{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,14]],"date-time":"2026-03-14T18:40:57Z","timestamp":1773513657148,"version":"3.50.1"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031439957","type":"print"},{"value":"9783031439964","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-43996-4_10","type":"book-chapter","created":{"date-parts":[[2023,9,30]],"date-time":"2023-09-30T23:07:48Z","timestamp":1696115268000},"page":"101-111","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Foundation Model for\u00a0Endoscopy Video Analysis via\u00a0Large-Scale Self-supervised Pre-train"],"prefix":"10.1007","author":[{"given":"Zhao","family":"Wang","sequence":"first","affiliation":[]},{"given":"Chang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Shaoting","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Qi","family":"Dou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,10,1]]},"reference":[{"key":"10_CR1","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. Arxiv (2016)"},{"key":"10_CR2","doi-asserted-by":"crossref","unstructured":"Bernal, J., S\u00e1nchez, F.J., Fern\u00e1ndez-Esparrach, G., Gil, D., Rodr\u00edguez, C., Vilari\u00f1o, F.: WM-DOVA maps for accurate polyp highlighting in colonoscopy: validation vs. saliency maps from physicians. Comput. Med. Imaging Graph. 43, 99\u2013111 (2015)","DOI":"10.1016\/j.compmedimag.2015.02.007"},{"key":"10_CR3","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML, vol. 2, p. 4 (2021)"},{"key":"10_CR4","doi-asserted-by":"publisher","unstructured":"Boecking, B., et al.: Making the most of text semantics to improve biomedical vision-language processing. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13696, pp. 1\u201321. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20059-5_1","DOI":"10.1007\/978-3-031-20059-5_1"},{"issue":"1","key":"10_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-020-00622-y","volume":"7","author":"H Borgli","year":"2020","unstructured":"Borgli, H., et al.: Hyperkvasir, a comprehensive multi-class image and video dataset for gastrointestinal endoscopy. Sci. Data 7(1), 1\u201314 (2020)","journal-title":"Sci. Data"},{"key":"10_CR6","doi-asserted-by":"crossref","unstructured":"Caron, M., et al.: Emerging properties in self-supervised vision transformers. In: ICCV (2021)","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"10_CR7","doi-asserted-by":"crossref","unstructured":"Ding, S., et al.: Motion-aware contrastive video representation learning via foreground-background merging. In: CVPR, pp. 9716\u20139726 (2022)","DOI":"10.1109\/CVPR52688.2022.00949"},{"key":"10_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth $$16 \\times 16$$ words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"10_CR9","doi-asserted-by":"publisher","unstructured":"Fu, Z., Jiao, J., Yasrab, R., Drukker, L., Papageorghiou, A.T., Noble, J.A.: Anatomy-aware contrastive representation learning for fetal ultrasound. In: Karlinsky, L., Michaeli, T., Nishino, K. (eds.) Computer Vision \u2013 ECCV 2022 Workshops. ECCV 2022. LNCS, vol. 13803, pp. 422\u2013436. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-25066-8_23","DOI":"10.1007\/978-3-031-25066-8_23"},{"key":"10_CR10","unstructured":"Goodman, E.D., et al.: A real-time spatiotemporal AI model analyzes skill in open surgical videos. arXiv:2112.07219 (2021)"},{"key":"10_CR11","doi-asserted-by":"publisher","unstructured":"Hatamizadeh, A., Nath, V., Tang, Y., Yang, D., Roth, H.R., Xu, D.: Swin UNETR: swin transformers for semantic segmentation of brain tumors in MRI images. In: Crimi, A., Bakas, S. (eds.) Brainlesion: Glioma, Multiple Sclerosis, Stroke and Traumatic Brain Injuries. BrainLes 2021. LNCS, vol. 12962, pp. 272\u2013284. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-08999-2_22","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"10_CR12","doi-asserted-by":"crossref","unstructured":"Hu, K., Shao, J., Liu, Y., Raj, B., Savvides, M., Shen, Z.: Contrast and order representations for video self-supervised learning. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7939\u20137949 (2021)","DOI":"10.1109\/ICCV48922.2021.00784"},{"issue":"6","key":"10_CR13","doi-asserted-by":"publisher","first-page":"531","DOI":"10.1007\/s11633-022-1371-y","volume":"19","author":"GP Ji","year":"2022","unstructured":"Ji, G.P., et al.: Video polyp segmentation: a deep learning perspective. Mach. Intell. Res. 19(6), 531\u2013549 (2022)","journal-title":"Mach. Intell. Res."},{"key":"10_CR14","doi-asserted-by":"crossref","unstructured":"Kirillov, A., et al.: Segment anything. arXiv:2304.02643 (2023)","DOI":"10.1109\/ICCV51070.2023.00371"},{"issue":"8","key":"10_CR15","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0255809","volume":"16","author":"K Li","year":"2021","unstructured":"Li, K., et al.: Colonoscopy polyp detection and classification: dataset creation and comparative evaluations. PLoS ONE 16(8), e0255809 (2021)","journal-title":"PLoS ONE"},{"key":"10_CR16","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. In: ICLR (2017)"},{"key":"10_CR17","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: ICLR (2019)"},{"key":"10_CR18","doi-asserted-by":"publisher","unstructured":"Ma, Yiting, Chen, Xuejin, Cheng, Kai, Li, Yang, Sun, Bin: LDPolypVideo benchmark: a large-scale colonoscopy video dataset of diverse polyps. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 387\u2013396. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_37","DOI":"10.1007\/978-3-030-87240-3_37"},{"issue":"9","key":"10_CR19","first-page":"2051","volume":"35","author":"P Mesejo","year":"2016","unstructured":"Mesejo, P., et al.: Computer-aided classification of gastrointestinal lesions in regular colonoscopy. IEEE TMI 35(9), 2051\u20132063 (2016)","journal-title":"IEEE TMI"},{"issue":"12","key":"10_CR20","first-page":"6070","volume":"26","author":"JH Moon","year":"2022","unstructured":"Moon, J.H., Lee, H., Shin, W., Kim, Y.H., Choi, E.: Multi-modal understanding and generation for medical images and text via vision-language pre-training. IEEE JBHI 26(12), 6070\u20136080 (2022)","journal-title":"IEEE JBHI"},{"key":"10_CR21","doi-asserted-by":"crossref","unstructured":"Moor, M., et al.: Foundation models for generalist medical artificial intelligence. Nature 616(7956), 259\u2013265 (2023)","DOI":"10.1038\/s41586-023-05881-4"},{"key":"10_CR22","unstructured":"Naseer, M.M., Ranasinghe, K., Khan, S.H., Hayat, M., Shahbaz Khan, F., Yang, M.H.: Intriguing properties of vision transformers. NeurIPS (2021)"},{"key":"10_CR23","volume":"78","author":"CI Nwoye","year":"2022","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Media 78, 102433 (2022)","journal-title":"Media"},{"key":"10_CR24","unstructured":"Pan, J., Lin, Z., Zhu, X., Shao, J., Li, H.: St-adapter: parameter-efficient image-to-video transfer learning for action recognition. NeurIPS (2022)"},{"key":"10_CR25","doi-asserted-by":"crossref","unstructured":"Park, J., Lee, J., Kim, I.J., Sohn, K.: Probabilistic representations for video contrastive learning. In: CVPR, pp. 14711\u201314721 (2022)","DOI":"10.1109\/CVPR52688.2022.01430"},{"key":"10_CR26","doi-asserted-by":"publisher","unstructured":"Qian, R., Ding, S., Liu, X., Lin, D.: Static and dynamic concepts for self-supervised video representation learning. In: Avidan, S., Brostow, G., Cisse, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13686, pp. 145\u2013164. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19809-0_9","DOI":"10.1007\/978-3-031-19809-0_9"},{"key":"10_CR27","doi-asserted-by":"crossref","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.00689"},{"key":"10_CR28","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763. PMLR (2021)"},{"key":"10_CR29","doi-asserted-by":"crossref","unstructured":"Ranasinghe, K., Naseer, M., Khan, S., Khan, F.S., Ryoo, M.: Self-supervised video transformer. In: CVPR, June 2022","DOI":"10.1109\/CVPR52688.2022.00289"},{"issue":"1","key":"10_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-021-00920-z","volume":"8","author":"PH Smedsrud","year":"2021","unstructured":"Smedsrud, P.H., et al.: Kvasir-capsule, a video capsule endoscopy dataset. Sci. Data 8(1), 1\u201310 (2021)","journal-title":"Sci. Data"},{"key":"10_CR31","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Self-supervised pre-training of Swin transformers for 3D medical image analysis. In: CVPR, pp. 20730\u201320740 (2022)","DOI":"10.1109\/CVPR52688.2022.02007"},{"key":"10_CR32","doi-asserted-by":"publisher","unstructured":"Tian, Y., et al.: Contrastive transformer-based multiple instance learning for weakly supervised polyp frame detection. In: Wang, L., Dou, Q., Fletcher, P.T., Speidel, S., Li, S. (eds.) Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022. MICCAI 2022. LNCS, vol. 13433, pp. 88\u201398. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-16437-8_9","DOI":"10.1007\/978-3-031-16437-8_9"},{"issue":"6","key":"10_CR33","doi-asserted-by":"publisher","DOI":"10.1148\/ryai.210284","volume":"4","author":"MJ Willemink","year":"2022","unstructured":"Willemink, M.J., Roth, H.R., Sandfort, V.: Toward foundational deep learning models for medical imaging in the new era of transformer networks. Radiol. Artif. Intell. 4(6), e210284 (2022)","journal-title":"Radiol. Artif. Intell."},{"key":"10_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"302","DOI":"10.1007\/978-3-030-87240-3_29","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"L Wu","year":"2021","unstructured":"Wu, L., Hu, Z., Ji, Y., Luo, P., Zhang, S.: Multi-frame collaboration for effective endoscopic video polyp detection via spatial-temporal feature transformation. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12905, pp. 302\u2013312. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87240-3_29"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43996-4_10","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,4]],"date-time":"2024-07-04T16:04:48Z","timestamp":1720109088000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-43996-4_10"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031439957","9783031439964"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-43996-4_10","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"1 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"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":"Vancouver, BC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Canada","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":"8 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conferences.miccai.org\/2023\/en\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"2250","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":"730","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":"32% - 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","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":"5","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}