44.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031995644"},{"type":"electronic","value":"9783031995651"}],"license":[{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,30]],"date-time":"2025-07-30T00:00:00Z","timestamp":1753833600000},"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\/978-3-031-99565-1_35","type":"book-chapter","created":{"date-parts":[[2025,7,29]],"date-time":"2025-07-29T06:42:45Z","timestamp":1753771365000},"page":"453-465","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Mitigating Distribution Bias in\u00a0Multimodal Datasets via\u00a0Clustering-Based Curation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6853-1375","authenticated-orcid":false,"given":"Mustapha","family":"El Aichouni","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1408-9803","authenticated-orcid":false,"given":"Lluis","family":"Gomez","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1962-3916","authenticated-orcid":false,"given":"Lei","family":"Kang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,7,30]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Bossard, L., Guillaumin, M., Van\u00a0Gool, L.: Food-101\u2013mining discriminative components with random forests. In: Computer vision\u2013ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6\u201312, 2014, proceedings, part VI 13, pp. 446\u2013461. Springer (2014)","DOI":"10.1007\/978-3-319-10599-4_29"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Dong, X., et\u00a0al.: Maskclip: Masked self-distillation advances contrastive language-image pretraining. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10995\u201311005 (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"35_CR3","unstructured":"Fang, A., Jose, A.M., Jain, A., Schmidt, L., Toshev, A., Shankar, V.: Data filtering networks. arXiv preprint arXiv:2309.17425 (2023)"},{"key":"35_CR4","unstructured":"Gadre, S.Y., et al.: Datacomp: in search of the next generation of multimodal datasets. In: Advances in Neural Information Processing Systems, vol. 36, pp. 27092\u201327112 (2023)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Jose, C., et\u00a0al.: Dinov2 meets text: a unified framework for image-and pixel-level vision-language alignment. arXiv preprint arXiv:2412.16334 (2024)","DOI":"10.1109\/CVPR52734.2025.02319"},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Kim, W., Chun, S., Kim, T., Han, D., Yun, S.: Hype: hyperbolic entailment filtering for underspecified images and texts. In: European Conference on Computer Vision, pp. 247\u2013265. Springer (2024)","DOI":"10.1007\/978-3-031-73661-2_14"},{"key":"35_CR7","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images (2009)"},{"issue":"11","key":"35_CR8","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"35_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"35_CR10","unstructured":"Netzer, Y., Wang, T., Coates, A., Bissacco, A., Wu, B., Ng, A.Y., et\u00a0al.: Reading digits in natural images with unsupervised feature learning. In: NIPS Workshop on Deep Learning and Unsupervised Feature Learning, vol.\u00a02011, p.\u00a04. Granada (2011)"},{"key":"35_CR11","unstructured":"Oquab, M., et\u00a0al.: Dinov2: learning robust visual features without supervision. arXiv preprint arXiv:2304.07193 (2023)"},{"key":"35_CR12","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"35_CR13","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"35_CR15","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, vol. 35, pp. 25278\u201325294 (2022)"},{"key":"35_CR16","unstructured":"Schuhmann, C., et al.: Laion-400m: open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)"},{"key":"35_CR17","unstructured":"Tschannen, M., et\u00a0al.: Siglip 2: multilingual vision-language encoders with improved semantic understanding, localization, and dense features. arXiv preprint arXiv:2502.14786 (2025)"},{"key":"35_CR18","unstructured":"Vo, H.V., et\u00a0al.: Automatic data curation for self-supervised learning: a clustering-based approach. arXiv preprint arXiv:2405.15613 (2024)"},{"key":"35_CR19","unstructured":"Xu, H., et al.: Demystifying clip data. arXiv preprint arXiv:2309.16671 (2023)"},{"key":"35_CR20","unstructured":"Yu, H., Tian, Y., Kumar, S., Yang, L., Wang, H.: The devil is in the details: a deep dive into the rabbit hole of data filtering. arXiv preprint arXiv:2309.15954 (2023)"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Zhai, X., Mustafa, B., Kolesnikov, A., Beyer, L.: Sigmoid loss for language image pre-training. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11975\u201311986 (2023)","DOI":"10.1109\/ICCV51070.2023.01100"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Image Analysis"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-99565-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T06:54:35Z","timestamp":1757314475000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-99565-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,30]]},"ISBN":["9783031995644","9783031995651"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-99565-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,7,30]]},"assertion":[{"value":"30 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IbPRIA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Iberian Conference on Pattern Recognition and Image Analysis","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Coimbra","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portugal","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ibpria2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ibpria.org\/2025\/?page=home","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}