{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,26]],"date-time":"2026-04-26T05:21:27Z","timestamp":1777180887981,"version":"3.51.4"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031720888","type":"print"},{"value":"9783031720895","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\/978-3-031-72089-5_18","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"187-196","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["EgoSurgery-Phase: A Dataset of\u00a0Surgical Phase Recognition from\u00a0Egocentric Open Surgery Videos"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9115-8414","authenticated-orcid":false,"given":"Ryo","family":"Fujii","sequence":"first","affiliation":[]},{"given":"Masashi","family":"Hatano","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2421-9862","authenticated-orcid":false,"given":"Hideo","family":"Saito","sequence":"additional","affiliation":[]},{"given":"Hiroki","family":"Kajita","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Czempiel, T., Paschali, M., Keicher, M., Simson, W., Feussner, H., Kim, S., Navab, N.: Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: MICCAI (2020)","DOI":"10.1007\/978-3-030-59716-0_33"},{"key":"18_CR2","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In: ICLR (2021)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Fujii, R., Hachiuma, R., Kajita, H., Saito, H.: Surgical Tool Detection in Open Surgery Videos. Applied Sciences (2022)","DOI":"10.3390\/app122010473"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Gao, X., Jin, Y., Long, Y., Dou, Q., Heng, P.A.: Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer. In: MICCAI (2021)","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"18_CR5","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: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"18_CR6","unstructured":"Jamal, M.A., Mohareri, O.: SurgMAE: Masked Autoencoders for Long Surgical Video Analysis (2023)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Jin, Y., Dou, Q., Chen, H., Yu, L., Qin, J., Fu, C.W., Heng, P.A.: SV-RCNet: Workflow Recognition From Surgical Videos Using Recurrent Convolutional Network. TMI (2018)","DOI":"10.1109\/TMI.2017.2787657"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Jin, Y., Long, Y., Chen, C., Zhao, Z., Dou, Q., Heng, P.A.: Temporal memory relation network for workflow recognition from surgical video. TMI (2021)","DOI":"10.1109\/TMI.2021.3069471"},{"key":"18_CR9","unstructured":"Li, G., Zheng, H., Liu, D., Wang, C., Su, B., Zheng, C.: SemMAE: Semantic-Guided Masking for Learning Masked Autoencoders. In: NeurIPS (2022)"},{"key":"18_CR10","unstructured":"Li, Z., Chen, Z., Yang, F., Li, W., Zhu, Y., Zhao, C., Deng, R., Wu, L., Zhao, R., Tang, M., Wang, J.: MST: Masked Self-Supervised Transformer for Visual Representation. In: NeurIPS (2021)"},{"key":"18_CR11","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Mao, Y., Deng, J., Zhou, W., Fang, Y., Ouyang, W., Li, H.: Masked motion predictors are strong 3d action representation learners. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Min, C., Xiao, L., Zhao, D., Nie, Y., Dai, B.: Occupancy-MAE: Self-Supervised Pre-Training Large-Scale LiDAR Point Clouds With Masked Occupancy Autoencoders. IV (2023)","DOI":"10.1109\/TIV.2023.3322409"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Sun, X., Chen, P., Chen, L., Li, C., Li, T.H., Tan, M., Gan, C.: Masked Motion Encoding for Self-Supervised Video Representation Learning. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00222"},{"key":"18_CR15","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: VideoMAE: Masked autoencoders are data-efficient learners for self-supervised video pre-training. In: NeurIPS (2022)"},{"key":"18_CR16","unstructured":"Twinanda, A.P., Mutter, D., Marescaux, J., de\u00a0Mathelin, M., Padoy, N.: Single- and Multi-Task Architectures for Surgical Workflow Challenge at M2CAI 2016 (2016)"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., de\u00a0Mathelin, M., Padoy, N.: EndoNet: A Deep Architecture for Recognition Tasks on Laparoscopic Videos. IEEE TMI (2017)","DOI":"10.1109\/TMI.2016.2593957"},{"key":"18_CR18","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L.u., Polosukhin, I.: Attention is All you Need. In: NeurIPS (2017)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wang, L., Huang, B., Zhao, Z., Tong, Z., He, Y., Wang, Y., Wang, Y., Qiao, Y.: VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01398"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Wang, Z., Lu, B., Long, Y., Zhong, F., Cheung, T.H., Dou, Q., Liu, Y.: AutoLaparo: A New Dataset of Integrated Multi-tasks for Image-guided Surgical Automation in Laparoscopic Hysterectomy. In: MICCAI (2022)","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Yi, F., Yang, Y., Jiang, T.: Not End-to-End: Explore Multi-Stage Architecture for Online Surgical Phase Recognition. In: ACCV (2023)","DOI":"10.1007\/978-3-031-26316-3_25"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72089-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:04:11Z","timestamp":1727885051000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_18","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":"3 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"The authors have no competing interests to declare that are relevant to the content of this article.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Disclosure of Interests"}},{"value":"MICCAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Medical Image Computing and Computer-Assisted Intervention","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Marrakesh","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Morocco","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":"7 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2024\/en\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}