{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:52:27Z","timestamp":1782575547694,"version":"3.54.5"},"publisher-location":"Cham","reference-count":33,"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_42","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:04:54Z","timestamp":1663315494000},"page":"442-452","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":43,"title":["Towards Holistic Surgical Scene Understanding"],"prefix":"10.1007","author":[{"given":"Natalia","family":"Valderrama","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Paola","family":"Ruiz Puentes","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Isabela","family":"Hern\u00e1ndez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicol\u00e1s","family":"Ayobi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mathilde","family":"Verlyck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jessica","family":"Santander","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juan","family":"Caicedo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicol\u00e1s","family":"Fern\u00e1ndez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Arbel\u00e1ez","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Ahmidi, N., et al.: A dataset and benchmarks for segmentation and recognition of gestures in robotic surgery. IEEE Trans. Biomed. Eng. 64(9), 2025\u20132041 (2017)","DOI":"10.1109\/TBME.2016.2647680"},{"key":"42_CR2","unstructured":"Allan, M., et al.: 2017 robotic instrument segmentation challenge. arXiv preprint arXiv:1902.06426 (2019)"},{"key":"42_CR3","unstructured":"Allan, M., et al.: 2018 robotic scene segmentation challenge. arXiv preprint arXiv:2001.11190 (2020)"},{"key":"42_CR4","unstructured":"Bawa, V.S., Singh, G., KapingA, F., Skarga-Bandurova, I., Oleari, E., et al.: The SARAS endoscopic surgeon action detection (ESAD) dataset: challenges and methods. arXiv preprint arXiv:2104.03178 (2021)"},{"key":"42_CR5","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/978-3-030-58452-8_13","volume-title":"Computer Vision \u2013 ECCV 2020","author":"N Carion","year":"2020","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-End object detection with transformers. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 213\u2013229. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_13"},{"key":"42_CR6","doi-asserted-by":"publisher","unstructured":"Czempiel, T., Paschali, M., Ostler, D., Kim, S.T., Busam, B., Navab, N.: OperA: attention-regularized transformers for surgical phase recognition. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 604\u2013614. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_58","DOI":"10.1007\/978-3-030-87202-1_58"},{"key":"42_CR7","unstructured":"Ding, X., Li, X.: Exploiting segment-level semantics for online phase recognition from surgical videos. arXiv preprint arXiv:2111.11044 (2021)"},{"key":"42_CR8","unstructured":"Dosovitskiy, A., et al.: An image is worth 16\u00a0$$\\times $$\u00a016 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"42_CR9","doi-asserted-by":"crossref","unstructured":"Fan, H., et al.: Multiscale vision transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6824\u20136835 (2021)","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"42_CR10","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":"42_CR11","doi-asserted-by":"publisher","unstructured":"Gao, X., Jin, Y., Long, Y., Dou, Q., Heng, P.-A.: Trans-SVNet: accurate phase recognition from surgical videos via\u00a0hybrid embedding aggregation transformer. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 593\u2013603. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_57","DOI":"10.1007\/978-3-030-87202-1_57"},{"key":"42_CR12","doi-asserted-by":"publisher","unstructured":"Gonz\u00e1lez, C., Bravo-S\u00e1nchez, L., Arbelaez, P.: ISINet: an instance-based approach for surgical instrument segmentation. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 595\u2013605. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_57","DOI":"10.1007\/978-3-030-59716-0_57"},{"key":"42_CR13","unstructured":"Goodman, E.D., et al.: A real-time spatiotemporal AI model analyzes skill in open surgical videos. arXiv preprint arXiv:2112.07219 (2021)"},{"key":"42_CR14","unstructured":"Grammatikopoulou, et al.: Cadis: Cataract dataset for image segmentation. arXiv preprint arXiv:1906.11586 (2019)"},{"key":"42_CR15","doi-asserted-by":"crossref","unstructured":"Gu, C., et al.: AVA: a video dataset of spatio-temporally localized atomic visual actions. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6047\u20136056 (2018)","DOI":"10.1109\/CVPR.2018.00633"},{"key":"42_CR16","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":"42_CR17","doi-asserted-by":"crossref","unstructured":"Huaulm\u00e9, A., et al.: Micro-surgical anastomose workflow recognition challenge report. Comput. Methods Programs Biomed. 212, 106452 (2021)","DOI":"10.1016\/j.cmpb.2021.106452"},{"key":"42_CR18","unstructured":"Kay, W., et al.: The kinetics human action video dataset. arXiv preprint arXiv:1705.06950 (2017)"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Kondo, S.: LapFormer: surgical tool detection in laparoscopic surgical video using transformer architecture. Comput. Meth. Biomech. Biomed. Eng. Imaging Visual. 9(3), 302\u2013307 (2021)","DOI":"10.1080\/21681163.2020.1835550"},{"issue":"3","key":"42_CR20","doi-asserted-by":"publisher","first-page":"495","DOI":"10.1007\/s11548-013-0940-5","volume":"9","author":"F Lalys","year":"2013","unstructured":"Lalys, F., Jannin, P.: Surgical process modelling: a review. Int. J. Comput. Assist. Radiol. Surg. 9(3), 495\u2013511 (2013). https:\/\/doi.org\/10.1007\/s11548-013-0940-5","journal-title":"Int. J. Comput. Assist. Radiol. Surg."},{"key":"42_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Video swin transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3202\u20133211 (2022)","DOI":"10.1109\/CVPR52688.2022.00320"},{"key":"42_CR22","unstructured":"Luo, Z., et al.: MOMA: multi-object multi-actor activity parsing. Adv. Neural Inf. Process. Syst. 34, 17939\u201317955 (2021)"},{"issue":"9","key":"42_CR23","doi-asserted-by":"publisher","first-page":"691","DOI":"10.1038\/s41551-017-0132-7","volume":"1","author":"L Maier-Hein","year":"2017","unstructured":"Maier-Hein, L., Vedula, S.S., Speidel, S., et al.: Surgical data science for next-generation interventions. Nat. Biomed. Eng. 1(9), 691\u2013696 (2017)","journal-title":"Nat. Biomed. Eng."},{"issue":"1","key":"42_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41597-021-00882-2","volume":"8","author":"L Maier-Hein","year":"2021","unstructured":"Maier-Hein, L., Wagner, M., Ross, T., et al.: Heidelberg colorectal data set for surgical data science in the sensor operating room. Scient. Data 8(1), 1\u201311 (2021)","journal-title":"Scient. Data"},{"key":"42_CR25","doi-asserted-by":"publisher","unstructured":"Nwoye, C.I., et al.: Recognition of instrument-tissue interactions in endoscopic videos via action triplets. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 364\u2013374. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_35","DOI":"10.1007\/978-3-030-59716-0_35"},{"key":"42_CR26","doi-asserted-by":"crossref","unstructured":"Nwoye, C.I., et al.: Rendezvous: attention mechanisms for the recognition of surgical action triplets in endoscopic videos. arXiv preprint arXiv:2109.03223 (2021)","DOI":"10.1016\/j.media.2022.102433"},{"key":"42_CR27","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. arXiv preprint arXiv:1506.01497 (2015)"},{"key":"42_CR28","doi-asserted-by":"publisher","unstructured":"Sharghi, A., Haugerud, H., Oh, D., Mohareri, O.: Automatic operating room surgical activity recognition for robot-assisted surgery. In: Martel, A.L., et al. (eds.) MICCAI 2020. LNCS, vol. 12263, pp. 385\u2013395. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-59716-0_37","DOI":"10.1007\/978-3-030-59716-0_37"},{"key":"42_CR29","unstructured":"Stauder, R., Ostler, D., et al.: The tum lapchole dataset for the m2cai 2016 workflow challenge. arXiv preprint arXiv:1610.09278 (2016)"},{"issue":"1","key":"42_CR30","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":"42_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, B., et al.: Towards accurate surgical workflow recognition with convolutional networks and transformers. Comput. Meth. Biomech. Biomed. Eng. Imaging Visual. 10(4), 1\u20138 (2021)","DOI":"10.1080\/21681163.2021.2002191"},{"key":"42_CR32","doi-asserted-by":"crossref","unstructured":"Zhao, Z., Jin, Y., Heng, P.A.: TraSeTR: track-to-segment transformer with contrastive query for instance-level instrument segmentation in robotic surgery. arXiv preprint arXiv:2202.08453 (2022)","DOI":"10.1109\/ICRA46639.2022.9811873"},{"key":"42_CR33","unstructured":"Zhu, X., Su, W., Lu, L., Li, B., Wang, X., Dai, J.: Deformable DETR: deformable transformers for end-to-end object detection. arXiv preprint arXiv:2010.04159 (2020)"}],"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_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:57:47Z","timestamp":1709830667000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_42","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)"}}]}}