{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,14]],"date-time":"2026-06-14T21:41:38Z","timestamp":1781473298445,"version":"3.54.1"},"publisher-location":"Cham","reference-count":28,"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_29","type":"book-chapter","created":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:02:20Z","timestamp":1727884940000},"page":"306-316","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["HecVL: Hierarchical Video-Language Pretraining for\u00a0Zero-Shot Surgical Phase Recognition"],"prefix":"10.1007","author":[{"given":"Kun","family":"Yuan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinkle","family":"Srivastav","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nassir","family":"Navab","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,3]]},"reference":[{"key":"29_CR1","doi-asserted-by":"crossref","unstructured":"Blum, T., Feu\u00dfner, H., Navab, N.: Modeling and segmentation of surgical workflow from laparoscopic video. In: Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2010: 13th International Conference, Beijing, China, September 20-24, 2010, Proceedings, Part III 13. pp. 400\u2013407. Springer (2010)","DOI":"10.1007\/978-3-642-15711-0_50"},{"issue":"4","key":"29_CR2","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1109\/TPAMI.2017.2699184","volume":"40","author":"LC Chen","year":"2017","unstructured":"Chen, L.C., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. IEEE transactions on pattern analysis and machine intelligence 40(4), 834\u2013848 (2017)","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"29_CR3","first-page":"31333","volume":"35","author":"T Chen","year":"2022","unstructured":"Chen, T., Saxena, S., Li, L., Lin, T.Y., Fleet, D.J., Hinton, G.E.: A unified sequence interface for vision tasks. Advances in Neural Information Processing Systems 35, 31333\u201331346 (2022)","journal-title":"Advances in Neural Information Processing Systems"},{"key":"29_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"},{"key":"29_CR5","unstructured":"Goodfellow, I.J., Mirza, M., Xiao, D., Courville, A., Bengio, Y.: An empirical investigation of catastrophic forgetting in gradient-based neural networks. arXiv preprint arXiv:1312.6211 (2013)"},{"key":"29_CR6","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":"29_CR7","doi-asserted-by":"crossref","unstructured":"Hu, M., Xia, P., Wang, L., Yan, S., Tang, F., Xu, Z., Luo, Y., Song, K., Leitner, J., Cheng, X., et\u00a0al.: Ophnet: A large-scale video benchmark for ophthalmic surgical workflow understanding. arXiv preprint arXiv:2406.07471 (2024)","DOI":"10.1007\/978-3-031-73235-5_27"},{"key":"29_CR8","unstructured":"Huang, K., Altosaar, J., Ranganath, R.: Clinicalbert: Modeling clinical notes and predicting hospital readmission. arXiv preprint arXiv:1904.05342 (2019)"},{"issue":"5","key":"29_CR9","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":"29_CR10","doi-asserted-by":"crossref","unstructured":"Lavanchy, J.L., Ramesh, S., Dall\u2019Alba, D., Gonzalez, C., Fiorini, P., Muller-Stich, B., Nett, P.C., Marescaux, J., Mutter, D., Padoy, N.: Challenges in multi-centric generalization: Phase and step recognition in roux-en-y gastric bypass surgery. arXiv preprint arXiv:2312.11250 (2023)","DOI":"10.1007\/s11548-024-03166-3"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Lin, W., Karlinsky, L., Shvetsova, N., Possegger, H., Kozinski, M., Panda, R., Feris, R., Kuehne, H., Bischof, H.: Match, expand and improve: Unsupervised finetuning for zero-shot action recognition with language knowledge. arXiv preprint arXiv:2303.08914 (2023)","DOI":"10.1109\/ICCV51070.2023.00267"},{"key":"29_CR12","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"29_CR13","doi-asserted-by":"crossref","unstructured":"Miech, A., Alayrac, J.B., Smaira, L., Laptev, I., Sivic, J., Zisserman, A.: End-to-end learning of visual representations from uncurated instructional videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 9879\u20139889 (2020)","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"29_CR14","unstructured":"Ming, H., Lin, W., Siyuan, Y., Don, M., Qingli, R., Peng, X., Wei, F., Peibo, D., Lie, J., Zongyuan, G.: Nurvid: A large expert-level video database for nursing procedure activity understanding. In: Thirty-seventh Conference on Neural Information Processing Systems Datasets and Benchmarks Track (2023)"},{"key":"29_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2022.102433","volume":"78","author":"CI Nwoye","year":"2022","unstructured":"Nwoye, C.I., Yu, T., Gonzalez, C., Seeliger, B., Mascagni, P., Mutter, D., Marescaux, J., Padoy, N.: Rendezvous: Attention mechanisms for the recognition of surgical action triplets in endoscopic videos. Medical Image Analysis 78, 102433 (2022)","journal-title":"Medical Image Analysis"},{"key":"29_CR16","unstructured":"Oord, A.v.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"issue":"3","key":"29_CR17","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. Medical image analysis 16(3), 632\u2013641 (2012)","journal-title":"Medical image analysis"},{"key":"29_CR18","unstructured":"Radford, A., Kim, J.W., Hallacy, C., Ramesh, A., Goh, G., Agarwal, S., Sastry, G., Askell, A., Mishkin, P., Clark, J., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International conference on machine learning. pp. 8748\u20138763. PMLR (2021)"},{"key":"29_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2023.102844","volume":"88","author":"S Ramesh","year":"2023","unstructured":"Ramesh, S., Srivastav, V., Alapatt, D., Yu, T., Murali, A., Sestini, L., Nwoye, C.I., Hamoud, I., Sharma, S., Fleurentin, A., et\u00a0al.: Dissecting self-supervised learning methods for surgical computer vision. Medical Image Analysis 88, 102844 (2023)","journal-title":"Medical Image Analysis"},{"issue":"1","key":"29_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":"29_CR21","doi-asserted-by":"crossref","unstructured":"Wang, H., Jin, Y., Zhu, L.: Dynamic interactive relation capturing via scene graph learning for robotic surgical report generation. In: 2023 IEEE International Conference on Robotics and Automation (ICRA). pp. 2702\u20132709. IEEE (2023)","DOI":"10.1109\/ICRA48891.2023.10160647"},{"key":"29_CR22","doi-asserted-by":"crossref","unstructured":"Wang, H., Zhu, L., Yang, G., Guo, Y., Zhang, S., Xu, B., Jin, Y.: Video-instrument synergistic network for referring video instrument segmentation in robotic surgery. arXiv preprint arXiv:2308.09475 (2023)","DOI":"10.1109\/TMI.2024.3426953"},{"key":"29_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Z., Liu, C., Zhang, S., Dou, Q.: Foundation model for endoscopy video analysis via large-scale self-supervised pre-train. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp. 101\u2013111. Springer (2023)","DOI":"10.1007\/978-3-031-43996-4_10"},{"key":"29_CR24","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":"29_CR25","doi-asserted-by":"crossref","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: Medical Image Computing and Computer Assisted Intervention\u2013MICCAI 2021: 24th International Conference, Strasbourg, France, September 27\u2013October 1, 2021, Proceedings, Part V 24. pp. 302\u2013312. Springer (2021)","DOI":"10.1007\/978-3-030-87240-3_29"},{"key":"29_CR26","unstructured":"Yuan, K., Srivastav, V., Yu, T., Lavanchy, J., Mascagni, P., Navab, N., Padoy, N.: Learning multi-modal representations by watching hundreds of surgical video lectures. arXiv preprint arXiv:2307.15220 (2023)"},{"key":"29_CR27","doi-asserted-by":"crossref","unstructured":"Zou, X., Dou, Z.Y., Yang, J., Gan, Z., Li, L., Li, C., Dai, X., Behl, H., Wang, J., Yuan, L., et\u00a0al.: Generalized decoding for pixel, image, and language. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15116\u201315127 (2023)","DOI":"10.1109\/CVPR52729.2023.01451"},{"key":"29_CR28","unstructured":"Zou, X., Yang, J., Zhang, H., Li, F., Li, L., Wang, J., Wang, L., Gao, J., Lee, Y.J.: Segment everything everywhere all at once. Advances in Neural Information Processing Systems 36 (2024)"}],"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_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,2]],"date-time":"2024-10-02T16:06:20Z","timestamp":1727885180000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72089-5_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031720888","9783031720895"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72089-5_29","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"}}]}}