{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T11:12:01Z","timestamp":1778584321724,"version":"3.51.4"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031703706","type":"print"},{"value":"9783031703713","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-3-031-70371-3_6","type":"book-chapter","created":{"date-parts":[[2024,8,31]],"date-time":"2024-08-31T23:31:13Z","timestamp":1725147073000},"page":"90-106","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Centered Masking for\u00a0Language-Image Pre-training"],"prefix":"10.1007","author":[{"given":"Mingliang","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Martha","family":"Larson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,22]]},"reference":[{"key":"6_CR1","unstructured":"Arnheim, R.: Art and Visual Perception: A Psychology of the Creative Eye. University of California Press (1954)"},{"key":"6_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1007\/978-3-031-19821-2_26","volume-title":"Computer Vision - ECCV 2022","author":"M Assran","year":"2022","unstructured":"Assran, M., et al.: Masked Siamese networks for label-efficient learning. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13691, pp. 456\u2013473. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19821-2_26"},{"key":"6_CR3","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. In: 2015 International Conference on Learning Representations (2015)"},{"key":"6_CR4","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 Computer Vision and Pattern Recognition Conference (2021)","DOI":"10.1109\/CVPR46437.2021.00356"},{"key":"6_CR5","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.: A simple framework for contrastive learning of visual representations. In: International Conference on Machine Learning (2020)"},{"key":"6_CR6","unstructured":"Chorowski, J.K., Bahdanau, D., Serdyuk, D., Cho, K., Bengio, Y.: Attention-based models for speech recognition. In: Advances in Neural Information Processing Systems, vol.\u00a028. Curran Associates, Inc. (2015)"},{"key":"6_CR7","unstructured":"Coates, A., Ng, A., Lee, H.: An analysis of single-layer networks in unsupervised feature learning. In: International Conference on Artificial Intelligence and Statistics (2011)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., Shlens, J., Le, Q.: RandAugment: practical automated data augmentation with a reduced search space. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol.\u00a033, pp. 18613\u201318624 (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"6_CR9","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":"6_CR10","unstructured":"DeVries, T., Taylor, G.W.: Dataset augmentation in feature space. arXiv preprint arXiv:1702.05538 (2017)"},{"key":"6_CR11","doi-asserted-by":"crossref","unstructured":"Dong, X., et al.: MaskCLIP: masked self-distillation advances contrastive language-image pretraining. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10995\u201311005 (2023)","DOI":"10.1109\/CVPR52729.2023.01058"},{"key":"6_CR12","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: International Conference on Learning Representations (2021)"},{"issue":"22","key":"6_CR13","doi-asserted-by":"publisher","first-page":"2199","DOI":"10.1001\/jama.2017.14585","volume":"318","author":"B Ehteshami Bejnordi","year":"2017","unstructured":"Ehteshami Bejnordi, B., et al.: Diagnostic assessment of deep learning algorithms for detection of lymph node metastases in women with breast cancer. J. Am. Med. Assoc. 318(22), 2199\u20132210 (2017)","journal-title":"J. Am. Med. Assoc."},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"issue":"7","key":"6_CR16","doi-asserted-by":"publisher","first-page":"2217","DOI":"10.1109\/JSTARS.2019.2918242","volume":"12","author":"P Helber","year":"2019","unstructured":"Helber, P., Bischke, B., Dengel, A., Borth, D.: EuroSAT: a novel dataset and deep learning benchmark for land use and land cover classification. IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens. 12(7), 2217\u20132226 (2019)","journal-title":"IEEE J. Sel. Top. Appl. Earth Observ. Remote Sens."},{"key":"6_CR17","unstructured":"Ilharco, G., et al.: OpenCLIP (2021)"},{"key":"6_CR18","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":"6_CR19","unstructured":"Krizhevsky, A., Hinton, G., et\u00a0al.: Learning multiple layers of features from tiny images. Technical report, University of Toronto (2009)"},{"key":"6_CR20","unstructured":"Krizhevsky, A., Sutskever, I., Hinton, G.E.: ImageNet classification with deep convolutional neural networks. In: Advances in Neural Information Processing Systems, vol. 25 (2012)"},{"issue":"11","key":"6_CR21","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":"6_CR22","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":"6_CR23","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":"6_CR24","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":"6_CR25","unstructured":"Lu, J., Yang, J., Batra, D., Parikh, D.: Hierarchical question-image co-attention for visual question answering. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"6_CR26","unstructured":"Mnih, V., Heess, N., Graves, A., et al.: Recurrent models of visual attention. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"6_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/978-3-031-19809-0_30","volume-title":"Computer Vision - ECCV 2022","author":"N Mu","year":"2022","unstructured":"Mu, N., Kirillov, A., Wagner, D.A., Xie, S.: SLIP: self-supervision meets language-image pre-training. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13686, pp. 529\u2013544. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_30"},{"key":"6_CR28","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1016\/j.neucom.2021.03.091","volume":"452","author":"Z Niu","year":"2021","unstructured":"Niu, Z., Zhong, G., Yu, H.: A review on the attention mechanism of deep learning. Neurocomputing 452, 48\u201362 (2021)","journal-title":"Neurocomputing"},{"key":"6_CR29","unstructured":"van\u00a0den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding (2019)"},{"issue":"2","key":"6_CR30","doi-asserted-by":"publisher","first-page":"4","DOI":"10.2307\/3192343","volume":"32","author":"RH Quan","year":"1979","unstructured":"Quan, R.H.: Photography and the creation of meaning. Art Educ. 32(2), 4\u20139 (1979)","journal-title":"Art Educ."},{"key":"6_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning (2021)"},{"key":"6_CR32","unstructured":"Schuhmann, C., et al.: LAION-5B: an open large-scale dataset for training next generation image-text models. In: Conference on Neural Information Processing Systems, Datasets and Benchmarks Track (2022)"},{"key":"6_CR33","unstructured":"Schuhmann, C., et al.: LAION-400M: open dataset of CLIP-filtered 400 million image-text pairs (2021)"},{"key":"6_CR34","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"},{"issue":"1","key":"6_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-019-0197-0","volume":"6","author":"C Shorten","year":"2019","unstructured":"Shorten, C., Khoshgoftaar, T.M.: A survey on image data augmentation for deep learning. J. Big Data 6(1), 1\u201348 (2019)","journal-title":"J. Big Data"},{"issue":"14","key":"6_CR36","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1167\/7.14.4","volume":"7","author":"BW Tatler","year":"2007","unstructured":"Tatler, B.W.: The central fixation bias in scene viewing: selecting an optimal viewing position independently of motor biases and image feature distributions. J. Vis. 7(14), 4 (2007)","journal-title":"J. Vis."},{"key":"6_CR37","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems (2017)"},{"key":"6_CR38","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"210","DOI":"10.1007\/978-3-030-00934-2_24","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"BS Veeling","year":"2018","unstructured":"Veeling, B.S., Linmans, J., Winkens, J., Cohen, T., Welling, M.: Rotation equivariant CNNs for digital pathology. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11071, pp. 210\u2013218. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00934-2_24"},{"key":"6_CR39","doi-asserted-by":"crossref","unstructured":"Yang, Y., et\u00a0al.: Attentive mask clip. In: IEEE\/CVF International Conference on Computer Vision, pp. 2771\u20132781 (2023)","DOI":"10.1109\/ICCV51070.2023.00260"},{"key":"6_CR40","doi-asserted-by":"crossref","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. 67\u201378 (2014)","DOI":"10.1162\/tacl_a_00166"}],"container-title":["Lecture Notes in Computer Science","Machine Learning and Knowledge Discovery in Databases. Research Track and Demo Track"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-70371-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,5]],"date-time":"2025-09-05T21:20:49Z","timestamp":1757107249000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-70371-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031703706","9783031703713"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-70371-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"22 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECML PKDD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Joint European Conference on Machine Learning and Knowledge Discovery in Databases","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vilnius","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ecml2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2024.ecmlpkdd.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}