{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,12]],"date-time":"2026-04-12T16:31:35Z","timestamp":1776011495844,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":36,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819984312","type":"print"},{"value":"9789819984329","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8432-9_18","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"221-233","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Autoencoder and\u00a0Masked Image Encoding-Based Attentional Pose Network"],"prefix":"10.1007","author":[{"given":"Longhua","family":"Hu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cheng","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","unstructured":"Joo, H., Neverova, N., Vedaldi, A.: Exemplar fine-tuning for 3D human model fitting towards in-the-wild 3D human pose estimation. In: 2021 International Conference on 3D Vision (3DV), pp. 42\u201352 (2021). https:\/\/doi.org\/10.1109\/3DV53792.2021.00015","DOI":"10.1109\/3DV53792.2021.00015"},{"issue":"07","key":"18_CR2","first-page":"10631","volume":"34","author":"Y Cheng","year":"2020","unstructured":"Cheng, Y., Yang, B., Wang, B., Tan, R.T.: 3D human pose estimation using spatio-temporal networks with explicit occlusion training. Proc. AAAI Conf. Artif. Intell. 34(07), 10631\u201310638 (2020)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"18_CR3","doi-asserted-by":"publisher","unstructured":"Cheng, Y., Yang, B., Wang, B., Wending, Y., Tan, R.: Occlusion-aware networks for 3D human pose estimation in video. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 723\u2013732 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00081","DOI":"10.1109\/ICCV.2019.00081"},{"key":"18_CR4","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2Mesh: graph convolutional network for 3D human pose and mesh recovery from a 2D human pose. arXiv arXiv:2008.09047 (2020)","DOI":"10.1007\/978-3-030-58571-6_45"},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Choutas, V., Pavlakos, G., Bolkart, T., Tzionas, D., Black, M.J.: Monocular expressive body regression through body-driven attention. arXiv arXiv:2008.09062 (2020)","DOI":"10.1007\/978-3-030-58607-2_2"},{"key":"18_CR6","unstructured":"Doersch, C., Zisserman, A.: Sim2real transfer learning for 3D human pose estimation: motion to the rescue. arXiv arXiv:1907.02499 (2019)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Georgakis, G., Li, R., Karanam, S., Chen, T., Kosecka, J., Wu, Z.: Hierarchical kinematic human mesh recovery. arXiv arXiv:2003.04232 (2020)","DOI":"10.1007\/978-3-030-58520-4_45"},{"key":"18_CR8","doi-asserted-by":"publisher","unstructured":"Ghiasi, G., Yang, Y., Ramanan, D., Fowlkes, C.C.: Parsing occluded people. In: 2014 IEEE Conference on Computer Vision and Pattern Recognition, pp. 2401\u20132408 (2014). https:\/\/doi.org\/10.1109\/CVPR.2014.308","DOI":"10.1109\/CVPR.2014.308"},{"key":"18_CR9","doi-asserted-by":"publisher","unstructured":"He, Y., Yan, R., Fragkiadaki, K., Yu, S.I.: Epipolar transformers. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7776\u20137785 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00780","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"18_CR10","unstructured":"Hinton, G.E., Zemel, R.S.: Autoencoders, minimum description length and Helmholtz free energy. In: Neural Information Processing Systems (1993)"},{"key":"18_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"48","DOI":"10.1007\/978-3-642-12307-8_5","volume-title":"Computer Vision \u2013 ACCV 2009","author":"J-B Huang","year":"2010","unstructured":"Huang, J.-B., Yang, M.-H.: Estimating human pose from occluded images. In: Zha, H., Taniguchi, R., Maybank, S. (eds.) ACCV 2009. LNCS, vol. 5994, pp. 48\u201360. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-12307-8_5"},{"key":"18_CR12","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv arXiv:1502.03167 (2015)"},{"key":"18_CR13","doi-asserted-by":"publisher","unstructured":"Kanazawa, A., Black, M.J., Jacobs, D.W., Malik, J.: End-to-end recovery of human shape and pose. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00744","DOI":"10.1109\/CVPR.2018.00744"},{"key":"18_CR14","doi-asserted-by":"publisher","unstructured":"Kanazawa, A., Zhang, J.Y., Felsen, P., Malik, J.: Learning 3D human dynamics from video. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5607\u20135616 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00576","DOI":"10.1109\/CVPR.2019.00576"},{"key":"18_CR15","doi-asserted-by":"publisher","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: VIBE: video inference for human body pose and shape estimation. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5252\u20135262 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00530","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"18_CR16","doi-asserted-by":"publisher","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: PARE: part attention regressor for 3D human body estimation. In: 2021 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 11107\u201311117 (2021). https:\/\/doi.org\/10.1109\/ICCV48922.2021.01094","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"18_CR17","doi-asserted-by":"publisher","unstructured":"Kolotouros, N., Pavlakos, G., Black, M., Daniilidis, K.: Learning to reconstruct 3D human pose and shape via model-fitting in the loop. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 2252\u20132261 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00234","DOI":"10.1109\/ICCV.2019.00234"},{"key":"18_CR18","doi-asserted-by":"publisher","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 4496\u20134505 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00463","DOI":"10.1109\/CVPR.2019.00463"},{"issue":"6","key":"18_CR19","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., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. (TOG) 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"18_CR20","doi-asserted-by":"publisher","unstructured":"Lu, X., Wang, W., Ma, C., Shen, J., Shao, L., Porikli, F.: See more, know more: unsupervised video object segmentation with co-attention siamese networks. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3618\u20133627 (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.00374","DOI":"10.1109\/CVPR.2019.00374"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Luo, Z., Golestaneh, S.A., Kitani, K.M.: 3D human motion estimation via motion compression and refinement. arXiv arXiv:2008.03789 (2020)","DOI":"10.1007\/978-3-030-69541-5_20"},{"key":"18_CR22","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_CR23","doi-asserted-by":"crossref","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. arXiv arXiv:2008.03713 (2020)","DOI":"10.1007\/978-3-030-58571-6_44"},{"key":"18_CR24","unstructured":"Nair, V., Hinton, G.E.: Rectified linear units improve restricted Boltzmann machines. In: International Conference on Machine Learning (2010)"},{"key":"18_CR25","doi-asserted-by":"publisher","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018). https:\/\/doi.org\/10.1109\/CVPR.2018.00055","DOI":"10.1109\/CVPR.2018.00055"},{"key":"18_CR26","doi-asserted-by":"publisher","unstructured":"Rafi, U., Gall, J., Leibe, B.: A semantic occlusion model for human pose estimation from a single depth image. In: 2015 IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 67\u201374 (2015). https:\/\/doi.org\/10.1109\/CVPRW.2015.7301338","DOI":"10.1109\/CVPRW.2015.7301338"},{"key":"18_CR27","doi-asserted-by":"crossref","unstructured":"Rockwell, C., Fouhey, D.F.: Full-body awareness from partial observations. arXiv arXiv:2008.06046 (2020)","DOI":"10.1007\/978-3-030-58520-4_31"},{"key":"18_CR28","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_CR29","doi-asserted-by":"publisher","unstructured":"Sun, Y., Ye, Y., Liu, W., Gao, W., Fu, Y., Mei, T.: Human mesh recovery from monocular images via a skeleton-disentangled representation. In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 5348\u20135357 (2019). https:\/\/doi.org\/10.1109\/ICCV.2019.00545","DOI":"10.1109\/ICCV.2019.00545"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Vincent, P., Larochelle, H., Bengio, Y., Manzagol, P.A.: Extracting and composing robust features with denoising autoencoders. In: Proceedings of the 25th International Conference on Machine Learning, pp. 1096\u20131103 (2008)","DOI":"10.1145\/1390156.1390294"},{"key":"18_CR31","doi-asserted-by":"crossref","unstructured":"Vosoughi, S., Amer, M.A.: Deep 3D human pose estimation under partial body presence. In: International Conference on Image Processing (2018)","DOI":"10.1109\/ICIP.2018.8451031"},{"key":"18_CR32","unstructured":"Wang, J., Xu, E., Xue, K., Kidzinski, L.: 3D pose detection in videos: focusing on occlusion. arXiv arXiv:2006.13517 (2020)"},{"key":"18_CR33","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. arXiv arXiv:1711.07971 (2017)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"18_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"465","DOI":"10.1007\/978-3-030-58539-6_28","volume-title":"Computer Vision \u2013 ECCV 2020","author":"A Zanfir","year":"2020","unstructured":"Zanfir, A., Bazavan, E.G., Xu, H., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: Weakly supervised 3D human pose and shape reconstruction with normalizing flows. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12351, pp. 465\u2013481. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_28"},{"key":"18_CR35","doi-asserted-by":"publisher","unstructured":"Zeiler, M.D., Krishnan, D., Taylor, G.W., Fergus, R.: Deconvolutional networks. In: 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 2528\u20132535 (2010). https:\/\/doi.org\/10.1109\/CVPR.2010.5539957","DOI":"10.1109\/CVPR.2010.5539957"},{"key":"18_CR36","doi-asserted-by":"publisher","unstructured":"Zhang, T., Huang, B., Wang, Y.: Object-occluded human shape and pose estimation from a single color image. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 7374\u20137383 (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00740","DOI":"10.1109\/CVPR42600.2020.00740"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8432-9_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:33:20Z","timestamp":1730921600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":36,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","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":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.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":"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":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}