{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,10]],"date-time":"2026-09-10T23:09:55Z","timestamp":1789081795963,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031164484","type":"print"},{"value":"9783031164491","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-16449-1_35","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:04:54Z","timestamp":1663315494000},"page":"365-375","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Free Lunch for\u00a0Surgical Video Understanding by\u00a0Distilling Self-supervisions"],"prefix":"10.1007","author":[{"given":"Xinpeng","family":"Ding","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaomeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"35_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1007\/978-3-642-15711-0_50","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2010","author":"T Blum","year":"2010","unstructured":"Blum, T., Feu\u00dfner, H., Navab, N.: Modeling and segmentation of surgical workflow from laparoscopic video. In: Jiang, T., Navab, N., Pluim, J.P.W., Viergever, M.A. (eds.) MICCAI 2010. LNCS, vol. 6363, pp. 400\u2013407. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-15711-0_50"},{"key":"35_CR2","first-page":"9912","volume":"33","author":"M Caron","year":"2020","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. Adv. Neural. Inf. Process. Syst. 33, 9912\u20139924 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR3","doi-asserted-by":"publisher","first-page":"101539","DOI":"10.1016\/j.media.2019.101539","volume":"58","author":"L Chen","year":"2019","unstructured":"Chen, L., Bentley, P., Mori, K., Misawa, K., Fujiwara, M., Rueckert, D.: Self-supervised learning for medical image analysis using image context restoration. Med. Image Anal. 58, 101539 (2019)","journal-title":"Med. Image Anal."},{"key":"35_CR4","unstructured":"Chen, X., Fan, H., Girshick, R., He, K.: Improved baselines with momentum contrastive learning. arXiv preprint arXiv:2003.04297 (2020)"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple siamese representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 15750\u201315758 (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"35_CR6","unstructured":"Ding, X., Li, X.: Exploiting segment-level semantics for online phase recognition from surgical videos. arXiv preprint arXiv:2111.11044 (2021)"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Ding, X., et al.: Support-set based cross-supervision for video grounding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11573\u201311582 (2021)","DOI":"10.1109\/ICCV48922.2021.01137"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Farha, Y.A., Gall, J.: MS-TCN: multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3575\u20133584 (2019)","DOI":"10.1109\/CVPR.2019.00369"},{"key":"35_CR9","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. arXiv preprint arXiv:2103.09712 (2021)","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR12","unstructured":"Hinton, G., Vinyals, O., Dean, J., et al.: Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531, vol. 2, no. 7 (2015)"},{"issue":"5","key":"35_CR13","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","volume":"37","author":"Y Jin","year":"2017","unstructured":"Jin, Y., et al.: SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans. Med. Imaging 37(5), 1114\u20131126 (2017)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"35_CR14","doi-asserted-by":"publisher","first-page":"101572","DOI":"10.1016\/j.media.2019.101572","volume":"59","author":"Y Jin","year":"2020","unstructured":"Jin, Y., et al.: Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Med. Image Anal. 59, 101572 (2020)","journal-title":"Med. Image Anal."},{"issue":"7","key":"35_CR15","doi-asserted-by":"publisher","first-page":"1911","DOI":"10.1109\/TMI.2021.3069471","volume":"40","author":"Y Jin","year":"2021","unstructured":"Jin, Y., Long, Y., Chen, C., Zhao, Z., Dou, Q., Heng, P.A.: Temporal memory relation network for workflow recognition from surgical video. IEEE Trans. Med. Imaging 40(7), 1911\u20131923 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"9","key":"35_CR16","doi-asserted-by":"publisher","first-page":"2284","DOI":"10.1109\/TMI.2021.3075244","volume":"40","author":"X Li","year":"2021","unstructured":"Li, X., et al.: Rotation-oriented collaborative self-supervised learning for retinal disease diagnosis. IEEE Trans. Med. Imaging 40(9), 2284\u20132294 (2021)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"12","key":"35_CR17","doi-asserted-by":"publisher","first-page":"4023","DOI":"10.1109\/TMI.2020.3008871","volume":"39","author":"X Li","year":"2020","unstructured":"Li, X., Jia, M., Islam, M.T., Yu, L., Xing, L.: Self-supervised feature learning via exploiting multi-modal data for retinal disease diagnosis. IEEE Trans. Med. Imaging 39(12), 4023\u20134033 (2020)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"35_CR18","unstructured":"Van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv e-prints pp. arXiv-1807 (2018)"},{"key":"35_CR19","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11205\u201311214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"issue":"3","key":"35_CR20","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. Int. J. Comput. Vision 115(3), 211\u2013252 (2015)","journal-title":"Int. J. Comput. Vision"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Stauder, R., Ostler, D., Kranzfelder, M., Koller, S., Feu\u00dfner, H., Navab, N.: The TUM LapChole dataset for the M2CAI 2016 workflow challenge. arXiv preprint arXiv:1610.09278 (2016)","DOI":"10.1515\/iss-2017-0035"},{"key":"35_CR22","first-page":"18158","volume":"33","author":"A Taleb","year":"2020","unstructured":"Taleb, A., et al.: 3D self-supervised methods for medical imaging. Adv. Neural. Inf. Process. Syst. 33, 18158\u201318172 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"35_CR23","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"},{"issue":"1","key":"35_CR24","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2016","unstructured":"Twinanda, A.P., Shehata, S., Mutter, D., Marescaux, J., De Mathelin, M., Padoy, N.: EndoNet: a deep architecture for recognition tasks on laparoscopic videos. IEEE Trans. Med. Imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"35_CR25","unstructured":"Wang, Z., Ding, X., Zhao, W., Li, X.: Less is more: surgical phase recognition from timestamp supervision. arXiv preprint arXiv:2202.08199 (2022)"},{"key":"35_CR26","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"341","DOI":"10.1007\/978-3-030-59722-1_33","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"X Xie","year":"2020","unstructured":"Xie, X., Chen, J., Li, Y., Shen, L., Ma, K., Zheng, Y.: Instance-aware self-supervised learning for nuclei segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12265, pp. 341\u2013350. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59722-1_33"},{"key":"35_CR27","unstructured":"Xu, Y., Zhang, Q., Zhang, J., Tao, D.: RegionCL: can simple region swapping contribute to contrastive learning? arXiv preprint arXiv:2111.12309 (2021)"},{"key":"35_CR28","unstructured":"Yi, F., Jiang, T.: Not end-to-end: explore multi-stage architecture for online surgical phase recognition. arXiv preprint arXiv:2107.04810 (2021)"},{"issue":"7","key":"35_CR29","doi-asserted-by":"publisher","first-page":"732","DOI":"10.1016\/j.media.2013.04.007","volume":"17","author":"L Zappella","year":"2013","unstructured":"Zappella, L., B\u00e9jar, B., Hager, G., Vidal, R.: Surgical gesture classification from video and kinematic data. Med. Image Anal. 17(7), 732\u2013745 (2013)","journal-title":"Med. Image Anal."},{"key":"35_CR30","doi-asserted-by":"crossref","unstructured":"Zhou, H.Y., Lu, C., Yang, S., Han, X., Yu, Y.: Preservational learning improves self-supervised medical image models by reconstructing diverse contexts. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3499\u20133509 (2021)","DOI":"10.1109\/ICCV48922.2021.00348"},{"key":"35_CR31","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"398","DOI":"10.1007\/978-3-030-59710-8_39","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"H-Y Zhou","year":"2020","unstructured":"Zhou, H.-Y., Yu, S., Bian, C., Hu, Y., Ma, K., Zheng, Y.: Comparing to learn: surpassing imagenet pretraining on radiographs by comparing image representations. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12261, pp. 398\u2013407. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59710-8_39"},{"key":"35_CR32","doi-asserted-by":"publisher","first-page":"101840","DOI":"10.1016\/j.media.2020.101840","volume":"67","author":"Z Zhou","year":"2021","unstructured":"Zhou, Z., Sodha, V., Pang, J., Gotway, M.B., Liang, J.: Models genesis. Med. Image Anal. 67, 101840 (2021)","journal-title":"Med. Image Anal."},{"key":"35_CR33","doi-asserted-by":"publisher","first-page":"101746","DOI":"10.1016\/j.media.2020.101746","volume":"64","author":"J Zhu","year":"2020","unstructured":"Zhu, J., Li, Y., Hu, Y., Ma, K., Zhou, S.K., Zheng, Y.: Rubik\u2019s Cube+: a self-supervised feature learning framework for 3D medical image analysis. Med. Image Anal. 64, 101746 (2020)","journal-title":"Med. Image Anal."},{"key":"35_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/978-3-030-32251-9_46","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2019","author":"X Zhuang","year":"2019","unstructured":"Zhuang, X., Li, Y., Hu, Y., Ma, K., Yang, Y., Zheng, Y.: Self-supervised feature learning for 3D medical images by playing a Rubik\u2019s cube. In: Shen, D., et al. (eds.) MICCAI 2019. LNCS, vol. 11767, pp. 420\u2013428. Springer, Cham (2019). https:\/\/doi.org\/10.1007\/978-3-030-32251-9_46"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16449-1_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:55:53Z","timestamp":1709830553000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"17 September 2022","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":"Singapore","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Singapore","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"miccai2022","order":10,"name":"conference_id","label":"Conference ID","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 Conference","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1831","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":"574","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":"31% - 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)"}}]}}