{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,22]],"date-time":"2026-10-22T13:36:05Z","timestamp":1792676165993,"version":"4.5.0"},"publisher-location":"Cham","reference-count":39,"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_12","type":"book-chapter","created":{"date-parts":[[2022,9,16]],"date-time":"2022-09-16T08:04:54Z","timestamp":1663315494000},"page":"115-125","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Self-supervised 3D Patient Modeling with\u00a0Multi-modal Attentive Fusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6677-2017","authenticated-orcid":false,"given":"Meng","family":"Zheng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6110-6437","authenticated-orcid":false,"given":"Benjamin","family":"Planche","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8303-633X","authenticated-orcid":false,"given":"Xuan","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1535-447X","authenticated-orcid":false,"given":"Fan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Terrence","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9774-7770","authenticated-orcid":false,"given":"Ziyan","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,9,17]]},"reference":[{"key":"12_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., et al.: PoseTrack: a benchmark for human pose estimation and tracking. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00542"},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Bogo, F., Kanazawa, A., Lassner, C., Gehler, P., Romero, J., Black, M.J.: Keep it SMPL: automatic estimation of 3D human pose and shape from a single image. In: ECCV (2016)","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1007\/s00330-020-07097-w","volume":"31","author":"R Booij","year":"2021","unstructured":"Booij, R., van Straten, M., Wimmer, A., Budde, R.P.: Automated patient positioning in CT using a 3D camera for body contour detection: accuracy in pediatric patients. Eur. Radiol. 31, 131\u2013138 (2021)","journal-title":"Eur. Radiol."},{"key":"12_CR4","unstructured":"Cao, Z., Martinez, G.H., Simon, T., Wei, S., Sheikh, Y.A.: OpenPose: realtime multi-person 2D pose estimation using part affinity fields. IEEE Trans. Patt. Anal. Mach. Intell. (2019)"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Chen, X., He, K.: Exploring simple Siamese representation learning. CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Ching, W., Robinson, J., McEntee, M.: Patient-based radiographic exposure factor selection: a systematic review. J. Med. Radiat. Sci. 61(3), 176\u2013190 (2014)","DOI":"10.1002\/jmrs.66"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Clever, H.M., Erickson, Z., Kapusta, A., Turk, G., Liu, K., Kemp, C.C.: Bodies at rest: 3D human pose and shape estimation from a pressure image using synthetic data. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00625"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Dang, Q., Yin, J., Wang, B., Zheng, W.: Deep learning based 2D human pose estimation: a survey. Tsinghua Sci. Technol. 24(6), 663\u2013676 (2019)","DOI":"10.26599\/TST.2018.9010100"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"Georgakis, G., Li, R., Karanam, S., Chen, T., Ko\u0161eck\u00e1, J., Wu, Z.: Hierarchical kinematic human mesh recovery. In: ECCV (2020)","DOI":"10.1007\/978-3-030-58520-4_45"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"He, K., Gkioxari, G., Doll\u00e1r, P., Girshick, R.: Mask R-CNN. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.322"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"12_CR12","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC (2010)","DOI":"10.5244\/C.24.12"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human pose fitting towards in-the-wild 3D human pose estimation. In: 3DV (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"Kadkhodamohammadi, A., Gangi, A., de Mathelin, M., Padoy, N.: Articulated clinician detection using 3D pictorial structures on RGB-D data. Med. Image Anal. 35, 215\u2013224 (2017)","DOI":"10.1016\/j.media.2016.07.001"},{"key":"12_CR15","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. In: WACV (2017)","DOI":"10.1109\/WACV.2017.47"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Karanam, S., Li, R., Yang, F., Hu, W., Chen, T., Wu, Z.: Towards contactless patient positioning. IEEE Trans. Med. Imaging 39(8), 2701\u20132710 (2020)","DOI":"10.1109\/TMI.2020.2991954"},{"key":"12_CR18","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"12_CR19","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"12_CR20","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., Bogo, F., Black, M.J., Gehler, P.V.: Unite the people: closing the loop between 3D and 2D human representations. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"12_CR21","doi-asserted-by":"crossref","unstructured":"Li, J., Udayasankar, U.K., Toth, T.L., Seamans, J., Small, W.C., Kalra, M.K.: Automatic patient centering for MDCT: effect on radiation dose. Am. J. Roentgenol. 188(2), 547\u2013552 (2007)","DOI":"10.2214\/AJR.06.0370"},{"key":"12_CR22","doi-asserted-by":"crossref","unstructured":"Lin, T., Maire, M., Belongie, S., et al.: Microsoft COCO: common objects in context. In: ECCV (2014)","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"12_CR23","doi-asserted-by":"crossref","unstructured":"Liu, C., Hu, Y., Li, Y., Song, S., Liu, J.: PKU-MMD: a large scale benchmark for continuous multi-modal human action understanding. arXiv:1703.07475 (2017)","DOI":"10.1145\/3132734.3132739"},{"key":"12_CR24","doi-asserted-by":"crossref","unstructured":"Liu, S., Ostadabbas, S.: Seeing under the cover: a physics guided learning approach for in-bed pose estimation. In: MICCAI (2019)","DOI":"10.1007\/978-3-030-32239-7_27"},{"key":"12_CR25","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Black, M.J.: MoSh: motion and shape capture from sparse markers. ACM Trans. Graph. 33(6), 1\u201313 (2014)","DOI":"10.1145\/2661229.2661273"},{"key":"12_CR26","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6) (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"12_CR27","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: AMASS: archive of motion capture as surface shapes. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"12_CR28","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"12_CR29","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., et al.: DeepCut: joint subset partition and labeling for multi person pose estimation. In: CVPR, June 2016","DOI":"10.1109\/CVPR.2016.533"},{"key":"12_CR30","unstructured":"Sengupta, A., Budvytis, I., Cipolla, R.: Synthetic training for accurate 3D human pose and shape estimation in the wild. In: BMVC (2020)"},{"key":"12_CR31","unstructured":"Shotton, J., Glocker, B., Zach, C., Izadi, S., Criminisi, A., Fitzgibbon, A.: Clustered pose and nonlinear appearance models for human pose estimation. In: CVPR (2013)"},{"key":"12_CR32","doi-asserted-by":"crossref","unstructured":"Singh, V., Ma, K., Tamersoy, B., et al.: DARWIN: deformable patient avatar representation with deep image network. In: MICCAI (2017)","DOI":"10.1007\/978-3-319-66185-8_56"},{"key":"12_CR33","doi-asserted-by":"crossref","unstructured":"Song, S., Lichtenberg, S.P., Xiao, J.: SUN RGB-D: A RGB-D scene understanding benchmark suite. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298655"},{"key":"12_CR34","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 (2018)"},{"key":"12_CR35","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"12_CR36","unstructured":"Sung, J., Ponce, C., Selman, B., Saxena, A.: Unstructured human activity detection from RGBD images. In: ICRA (2012)"},{"key":"12_CR37","doi-asserted-by":"crossref","unstructured":"Von Marcard, T., Henschel, R., Black, M.J., Rosenhahn, B., Pons-Moll, G.: Recovering accurate 3D human pose in the wild using IMUs and a moving camera. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"12_CR38","doi-asserted-by":"crossref","unstructured":"Yang, F., et al.: Robust multi-modal 3D patient body modeling. In: MICCAI (2020)","DOI":"10.1007\/978-3-030-59716-0_9"},{"key":"12_CR39","unstructured":"Yin, Y., Robinson, J.P., Fu, Y.: Multimodal in-bed pose and shape estimation under the blankets. In: ArXiv:2012.06735 (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_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T16:53:36Z","timestamp":1709830416000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16449-1_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031164484","9783031164491"],"references-count":39,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16449-1_12","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)"}}]}}