{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T17:52:53Z","timestamp":1784310773476,"version":"3.55.0"},"publisher-location":"Cham","reference-count":27,"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_28","type":"book-chapter","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T19:03:23Z","timestamp":1632337403000},"page":"290-299","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Surgical Instruction Generation with Transformers"],"prefix":"10.1007","author":[{"given":"Jinglu","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yinyu","family":"Nie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian Jun","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"28_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"382","DOI":"10.1007\/978-3-319-46454-1_24","volume-title":"Computer Vision \u2013 ECCV 2016","author":"P Anderson","year":"2016","unstructured":"Anderson, P., Fernando, B., Johnson, M., Gould, S.: SPICE: semantic propositional image caption evaluation. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 382\u2013398. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_24"},{"key":"28_CR2","doi-asserted-by":"crossref","unstructured":"Anderson, P., et al.: Bottom-up and top-down attention for image captioning and visual question answering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6077\u20136086 (2018)","DOI":"10.1109\/CVPR.2018.00636"},{"key":"28_CR3","unstructured":"Banerjee, S., Lavie, A.: Meteor: an automatic metric for mt evaluation with improved correlation with human judgments. In: Proceedings of the acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/or Summarization, pp. 65\u201372 (2005)"},{"key":"28_CR4","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: Advances in Neural Information Processing Systems, pp. 1171\u20131179 (2015)"},{"issue":"4","key":"28_CR5","doi-asserted-by":"publisher","first-page":"379","DOI":"10.1177\/1553350617708725","volume":"24","author":"E Bilgic","year":"2017","unstructured":"Bilgic, E., et al.: Effectiveness of telementoring in surgery compared with on-site mentoring: a systematic review. Surg. Innov. 24(4), 379\u2013385 (2017)","journal-title":"Surg. Innov."},{"key":"28_CR6","doi-asserted-by":"crossref","unstructured":"Bustos, A., Pertusa, A., Salinas, J.M., de la Iglesia-Vay\u00e1, M.: Padchest: a large chest x-ray image dataset with multi-label annotated reports. Med. Image Anal. 66, 101797 (2020)","DOI":"10.1016\/j.media.2020.101797"},{"key":"28_CR7","doi-asserted-by":"crossref","unstructured":"Chen, Z., Song, Y., Chang, T.H., Wan, X.: Generating radiology reports via memory-driven transformer. arXiv preprint arXiv:2010.16056 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.112"},{"key":"28_CR8","doi-asserted-by":"crossref","unstructured":"Cornia, M., Stefanini, M., Baraldi, L., Cucchiara, R.: Meshed-memory transformer for image captioning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10578\u201310587 (2020)","DOI":"10.1109\/CVPR42600.2020.01059"},{"issue":"1","key":"28_CR9","doi-asserted-by":"publisher","first-page":"95","DOI":"10.1177\/1553350618813250","volume":"26","author":"S Erridge","year":"2019","unstructured":"Erridge, S., Yeung, D.K., Patel, H.R., Purkayastha, S.: Telementoring of surgeons: a systematic review. Surg. Innov. 26(1), 95\u2013111 (2019)","journal-title":"Surg. Innov."},{"key":"28_CR10","doi-asserted-by":"crossref","unstructured":"Funke, I., Bodenstedt, S., Oehme, F., von Bechtolsheim, F., Weitz, J., Speidel, S.: Using 3d convolutional neural networks to learn spatiotemporal features for automatic surgical gesture recognition in video. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 467\u2013475. Springer (2019)","DOI":"10.1007\/978-3-030-32254-0_52"},{"key":"28_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":"28_CR12","doi-asserted-by":"crossref","unstructured":"Jing, B., Xie, P., Xing, E.: On the automatic generation of medical imaging reports. arXiv preprint arXiv:1711.08195 (2017)","DOI":"10.18653\/v1\/P18-1240"},{"key":"28_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"28_CR14","unstructured":"Lin, C.Y.: Rouge: a package for automatic evaluation of summaries. In: Text Summarization Branches Out, pp. 74\u201381 (2004)"},{"key":"28_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"TY Lin","year":"2014","unstructured":"Lin, T.Y., et al.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"28_CR16","doi-asserted-by":"crossref","unstructured":"Papineni, K., Roukos, S., Ward, T., Zhu, W.J.: Bleu: a method for automatic evaluation of machine translation. In: Proceedings of the 40th Annual Meeting of the Association For Computational Linguistics, pp. 311\u2013318 (2002)","DOI":"10.3115\/1073083.1073135"},{"key":"28_CR17","unstructured":"Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: International Conference on Machine Learning, pp. 1310\u20131318 (2013)"},{"issue":"6","key":"28_CR18","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2016","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster r-cnn: towards real-time object detection with region proposal networks. IEEE Trans. Pattern Anal. Mach. Intell. 39(6), 1137\u20131149 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"28_CR19","doi-asserted-by":"crossref","unstructured":"Rennie, S.J., Marcheret, E., Mroueh, Y., Ross, J., Goel, V.: Self-critical sequence training for image captioning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7008\u20137024 (2017)","DOI":"10.1109\/CVPR.2017.131"},{"key":"28_CR20","unstructured":"Rojas-Mu\u00f1oz, E., Couperus, K., Wachs, J.: Daisi: Database for ai surgical instruction. arXiv preprint arXiv:2004.02809 (2020)"},{"key":"28_CR21","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)"},{"issue":"1","key":"28_CR22","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":"28_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"28_CR24","doi-asserted-by":"crossref","unstructured":"Vedantam, R., Lawrence Zitnick, C., Parikh, D.: Cider: consensus-based image description evaluation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4566\u20134575 (2015)","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"28_CR25","doi-asserted-by":"crossref","unstructured":"Vinyals, O., Toshev, A., Bengio, S., Erhan, D.: Show and tell: a neural image caption generator. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3156\u20133164 (2015)","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"28_CR26","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning, pp. 2048\u20132057 (2015)"},{"key":"28_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"409","DOI":"10.1007\/978-3-030-59716-0_39","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"J Zhang","year":"2020","unstructured":"Zhang, J., et al.: Symmetric dilated convolution for surgical gesture recognition. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 409\u2013418. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_39"}],"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_28","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T18:19:16Z","timestamp":1725819556000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87202-1_28"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030872014","9783030872021"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87202-1_28","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)"}}]}}