{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T15:57:49Z","timestamp":1787500669610,"version":"build-2736575974"},"publisher-location":"Cham","reference-count":36,"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_43","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T04:04:54Z","timestamp":1663301094000},"page":"453-463","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-modal Unsupervised Pre-training for\u00a0Surgical Operating Room Workflow Analysis"],"prefix":"10.1007","author":[{"given":"Muhammad Abdullah","family":"Jamal","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Omid","family":"Mohareri","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"43_CR1","unstructured":"Bao, H., Dong, L., Wei, F.: Beit: BERT pre-training of image transformers. CoRR abs\/2106.08254 (2021)"},{"key":"43_CR2","unstructured":"Bertasius, G., Wang, H., Torresani, L.: Is space-time attention all you need for video understanding? CoRR abs\/2102.05095 (2021)"},{"key":"43_CR3","doi-asserted-by":"crossref","unstructured":"Caron, M., Bojanowski, P., Joulin, A., Douze, M.: Deep clustering for unsupervised learning of visual features. CoRR abs\/1807.05520 (2018)","DOI":"10.1007\/978-3-030-01264-9_9"},{"key":"43_CR4","unstructured":"Caron, M., Misra, I., Mairal, J., Goyal, P., Bojanowski, P., Joulin, A.: Unsupervised learning of visual features by contrasting cluster assignments. CoRR abs\/2006.09882 (2020)"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? a new model and the kinetics dataset. CoRR abs\/1705.07750 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"issue":"9","key":"43_CR6","doi-asserted-by":"publisher","first-page":"3749","DOI":"10.1007\/s00464-015-4671-2","volume":"30","author":"K Catchpole","year":"2015","unstructured":"Catchpole, K., et al.: Safety, efficiency and learning curves in robotic surgery: a human factors analysis. Surg. Endosc. 30(9), 3749\u20133761 (2015). https:\/\/doi.org\/10.1007\/s00464-015-4671-2","journal-title":"Surg. Endosc."},{"key":"43_CR7","unstructured":"Chen, L., Papandreou, G., Kokkinos, I., Murphy, K., Yuille, A.L.: Deeplab: Semantic image segmentation with deep convolutional nets, atrous convolution, and fully connected crfs. CoRR abs\/1606.00915 (2016)"},{"key":"43_CR8","unstructured":"Chen, T., Kornblith, S., Norouzi, M., Hinton, G.E.: A simple framework for contrastive learning of visual representations. CoRR abs\/2002.05709 (2020)"},{"key":"43_CR9","unstructured":"Cuturi, M.: Sinkhorn distances: Lightspeed computation of optimal transport. In: Burges, C.J.C., Bottou, L., Welling, M., Ghahramani, Z., Weinberger, K.Q. (eds.) Advances in Neural Information Processing Systems (2013)"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Malik, J., He, K.: Slowfast networks for video recognition. CoRR abs\/1812.03982 (2018)","DOI":"10.1109\/ICCV.2019.00630"},{"key":"43_CR11","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Fan, H., Xiong, B., Girshick, R.B., He, K.: A large-scale study on unsupervised spatiotemporal representation learning. CoRR abs\/2104.14558 (2021)","DOI":"10.1109\/CVPR46437.2021.00331"},{"key":"43_CR12","unstructured":"Grill, J., et al.: Bootstrap your own latent: a new approach to self-supervised learning. CoRR abs\/2006.07733 (2020)"},{"key":"43_CR13","unstructured":"Han, T., Xie, W., Zisserman, A.: Self-supervised co-training for video representation learning. CoRR abs\/2010.09709 (2020)"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.B.: Masked autoencoders are scalable vision learners. CoRR abs\/2111.06377 (2021)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.B.: Momentum contrast for unsupervised visual representation learning. CoRR abs\/1911.05722 (2019)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"43_CR16","unstructured":"Issenhuth, T., Srivastav, V., Gangi, A., Padoy, N.: Face detection in the operating room: Comparison of state-of-the-art methods and a self-supervised approach. CoRR abs\/1811.12296 (2018)"},{"key":"43_CR17","unstructured":"Kadkhodamohammadi, A., Gangi, A., de Mathelin, M., Padoy, N.: 3d pictorial structures on RGB-D data for articulated human detection in operating rooms. CoRR abs\/1602.03468 (2016)"},{"key":"43_CR18","doi-asserted-by":"crossref","unstructured":"Kadkhodamohammadi, A., Gangi, A., de Mathelin, M., Padoy, N.: A multi-view RGB-D approach for human pose estimation in operating rooms. CoRR abs\/1701.07372 (2017)","DOI":"10.1109\/WACV.2017.47"},{"key":"43_CR19","unstructured":"Kay, W., et al.: The kinetics human action video dataset. CoRR abs\/1705.06950 (2017)"},{"key":"43_CR20","doi-asserted-by":"crossref","unstructured":"Lee, H., Huang, J., Singh, M., Yang, M.: Unsupervised representation learning by sorting sequences. CoRR abs\/1708.01246 (2017)","DOI":"10.1109\/ICCV.2017.79"},{"key":"43_CR21","unstructured":"Li, Z., Shaban, A., Simard, J., Rabindran, D., DiMaio, S.P., Mohareri, O.: A robotic 3d perception system for operating room environment awareness. CoRR abs\/2003.09487 (2020)"},{"key":"43_CR22","doi-asserted-by":"crossref","unstructured":"Misra, I., van der Maaten, L.: Self-supervised learning of pretext-invariant representations. CoRR abs\/1912.01991 (2019)","DOI":"10.1109\/CVPR42600.2020.00674"},{"key":"43_CR23","unstructured":"van den Oord, A., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. CoRR abs\/1807.03748 (2018)"},{"key":"43_CR24","doi-asserted-by":"crossref","unstructured":"Peyr\u00e9, G., Cuturi, M.: Computational optimal transport (2020)","DOI":"10.1561\/9781680835519"},{"key":"43_CR25","unstructured":"Qian, R., et al.: Spatiotemporal contrastive video representation learning. CoRR abs\/2008.03800 (2020)"},{"key":"43_CR26","doi-asserted-by":"crossref","unstructured":"Ranzato, M., Huang, F.J., Boureau, Y.L., LeCun, Y.: Unsupervised learning of invariant feature hierarchies with applications to object recognition. In: CVPR (2007)","DOI":"10.1109\/CVPR.2007.383157"},{"key":"43_CR27","unstructured":"Russakovsky, O., et al.: Imagenet large scale visual recognition challenge. CoRR abs\/1409.0575 (2014)"},{"key":"43_CR28","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"626","DOI":"10.1007\/978-3-030-87202-1_60","volume-title":"Medical Image Computing and Computer Assisted Intervention \u2013 MICCAI 2021","author":"A Schmidt","year":"2021","unstructured":"Schmidt, A., Sharghi, A., Haugerud, H., Oh, D., Mohareri, O.: Multi-view surgical video action detection via mixed global view attention. In: de Bruijne, M., et al. (eds.) MICCAI 2021. LNCS, vol. 12904, pp. 626\u2013635. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-87202-1_60"},{"key":"43_CR29","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":"43_CR30","doi-asserted-by":"crossref","unstructured":"Srivastav, V., Gangi, A., Padoy, N.: Human pose estimation on privacy-preserving low-resolution depth images. CoRR abs\/2007.08340 (2020)","DOI":"10.1007\/978-3-030-32254-0_65"},{"key":"43_CR31","unstructured":"Srivastav, V., Issenhuth, T., Kadkhodamohammadi, A., de Mathelin, M., Gangi, A., Padoy, N.: MVOR: a multi-view RGB-D operating room dataset for 2d and 3d human pose estimation. CoRR abs\/1808.08180 (2018)"},{"key":"43_CR32","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: ICML 2008 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"43_CR33","doi-asserted-by":"crossref","unstructured":"Wang, J., Jiao, J., Liu, Y.: Self-supervised video representation learning by pace prediction. CoRR abs\/2008.05861 (2020)","DOI":"10.1007\/978-3-030-58520-4_30"},{"key":"43_CR34","doi-asserted-by":"crossref","unstructured":"Xu, D., Xiao, J., Zhao, Z., Shao, J., Xie, D., Zhuang, Y.: Self-supervised spatiotemporal learning via video clip order prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01058"},{"key":"43_CR35","doi-asserted-by":"crossref","unstructured":"Yao, Y., Liu, C., Luo, D., Zhou, Y., Ye, Q.: Video playback rate perception for self-supervisedspatio-temporal representation learning. CoRR abs\/2006.11476 (2020)","DOI":"10.1109\/CVPR42600.2020.00658"},{"key":"43_CR36","unstructured":"Asano, Y.M., Rupprecht, C., Vedald, A.: Self-labelling via simultaneous clustering and representation learning. In: International Conference on Learning Representations (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_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T20:05:45Z","timestamp":1727985945000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_43","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)"}}]}}