{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,26]],"date-time":"2026-01-26T19:50:57Z","timestamp":1769457057527,"version":"3.49.0"},"publisher-location":"Cham","reference-count":46,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031204968","type":"print"},{"value":"9783031204975","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.springernature.com\/gp\/researchers\/text-and-data-mining"},{"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.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20497-5_18","type":"book-chapter","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:09:06Z","timestamp":1671192546000},"page":"216-228","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["MHPro: Multi-hypothesis Probabilistic Modeling for\u00a0Human Mesh Recovery"],"prefix":"10.1007","author":[{"given":"Haibiao","family":"Xuan","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kun","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,12,17]]},"reference":[{"key":"18_CR1","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., et al.: Revisiting skeleton-based action recognition. In: CVPR, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"18_CR2","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1007\/s10772-021-09901-4","volume":"25","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Sivaparthipan, C.B., Shankar, A.: Human-computer Interaction Based Visual Feedback System for Augmentative and Alternative Communication. Int. J. Speech Technol. 25, 305\u2013314 (2022). https:\/\/doi.org\/10.1007\/s10772-021-09901-4","journal-title":"Int. J. Speech Technol."},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Weng, C.Y., Curless, B., Kemelmacher-Shlizerman, I.: Photo wake-up: 3D character animation from a single photo. In: CVPR, pp. 5908\u20135917 (2019)","DOI":"10.1109\/CVPR.2019.00606"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Khirodkar, R., Tripathi, S., Kitani, K.: Occluded human mesh recovery. In: CVPR, pp. 1715\u20131725 (2022)","DOI":"10.1109\/CVPR52688.2022.00176"},{"key":"18_CR5","unstructured":"Zheng, C., Wu, W., Yang, T., et al.: Deep learning-based human pose estimation: a survey. ArXiv:2012.13392 (2020)"},{"key":"18_CR6","unstructured":"Tian, Y., Zhang, H., Liu, Y., et al.: Recovering 3D human mesh from monocular images: a survey. ArXiv:2203.01923 (2022)"},{"issue":"6","key":"18_CR7","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., et al.: SMPL: a skinned multi-person linear model. TOG 34(6), 1\u201316 (2015)","journal-title":"TOG"},{"key":"18_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1007\/978-3-319-46454-1_34","volume-title":"Computer Vision \u2013 ECCV 2016","author":"F Bogo","year":"2016","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: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9909, pp. 561\u2013578. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46454-1_34"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Lassner, C., Romero, J., Kiefel, M., et al.: Unite the people: closing the loop between 3D and 2D human representations. In: CVPR, pp. 6050\u20136059 (2017)","DOI":"10.1109\/CVPR.2017.500"},{"key":"18_CR10","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"744","DOI":"10.1007\/978-3-030-58565-5_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Song","year":"2020","unstructured":"Song, J., Chen, X., Hilliges, O.: Human body model fitting by learned gradient descent. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 744\u2013760. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_44"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., et al.: End-to-end recovery of human shape and pose. In: CVPR, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., et al.: Learning to estimate 3D human pose and shape from a single color image. In: CVPR, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Black, M.J., et al.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: ICCV, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: CVPR, pp. 4501\u20134510 (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"18_CR15","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"752","DOI":"10.1007\/978-3-030-58571-6_44","volume-title":"Computer Vision \u2013 ECCV 2020","author":"G Moon","year":"2020","unstructured":"Moon, G., Lee, K.M.: I2L-MeshNet: image-to-lixel prediction network for accurate 3D human pose and mesh estimation from a single RGB image. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 752\u2013768. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_44"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: VIBE: video inference for human body pose and shape estimation. In: CVPR, pp. 5253\u20135263 (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, W., Kolotouros, N., Pavlakos, G., et al.: Coherent reconstruction of multiple humans from a single image. In: CVPR, pp. 5579\u20135588 (2020)","DOI":"10.1109\/CVPR42600.2020.00562"},{"key":"18_CR18","doi-asserted-by":"crossref","unstructured":"Lee, G.H., Lee, S.W.: Uncertainty-aware human mesh recovery from video by learning part-based 3D dynamics. In: ICCV, pp. 12375\u201312384 (2021)","DOI":"10.1109\/ICCV48922.2021.01215"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Zhang, H., Tian, Y., Zhou, X., et al.: PyMAF: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: ICCV, pp. 11446\u201311456 (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Wan, Z., Li, Z., Tian, M., et al.: Encoder-decoder with multi-level attention for 3D human shape and pose estimation. In: ICCV, pp. 13033\u201313042 (2021)","DOI":"10.1109\/ICCV48922.2021.01279"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., et al.: PARE: part attention regressor for 3D human body estimation. In: ICCV, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Li, C., Lee, G.H.: Generating multiple hypotheses for 3D human pose estimation with mixture density network. In: CVPR, pp. 9887\u20139895 (2019)","DOI":"10.1109\/CVPR.2019.01012"},{"key":"18_CR23","unstructured":"Li, C., Lee, G.H.: Weakly supervised generative network for multiple 3D human pose hypotheses. ArXiv:2008.05770 (2020)"},{"key":"18_CR24","unstructured":"Biggs, B., Novotny, D., Ehrhardt, S., et al.: 3D multi-bodies: fitting sets of plausible 3D human models to ambiguous image data. In: NIPS, vol. 33, pp. 20496\u201320507 (2020)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Oikarinen, T., Hannah, D., Kazerounian, S.: GraphMDN: leveraging graph structure and deep learning to solve inverse problems. In: IJCNN, pp. 1\u20139 (2021)","DOI":"10.1109\/IJCNN52387.2021.9534301"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Wehrbein, T., Rudolph, M., Rosenhahn, B., et al.: Probabilistic monocular 3D human pose estimation with normalizing flows. In: ICCV, pp. 11199\u201311208 (2021)","DOI":"10.1109\/ICCV48922.2021.01101"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Jayaraman, D., et al.: Probabilistic modeling for human mesh recovery. In: ICCV, pp. 11605\u201311614 (2021)","DOI":"10.1109\/ICCV48922.2021.01140"},{"key":"18_CR28","doi-asserted-by":"crossref","unstructured":"Sengupta, A., Budvytis, I., Cipolla, R.: Hierarchical kinematic probability distributions for 3D human shape and pose estimation from images in the wild. In: ICCV, pp. 11219\u201311229 (2021)","DOI":"10.1109\/ICCV48922.2021.01103"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., et al.: MHFormer: multi-hypothesis transformer for 3D human pose estimation. ArXiv:2111.12707 (2021)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"18_CR30","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: NIPS, vol. 30 (2017)"},{"key":"18_CR31","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., et al.: An image is worth $$16\\times 16$$ words: transformers for image recognition at scale. ArXiv:2010.11929 (2020)"},{"key":"18_CR32","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: CVPR, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"18_CR33","unstructured":"Jiang, Y., Chang, S., Wang, Z.: TransGAN: two pure transformers can make one strong GAN, and that can scale up. In: NIPS, vol. 34 (2021)"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Chen, H., Wang, Y., Guo, T., et al.: Pre-trained image processing transformer. In: CVPR, pp. 12299\u201312310 (2021)","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Dai, Z., Cai, B., Lin, Y., et al.: UP-DETR: unsupervised pre-training for object detection with transformers. In: CVPR, pp. 1601\u20131610 (2021)","DOI":"10.1109\/CVPR46437.2021.00165"},{"key":"18_CR36","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1007\/978-3-030-58517-4_31","volume-title":"Computer Vision \u2013 ECCV 2020","author":"Y Zeng","year":"2020","unstructured":"Zeng, Y., Fu, J., Chao, H.: Learning joint spatial-temporal transformations for video inpainting. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 528\u2013543. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_31"},{"key":"18_CR37","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., et al.: On the continuity of rotation representations in neural networks. In: CVPR, pp. 5745\u20135753 (2019)","DOI":"10.1109\/CVPR.2019.00589"},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: ICCV, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"18_CR39","doi-asserted-by":"crossref","unstructured":"Wei, X., Zhang, T., Li, Y., et al.: Multi-modality cross attention network for image and sentence matching. In: CVPR, pp. 10941\u201310950 (2020)","DOI":"10.1109\/CVPR42600.2020.01095"},{"key":"18_CR40","unstructured":"Hou, R., Chang, H., Ma, B., et al.: Cross attention network for few-shot classification. In: NIPS, vol. 32 (2019)"},{"issue":"7","key":"18_CR41","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","unstructured":"Ionescu, C., Papava, D., Olaru, V., et al.: Human3.6M: large scale datasets and predictive methods for 3D human sensing in natural environments. TPAMI 36(7), 1325\u20131339 (2013)","journal-title":"TPAMI"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: 3DV, pp. 506\u2013516 (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"18_CR43","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"614","DOI":"10.1007\/978-3-030-01249-6_37","volume-title":"Computer Vision \u2013 ECCV 2018","author":"T von Marcard","year":"2018","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: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11214, pp. 614\u2013631. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01249-6_37"},{"key":"18_CR44","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":"T-Y 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":"18_CR45","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., et al.: 2D human pose estimation: new benchmark and state of the art analysis. In: CVPR, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"18_CR46","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol. 2, no. 4, p. 5 (2010)","DOI":"10.5244\/C.24.12"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20497-5_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T12:16:28Z","timestamp":1671192988000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20497-5_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031204968","9783031204975"],"references-count":46,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20497-5_18","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 December 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"27 August 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.cn\/#\/","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"472","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":"164","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":"35% - 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":"3.1","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":"3.7","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)"}}]}}