{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T17:54:15Z","timestamp":1782928455640,"version":"3.54.5"},"publisher-location":"Cham","reference-count":30,"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_60","type":"book-chapter","created":{"date-parts":[[2021,9,22]],"date-time":"2021-09-22T19:03:23Z","timestamp":1632337403000},"page":"626-635","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Multi-view Surgical Video Action Detection via Mixed Global View Attention"],"prefix":"10.1007","author":[{"given":"Adam","family":"Schmidt","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aidean","family":"Sharghi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Helene","family":"Haugerud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Oh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Mohareri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,21]]},"reference":[{"key":"60_CR1","unstructured":"University of Central Florida-aerial camera, rooftop camera and ground camera dataset. https:\/\/www.crcv.ucf.edu\/data\/UCF-ARG.php"},{"key":"60_CR2","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.media.2018.11.008","volume":"52","author":"H Al Hajj","year":"2019","unstructured":"Al Hajj, H., et al.: CATARACTS: challenge on automatic tool annotation for cataract surgery. Med. Image Anal. 52, 24\u201341 (2019)","journal-title":"Med. Image Anal."},{"issue":"2","key":"60_CR3","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"60_CR4","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo Vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 6299\u20136308 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"60_CR5","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C.: X3D: Expanding architectures for efficient video recognition. arXiv:2004.04730 [cs], April 2020","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"60_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: SlowFast networks for video recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 6202\u20136211 (2019)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"60_CR7","doi-asserted-by":"publisher","unstructured":"Gkalelis, N., Kim, H., Hilton, A., Nikolaidis, N., Pitas, I.: The i3DPost multi-view and 3D human action\/interaction database. In: 2009 Conference for Visual Media Production, London, United Kingdom, pp. 159\u2013168. IEEE, November 2009. https:\/\/doi.org\/10.1109\/CVMP.2009.19","DOI":"10.1109\/CVMP.2009.19"},{"key":"60_CR8","doi-asserted-by":"crossref","unstructured":"Home Office Scientific Development Branch: Imagery library for intelligent detection systems (i-LIDS). In: 2006 IET Conference on Crime and Security, pp. 445\u2013448, June 2006","DOI":"10.1049\/ic:20060350"},{"key":"60_CR9","unstructured":"Joze, H.R.V., Shaban, A., Iuzzolino, M.L., Koishida, K.: MMTM: multimodal transfer module for CNN fusion. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13289\u201313299 (2020)"},{"issue":"2\u20133","key":"60_CR10","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev, I.: On space-time interest points. Int. J. Comput. Vis. 64(2\u20133), 107\u2013123 (2005)","journal-title":"Int. J. Comput. Vis."},{"key":"60_CR11","doi-asserted-by":"publisher","unstructured":"Li, W., Wong, Y., Liu, A.A., Li, Y., Su, Y.T., Kankanhalli, M.: Multi-camera action dataset for cross-camera action recognition benchmarking. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 187\u2013196, March 2017. https:\/\/doi.org\/10.1109\/WACV.2017.28","DOI":"10.1109\/WACV.2017.28"},{"key":"60_CR12","doi-asserted-by":"crossref","unstructured":"Lin, T., Liu, X., Li, X., Ding, E., Wen, S.: BMN: boundary-matching network for temporal action proposal generation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3889\u20133898 (2019)","DOI":"10.1109\/ICCV.2019.00399"},{"issue":"6","key":"60_CR13","doi-asserted-by":"publisher","first-page":"1194","DOI":"10.1109\/TCYB.2014.2347057","volume":"45","author":"A Liu","year":"2015","unstructured":"Liu, A., Su, Y., Jia, P., Gao, Z., Hao, T., Yang, Z.: Multiple\/single-view human action recognition via part-induced multitask structural learning. IEEE Trans. Cybern. 45(6), 1194\u20131208 (2015). https:\/\/doi.org\/10.1109\/TCYB.2014.2347057","journal-title":"IEEE Trans. Cybern."},{"issue":"7","key":"60_CR14","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1109\/TCYB.2016.2582918","volume":"47","author":"A Liu","year":"2017","unstructured":"Liu, A., Xu, N., Nie, W., Su, Y., Wong, Y., Kankanhalli, M.: Benchmarking a multimodal and multiview and interactive dataset for human action recognition. IEEE Trans. Cybern. 47(7), 1781\u20131794 (2017). https:\/\/doi.org\/10.1109\/TCYB.2016.2582918","journal-title":"IEEE Trans. Cybern."},{"issue":"10","key":"60_CR15","doi-asserted-by":"publisher","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2020","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2020). https:\/\/doi.org\/10.1109\/TPAMI.2019.2916873","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"60_CR16","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1097\/CCM.0000000000002265","volume":"45","author":"AJ Ma","year":"2017","unstructured":"Ma, A.J., et al.: Measuring patient mobility in the ICU using a novel noninvasive sensor. Crit. Care Med. 45(4), 630 (2017)","journal-title":"Crit. Care Med."},{"key":"60_CR17","doi-asserted-by":"crossref","unstructured":"Machado, G., Ferreira, E., Nogueira, K., Oliveira, H., Gama, P., dos Santos, J.A.: AiRound and CV-BrCT: novel multi-view datasets for scene classification. arXiv:2008.01133 [cs], August 2020","DOI":"10.1109\/JSTARS.2020.3033424"},{"issue":"7","key":"60_CR18","doi-asserted-by":"publisher","first-page":"758","DOI":"10.1049\/iet-cvi.2015.0416","volume":"10","author":"F Murtaza","year":"2016","unstructured":"Murtaza, F., Yousaf, M.H., Velastin, S.A.: Multi-view human action recognition using 2D motion templates based on MHIs and their HOG description. IET Comput. Vis. 10(7), 758\u2013767 (2016). https:\/\/doi.org\/10.1049\/iet-cvi.2015.0416","journal-title":"IET Comput. Vis."},{"key":"60_CR19","doi-asserted-by":"publisher","unstructured":"Rybok, L., Friedberger, S., Hanebeck, U.D., Stiefelhagen, R.: The KIT Robo-kitchen data set for the evaluation of view-based activity recognition systems. In: 2011 11th IEEE-RAS International Conference on Humanoid Robots, Bled, Slovenia, pp. 128\u2013133. IEEE, October 2011. https:\/\/doi.org\/10.1109\/Humanoids.2011.6100854","DOI":"10.1109\/Humanoids.2011.6100854"},{"key":"60_CR20","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"60_CR21","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"385","DOI":"10.1007\/978-3-030-59716-0_37","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2020","author":"A Sharghi","year":"2020","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"},{"key":"60_CR22","doi-asserted-by":"crossref","unstructured":"Sigurdsson, G.A., Gupta, A., Schmid, C., Farhadi, A., Alahari, K.: Actor and observer: joint modeling of first and third-person videos. arXiv:1804.09627 [cs], April 2018","DOI":"10.1109\/CVPR.2018.00772"},{"key":"60_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. arXiv:1706.03762 [cs], December 2017"},{"key":"60_CR24","doi-asserted-by":"crossref","unstructured":"Wang, H., Schmid, C.: Action recognition with improved trajectories. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3551\u20133558 (2013)","DOI":"10.1109\/ICCV.2013.441"},{"key":"60_CR25","doi-asserted-by":"publisher","unstructured":"Wang, J., Nie, X., Xia, Y., Wu, Y., Zhu, S.C.: Cross-view action modeling, learning, and recognition. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 2649\u20132656. IEEE, June 2014. https:\/\/doi.org\/10.1109\/CVPR.2014.339","DOI":"10.1109\/CVPR.2014.339"},{"issue":"2\u20133","key":"60_CR26","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.cviu.2006.07.013","volume":"104","author":"D Weinland","year":"2006","unstructured":"Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Comput. Vis. Image Underst. 104(2\u20133), 249\u2013257 (2006). https:\/\/doi.org\/10.1016\/j.cviu.2006.07.013","journal-title":"Comput. Vis. Image Underst."},{"key":"60_CR27","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":"1","key":"60_CR28","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41746-018-0076-7","volume":"2","author":"S Yeung","year":"2019","unstructured":"Yeung, S., et al.: A computer vision system for deep learning-based detection of patient mobilization activities in the ICU. NPJ Digit. Med. 2(1), 1\u20135 (2019)","journal-title":"NPJ Digit. Med."},{"key":"60_CR29","doi-asserted-by":"crossref","unstructured":"Zhao, Y., Xiong, Y., Wang, L., Wu, Z., Tang, X., Lin, D.: Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2914\u20132923 (2017)","DOI":"10.1109\/ICCV.2017.317"},{"key":"60_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1007\/978-3-030-00937-3_32","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2018","author":"A Zia","year":"2018","unstructured":"Zia, A., Hung, A., Essa, I., Jarc, A.: Surgical activity recognition in robot-assisted radical prostatectomy using deep learning. In: Frangi, A.F., Schnabel, J.A., Davatzikos, C., Alberola-L\u00f3pez, C., Fichtinger, G. (eds.) MICCAI 2018. LNCS, vol. 11073, pp. 273\u2013280. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-00937-3_32"}],"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_60","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T18:19:34Z","timestamp":1725819574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87202-1_60"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030872014","9783030872021"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87202-1_60","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)"}}]}}