{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T16:26:45Z","timestamp":1773246405575,"version":"3.50.1"},"publisher-location":"Cham","reference-count":26,"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_57","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"606-616","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":15,"title":["Surgformer: Surgical Transformer with\u00a0Hierarchical Temporal Attention for\u00a0Surgical Phase Recognition"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1761-9286","authenticated-orcid":false,"given":"Shu","family":"Yang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7485-4151","authenticated-orcid":false,"given":"Luyang","family":"Luo","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9515-7745","authenticated-orcid":false,"given":"Qiong","family":"Wang","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8400-3780","authenticated-orcid":false,"given":"Hao","family":"Chen","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"57_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Dehghani, M., Heigold, G., Sun, C., Lu\u010di\u0107, M., Schmid, C.: Vivit: A video vision transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6836\u20136846 (2021)","DOI":"10.1109\/ICCV48922.2021.00676"},{"key":"57_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? In: ICML. vol.\u00a02, p.\u00a04 (2021)"},{"key":"57_CR3","doi-asserted-by":"crossref","unstructured":"Cleary, K., Chung, H.Y., Mun, S.K.: Or2020 workshop overview: operating room of the future. In: International Congress Series. vol.\u00a01268, pp. 847\u2013852. Elsevier (2004)","DOI":"10.1016\/j.ics.2004.03.287"},{"key":"57_CR4","doi-asserted-by":"crossref","unstructured":"Czempiel, T., Paschali, M., Keicher, M., Simson, W., Feussner, H., Kim, S.T., Navab, N.: Tecno: Surgical phase recognition with multi-stage temporal convolutional networks. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2020: 23rd International Conference, Lima, Peru, October 4\u20138, 2020, Proceedings, Part III 23. pp. 343\u2013352. Springer (2020)","DOI":"10.1007\/978-3-030-59716-0_33"},{"issue":"3","key":"57_CR5","doi-asserted-by":"publisher","first-page":"427","DOI":"10.1097\/ACM.0000000000002414","volume":"94","author":"RD Dias","year":"2019","unstructured":"Dias, R.D., Gupta, A., Yule, S.J.: Using machine learning to assess physician competence: a systematic review. Academic Medicine 94(3), 427\u2013439 (2019)","journal-title":"Academic Medicine"},{"key":"57_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"57_CR7","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1007\/s11548-018-1791-x","volume":"13","author":"S Franke","year":"2018","unstructured":"Franke, S., Rockstroh, M., Hofer, M., Neumuth, T.: The intelligent or: design and validation of a context-aware surgical working environment. International Journal of Computer Assisted Radiology and Surgery 13, 1301\u20131308 (2018)","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"57_CR8","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: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part IV 24. pp. 593\u2013603. Springer (2021)","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"57_CR9","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Grauman, K.: Anticipative video transformer. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 13505\u201313515 (2021)","DOI":"10.1109\/ICCV48922.2021.01325"},{"issue":"5","key":"57_CR10","doi-asserted-by":"publisher","first-page":"1114","DOI":"10.1109\/TMI.2017.2787657","volume":"37","author":"Y Jin","year":"2017","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. IEEE transactions on medical imaging 37(5), 1114\u20131126 (2017)","journal-title":"IEEE transactions on medical imaging"},{"key":"57_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2019.101572","volume":"59","author":"Y Jin","year":"2020","unstructured":"Jin, Y., Li, H., Dou, Q., Chen, H., Qin, J., Fu, C.W., Heng, P.A.: Multi-task recurrent convolutional network with correlation loss for surgical video analysis. Medical image analysis 59, 101572 (2020)","journal-title":"Medical image analysis"},{"issue":"7","key":"57_CR12","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 Transactions on Medical Imaging 40(7), 1911\u20131923 (2021)","journal-title":"IEEE Transactions on Medical Imaging"},{"key":"57_CR13","unstructured":"Kay, W., Carreira, J., Simonyan, K., Zhang, B., Hillier, C., Vijayanarasimhan, S., Viola, F., Green, T., Back, T., Natsev, P., et\u00a0al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"57_CR14","doi-asserted-by":"publisher","first-page":"3732","DOI":"10.1007\/s00464-019-06667-4","volume":"33","author":"KF Kowalewski","year":"2019","unstructured":"Kowalewski, K.F., Garrow, C.R., Schmidt, M.W., Benner, L., M\u00fcller-Stich, B.P., Nickel, F.: Sensor-based machine learning for workflow detection and as key to detect expert level in laparoscopic suturing and knot-tying. Surgical endoscopy 33, 3732\u20133740 (2019)","journal-title":"Surgical endoscopy"},{"key":"57_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Y., Boels, M., Garcia-Peraza-Herrera, L.C., Vercauteren, T., Dasgupta, P., Granados, A., Ourselin, S.: Lovit: Long video transformer for surgical phase recognition. arXiv preprint arXiv:2305.08989 (2023)","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"57_CR16","doi-asserted-by":"crossref","unstructured":"Liu, Y., Huo, J., Peng, J., Sparks, R., Dasgupta, P., Granados, A., Ourselin, S.: Skit: a fast key information video transformer for online surgical phase recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 21074\u201321084 (2023)","DOI":"10.1109\/ICCV51070.2023.01927"},{"key":"57_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2023.107672","volume":"167","author":"Y Liu","year":"2023","unstructured":"Liu, Y., Zhong, X., Zhai, S., Du, Z., Gao, Z., Huang, Q., Zhang, C.Y., Jiang, B., Pandey, V.K., Han, S., et\u00a0al.: Prompt-enhanced hierarchical transformer elevating cardiopulmonary resuscitation instruction via temporal action segmentation. Computers in Biology and Medicine 167, 107672 (2023)","journal-title":"Computers in Biology and Medicine"},{"issue":"3","key":"57_CR18","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1515\/iss-2017-0005","volume":"2","author":"T Neumuth","year":"2017","unstructured":"Neumuth, T.: Surgical process modeling. Innovative surgical sciences 2(3), 123\u2013137 (2017)","journal-title":"Surgical process modeling. Innovative surgical sciences"},{"key":"57_CR19","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. arXiv preprint arXiv:1610.08844 (2016)"},{"issue":"1","key":"57_CR20","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\u00a0Mathelin, M., Padoy, N.: Endonet: a deep architecture for recognition tasks on laparoscopic videos. IEEE transactions on medical imaging 36(1), 86\u201397 (2016)","journal-title":"IEEE transactions on medical imaging"},{"key":"57_CR21","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: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 486\u2013496. Springer (2022)","DOI":"10.1007\/978-3-031-16449-1_46"},{"key":"57_CR22","doi-asserted-by":"crossref","unstructured":"Yang, S., Zhang, L., Qi, J., Lu, H., Wang, S., Zhang, X.: Learning motion-appearance co-attention for zero-shot video object segmentation. In: Proceedings of the IEEE\/CVF international conference on computer vision. pp. 1564\u20131573 (2021)","DOI":"10.1109\/ICCV48922.2021.00159"},{"key":"57_CR23","doi-asserted-by":"crossref","unstructured":"Yi, F., Jiang, T.: Hard frame detection and online mapping for surgical phase recognition. In: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2019: 22nd International Conference, Shenzhen, China, October 13\u201317, 2019, Proceedings, Part V 22. pp. 449\u2013457. Springer (2019)","DOI":"10.1007\/978-3-030-32254-0_50"},{"key":"57_CR24","doi-asserted-by":"crossref","unstructured":"Zhang, L., Lin, Z., Zhang, J., Lu, H., He, Y.: Fast video object segmentation via dynamic targeting network. In: Proceedings of the IEEE International Conference on Computer Vision. pp. 5582\u20135591 (2019)","DOI":"10.1109\/ICCV.2019.00568"},{"key":"57_CR25","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhang, J., Lin, Z., M\u011bch, R., Lu, H., He, Y.: Unsupervised video object segmentation with joint hotspot tracking. In: Proceedings of the European Conference on Computer Vision. pp. 490\u2013506. Springer International Publishing (2020)","DOI":"10.1007\/978-3-030-58568-6_29"},{"key":"57_CR26","doi-asserted-by":"publisher","first-page":"8326","DOI":"10.1109\/TIP.2020.3013162","volume":"29","author":"T Zhou","year":"2020","unstructured":"Zhou, T., Li, J., Wang, S., Tao, R., Shen, J.: Matnet: Motion-attentive transition network for zero-shot video object segmentation. IEEE Transactions on Image Processing 29, 8326\u20138338 (2020)","journal-title":"IEEE Transactions on Image Processing"}],"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_57","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:08:40Z","timestamp":1727885320000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_57"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_57","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"}}]}}