{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T01:04:46Z","timestamp":1785200686213,"version":"3.55.0"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030872014","type":"print"},{"value":"9783030872021","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87202-1_58","type":"book-chapter","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T19:03:23Z","timestamp":1632337403000},"page":"604-614","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":80,"title":["OperA: Attention-Regularized Transformers for Surgical Phase Recognition"],"prefix":"10.1007","author":[{"given":"Tobias","family":"Czempiel","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Magdalini","family":"Paschali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Ostler","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Seong Tae","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Benjamin","family":"Busam","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"58_CR1","unstructured":"Maier-Hein, L., et al.: Surgical data science: a consensus perspective. arXiv preprint arXiv:1806.03184 (2018)"},{"key":"58_CR2","doi-asserted-by":"publisher","first-page":"684","DOI":"10.1097\/SLA.0000000000004425","volume":"273","author":"CR Garrow","year":"2020","unstructured":"Garrow, C.R., et al.: Machine learning for surgical phase recognition: a systematic review. Ann. Surg. 273, 684\u2013693 (2020)","journal-title":"Ann. Surg."},{"key":"58_CR3","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1080\/13645706.2019.1584116","volume":"28","author":"N Padoy","year":"2019","unstructured":"Padoy, N.: Machine and deep learning for workflow recognition during surgery. Minim. Invasive Ther. Allied Technol. 28, 82\u201390 (2019)","journal-title":"Minim. Invasive Ther. Allied Technol."},{"issue":"May","key":"58_CR4","first-page":"2020","volume":"104","author":"A Huaulm\u00e9","year":"2019","unstructured":"Huaulm\u00e9, A., Jannin, P., Reche, F., Faucheron, J.L., Moreau-Gaudry, A., Voros, S.: Offline identification of surgical deviations in laparoscopic rectopexy. Artif. Intell. Med. 104(May), 2020 (2019)","journal-title":"Artif. Intell. Med."},{"issue":"1","key":"58_CR5","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1109\/TMI.2016.2593957","volume":"36","author":"AP Twinanda","year":"2017","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 (2017)","journal-title":"IEEE Trans. Med. Imaging"},{"issue":"7","key":"58_CR6","doi-asserted-by":"publisher","first-page":"1217","DOI":"10.1007\/s11548-019-01995-1","volume":"14","author":"I Funke","year":"2019","unstructured":"Funke, I., Mees, S.T., Weitz, J., Speidel, S.: Video-based surgical skill assessment using 3D convolutional neural networks. Int. J. Comput. Assist. Radiol. Surg. 14(7), 1217\u20131225 (2019)","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"58_CR7","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 2017-Decem, no. Nips, pp. 5999\u20136009 (2017)"},{"key":"58_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: NAACL HLT 2019\u20132019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies - Proceedings of the Conference, vol. 1, no. Mlm, pp. 4171\u20134186 (2019)"},{"issue":"8","key":"58_CR9","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"58_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"420","DOI":"10.1007\/11866565_52","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2006","author":"S-A Ahmadi","year":"2006","unstructured":"Ahmadi, S.-A., Sielhorst, T., Stauder, R., Horn, M., Feussner, H., Navab, N.: Recovery of surgical workflow without explicit models. In: Larsen, R., Nielsen, M., Sporring, J. (eds.) MICCAI 2006. LNCS, vol. 4190, pp. 420\u2013428. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11866565_52"},{"issue":"3","key":"58_CR11","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1016\/j.media.2010.10.001","volume":"16","author":"N Padoy","year":"2012","unstructured":"Padoy, N., Blum, T., Ahmadi, S.A., Feussner, H., Berger, M.O., Navab, N.: Statistical modeling and recognition of surgical workflow. Med. Image Anal. 16(3), 632\u2013641 (2012)","journal-title":"Med. Image Anal."},{"key":"58_CR12","unstructured":"Twinanda, A.P., Padoy, N., Troccaz, M.J., Hager, G.: Vision-based approaches for surgical activity recognition using laparoscopic and RBGD videos, Thesis, no. Umr 7357 (2017)"},{"key":"58_CR13","unstructured":"Yengera, G., Mutter, D., Marescaux, J., Padoy, N.: Less is more: surgical phase recognition with less annotations through self-supervised pre-training of CNN-LSTM networks. arXiv preprint arXiv:1805.08569 (2018)"},{"issue":"5","key":"58_CR14","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","volume":"37","author":"Y Jin","year":"2018","unstructured":"Jin, Y., et al.: SV-RCNet: workflow recognition from surgical videos using recurrent convolutional network. IEEE Trans. Med. Imaging 37(5), 1114\u20131126 (2018)","journal-title":"IEEE Trans. Med. Imaging"},{"key":"58_CR15","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."},{"key":"58_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1007\/978-3-030-59716-0_33","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"T Czempiel","year":"2020","unstructured":"Czempiel, T., et al.: TeCNO: surgical phase recognition with multi-stage temporal convolutional networks. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 343\u2013352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_33"},{"key":"58_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun,J.: Deep residual learning for image recognition. In: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"58_CR18","unstructured":"Brown, T.B., et al.: Language models are few-shot learners. arXiv (2020)"},{"key":"58_CR19","unstructured":"Dosovitskiy, A., et al.: An image is worth 16 $$\\times $$ 16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"58_CR20","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. arXiv preprint arXiv:2102.12092 (2021)"},{"key":"58_CR21","doi-asserted-by":"publisher","first-page":"637","DOI":"10.1002\/prot.25847","volume":"88","author":"L Heo","year":"2020","unstructured":"Heo, L., Feig, M.: High-accuracy protein structures by combining machine-learning with physics-based refinement. Proteins 88, 637\u2013642 (2020)","journal-title":"Proteins"},{"key":"58_CR22","doi-asserted-by":"crossref","unstructured":"Kondo, S.: Lapformer: surgical tool detection in laparoscopic surgical video using transformer architecture. In: Computer Methods in Biomechanics and Biomedical Engineering: Imaging & Visualization, pp. 1\u20136 (2020)","DOI":"10.1080\/21681163.2020.1835550"},{"key":"58_CR23","unstructured":"Jain, S., Wallace, B.C.: Attention is not explanation. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, NAACL-HLT 2019, Minneapolis, MN, USA, 2\u20137 June 2019, vol. 1, pp. 3543\u20133556. Association for Computational Linguistics (2019)"},{"key":"58_CR24","doi-asserted-by":"crossref","unstructured":"Wiegreffe, S., Pinter, Y.: Attention is not not explanation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), Hong Kong, China, pp. 11\u201320. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/D19-1002"},{"key":"58_CR25","unstructured":"Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. In: International Conference on Learning Representations, pp. 1\u201321 (2017)"},{"key":"58_CR26","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"58_CR27","doi-asserted-by":"crossref","unstructured":"Eigen, D., Fergus, R.: Predicting depth, surface normals and semantic labels with a common multi-scale convolutional architecture. In: 2015 IEEE International Conference on Computer Vision (ICCV). IEEE (2015)","DOI":"10.1109\/ICCV.2015.304"},{"key":"58_CR28","doi-asserted-by":"crossref","unstructured":"Al-Rfou, R., Choe, D., Constant, N., Guo, M., Jones, L.: Character-level language modeling with deeper self-attention. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, July 2019","DOI":"10.1609\/aaai.v33i01.33013159"}],"container-title":["Lecture Notes in Computer Science","Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87202-1_58","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T03:53:22Z","timestamp":1632369202000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87202-1_58"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030872014","9783030872021"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87202-1_58","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"21 September 2021","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":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 October 2021","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":"miccai2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/miccai2021.org\/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":"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":"1622","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":"531","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":"33% - 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":"4","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)"}},{"value":"The conference was held virtually.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}