{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,10]],"date-time":"2026-04-10T16:47:17Z","timestamp":1775839637883,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":35,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819985425","type":"print"},{"value":"9789819985432","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,29]],"date-time":"2023-12-29T00:00:00Z","timestamp":1703808000000},"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\/978-981-99-8543-2_31","type":"book-chapter","created":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T10:03:03Z","timestamp":1703757783000},"page":"377-390","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Improving Masked Autoencoders by\u00a0Learning Where to\u00a0Mask"],"prefix":"10.1007","author":[{"given":"Haijian","family":"Chen","sequence":"first","affiliation":[]},{"given":"Wendong","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yunbo","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,29]]},"reference":[{"key":"31_CR1","unstructured":"Bao, H., Dong, L., et al.: Beit: BERT pre-training of image transformers. In: ICLR (2022)"},{"key":"31_CR2","doi-asserted-by":"crossref","unstructured":"Caron, M., Touvron, H., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"31_CR3","unstructured":"Chen, M., Radford, A., et al.: Generative pretraining from pixels. In: ICML (2020)"},{"key":"31_CR4","unstructured":"Chen, T., Kornblith, S., Norouzi, M., et al.: A simple framework for contrastive learning of visual representations. In: ICML (2020)"},{"key":"31_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Cubuk, E.D., Zoph, B., et al.: Randaugment: practical automated data augmentation with a reduced search space. In: CVPR Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"31_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: Imagenet: a large-scale hierarchical image database. In: CVPR (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"31_CR8","unstructured":"Devlin, J., Chang, M., et al.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL-HLT (2019)"},{"key":"31_CR9","unstructured":"Dosovitskiy, A., Beyer, L., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"31_CR10","unstructured":"Feichtenhofer, C., Fan, H., et al.: Masked autoencoders as spatiotemporal learners. In: NeurIPS (2022)"},{"key":"31_CR11","unstructured":"Grill, J.B., Strub, F., et al.: Bootstrap your own latent-a new approach to self-supervised learning. In: NeurIPS (2020)"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., et al.: Masked autoencoders are scalable vision learners. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., et al.: Momentum contrast for unsupervised visual representation learning. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., et al.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"31_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"646","DOI":"10.1007\/978-3-319-46493-0_39","volume-title":"Computer Vision \u2013 ECCV 2016","author":"G Huang","year":"2016","unstructured":"Huang, G., Sun, Yu., Liu, Z., Sedra, D., Weinberger, K.Q.: Deep networks with stochastic depth. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9908, pp. 646\u2013661. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46493-0_39"},{"key":"31_CR16","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"300","DOI":"10.1007\/978-3-031-20056-4_18","volume-title":"ECCV 2022","author":"I Kakogeorgiou","year":"2022","unstructured":"Kakogeorgiou, I., Gidaris, S., et al.: What to hide from your students: Attention-guided masked image modeling. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13690, pp. 300\u2013318. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20056-4_18"},{"key":"31_CR17","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., et al.: 3D object representations for fine-grained categorization. In: ICCV Workshops (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"31_CR18","unstructured":"Li, G., Zheng, H., et al.: Semmae: semantic-guided masking for learning masked autoencoders. In: NeurIPS (2022)"},{"key":"31_CR19","unstructured":"Li, Y., Xie, S., et al.: Benchmarking detection transfer learning with vision transformers. CoRR (2021)"},{"key":"31_CR20","unstructured":"Li, Z., Chen, Z., et al.: MST: masked self-supervised transformer for visual representation. In: NeurIPS (2021)"},{"key":"31_CR21","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":"31_CR22","doi-asserted-by":"crossref","unstructured":"Mao, X., Li, Q., et al.: Least squares generative adversarial networks. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.304"},{"key":"31_CR23","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: ICML (2021)"},{"key":"31_CR24","unstructured":"Shi, Y., et al.: Adversarial masking for self-supervised learning. In: ICML (2022)"},{"key":"31_CR25","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1007\/978-3-030-58621-8_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Tian","year":"2020","unstructured":"Tian, Y., Krishnan, D., Isola, P.: Contrastive multiview coding. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12356, pp. 776\u2013794. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58621-8_45"},{"key":"31_CR26","unstructured":"Tong, Z., Song, Y., et al.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Van Horn, G., Mac Aodha, O., et al.: The inaturalist species classification and detection dataset. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00914"},{"key":"31_CR28","unstructured":"Wah, C., Branson, S., et al.: The Caltech-UCSD birds-200-2011 dataset (2011)"},{"key":"31_CR29","unstructured":"Xiao, K., Engstrom, L., Ilyas, A., Madry, A.: Noise or signal: the role of image backgrounds in object recognition. In: ICLR (2021)"},{"key":"31_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"432","DOI":"10.1007\/978-3-030-01228-1_26","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T Xiao","year":"2018","unstructured":"Xiao, T., Liu, Y., Zhou, B., Jiang, Y., Sun, J.: Unified perceptual parsing for scene understanding. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11209, pp. 432\u2013448. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01228-1_26"},{"key":"31_CR31","doi-asserted-by":"crossref","unstructured":"Xie, Z., Zhang, Z., et al.: Simmim: a simple framework for masked image modeling. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"31_CR32","doi-asserted-by":"crossref","unstructured":"Yun, S., Han, D., et al.: Cutmix: regularization strategy to train strong classifiers with localizable features. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00612"},{"key":"31_CR33","unstructured":"Zhang, H., Ciss\u00e9, M., et al.: mixup: beyond empirical risk minimization. In: ICLR (2018)"},{"key":"31_CR34","doi-asserted-by":"crossref","unstructured":"Zhou, B., Zhao, H., et al.: Semantic understanding of scenes through the ADE20K dataset. In: ICCV (2019)","DOI":"10.1007\/s11263-018-1140-0"},{"key":"31_CR35","unstructured":"Zhou, J., Wei, C., et al.: iBOT: image BERT pre-training with online tokenizer. In: ICLR (2022)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8543-2_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,28]],"date-time":"2023-12-28T10:09:28Z","timestamp":1703758168000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8543-2_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,29]]},"ISBN":["9789819985425","9789819985432"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8543-2_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,29]]},"assertion":[{"value":"29 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision  (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}