{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,28]],"date-time":"2025-03-28T07:05:35Z","timestamp":1743145535445,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031500688"},{"type":"electronic","value":"9783031500695"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-3-031-50069-5_39","type":"book-chapter","created":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:02:34Z","timestamp":1705644154000},"page":"476-488","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MANet: Multi-level Attention Network for\u00a03D Human Shape and\u00a0Pose Estimation"],"prefix":"10.1007","author":[{"given":"Chenhao","family":"Yao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guiqing","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juncheng","family":"Zeng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongwei","family":"Nie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuhua","family":"Xian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,1,20]]},"reference":[{"key":"39_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"39_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: Proceedings of the European Conference on Computer Vision, pp. 561\u2013578 (2016)","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"39_CR3","doi-asserted-by":"crossref","unstructured":"Cho, J., Yoon, Y., Kwak, S.: Collaborative transformers for grounded situation recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 19659\u201319668 (2022)","DOI":"10.1109\/CVPR52688.2022.01904"},{"key":"39_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"342","DOI":"10.1007\/978-3-031-19769-7_20","volume-title":"Computer Vision - ECCV 2022","author":"J Cho","year":"2022","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3D human mesh recovery with transformers. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022, Part I. LNCS, vol. 13661, pp. 342\u2013359. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19769-7_20"},{"key":"39_CR5","doi-asserted-by":"crossref","unstructured":"Choi, H., Moon, G., Chang, J.Y., Lee, K.M.: Beyond static features for temporally consistent 3D human pose and shape from a video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1964\u20131973 (2021)","DOI":"10.1109\/CVPR46437.2021.00200"},{"key":"39_CR6","doi-asserted-by":"crossref","unstructured":"Diaz-Arias, A., Shin, D.: Convformer: parameter reduction in transformer models for 3D human pose estimation by leveraging dynamic multi-headed convolutional attention. arXiv preprint arXiv:2304.02147 (2023)","DOI":"10.1007\/s00371-023-02936-5"},{"key":"39_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"39_CR8","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3. 6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"39_CR9","doi-asserted-by":"crossref","unstructured":"Johnson, S., Everingham, M.: Learning effective human pose estimation from inaccurate annotation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1465\u20131472 (2011)","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"39_CR10","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: International Conference on 3D Vision (2020)","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"39_CR11","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: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7122\u20137131 (2018)","DOI":"10.1109\/CVPR.2018.00744"},{"key":"39_CR12","doi-asserted-by":"crossref","unstructured":"Kato, H., Ushiku, Y., Harada, T.: Neural 3D mesh renderer. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2018)","DOI":"10.1109\/CVPR.2018.00411"},{"key":"39_CR13","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Athanasiou, N., Black, M.J.: Vibe: Video inference for human body pose and shape estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263 (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"39_CR14","doi-asserted-by":"crossref","unstructured":"Kocabas, M., Huang, C.H.P., Hilliges, O., Black, M.J.: Pare: part attention regressor for 3D human body estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 11127\u201311137 (2021)","DOI":"10.1109\/ICCV48922.2021.01094"},{"key":"39_CR15","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: Proceedings of the IEEE International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"39_CR16","doi-asserted-by":"publisher","first-page":"2855","DOI":"10.1007\/s00371-021-02236-w","volume":"37","author":"L Li","year":"2021","unstructured":"Li, L., Tang, J., Ye, Z., Sheng, B., Mao, L., Ma, L.: Unsupervised face super-resolution via gradient enhancement and semantic guidance. Vis. Comput. 37, 2855\u20132867 (2021)","journal-title":"Vis. Comput."},{"key":"39_CR17","doi-asserted-by":"crossref","unstructured":"Li, Z., Liu, J., Zhang, Z., Xu, S., Yan, Y.: Cliff: carrying location information in full frames into human pose and shape estimation. arXiv preprint arXiv:2208.00571 (2022)","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"39_CR18","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: End-to-end human pose and mesh reconstruction with transformers. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"39_CR19","doi-asserted-by":"crossref","unstructured":"Lin, K., Wang, L., Liu, Z.: Mesh graphormer. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 12939\u201312948 (2021)","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"39_CR20","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":"39_CR21","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2023","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: EAPT: efficient attention pyramid transformer for image processing. IEEE Trans. Multimedia 25, 50\u201361 (2023). https:\/\/doi.org\/10.1109\/TMM.2021.3120873","journal-title":"IEEE Trans. Multimedia"},{"issue":"6","key":"39_CR22","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. 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph."},{"key":"39_CR23","doi-asserted-by":"crossref","unstructured":"Mehta, D., et al.: Monocular 3D human pose estimation in the wild using improved CNN supervision. In: International Conference on 3D Vision, pp. 506\u2013516 (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"39_CR24","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":"39_CR25","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhu, L., Zhou, X., Daniilidis, K.: Learning to estimate 3D human pose and shape from a single color image. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 459\u2013468 (2018)","DOI":"10.1109\/CVPR.2018.00055"},{"key":"39_CR26","doi-asserted-by":"crossref","unstructured":"Sun, K., Xiao, B., Liu, D., Wang, J.: Deep high-resolution representation learning for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"39_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"39_CR28","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":"39_CR29","doi-asserted-by":"crossref","unstructured":"Wan, Z., Li, Z., Tian, M., Liu, J., Yi, S., Li, H.: Encoder-decoder with multi-level attention for 3D human shape and pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 13033\u201313042 (2021)","DOI":"10.1109\/ICCV48922.2021.01279"},{"key":"39_CR30","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhang, G., Yang, J.: 3D human pose and shape estimation with dense correspondence from a single depth image. Vis. Comput. 1\u201313 (2023)","DOI":"10.1007\/s00371-021-02339-4"},{"key":"39_CR31","unstructured":"Wang, Q., et al.: Learning deep transformer models for machine translation. arXiv preprint arXiv:1906.01787 (2019)"},{"key":"39_CR32","doi-asserted-by":"crossref","unstructured":"Zhang, H., et al.: Pymaf: 3D human pose and shape regression with pyramidal mesh alignment feedback loop. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 11446\u201311456 (2021)","DOI":"10.1109\/ICCV48922.2021.01125"},{"issue":"4","key":"39_CR33","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","volume":"41","author":"X Zhou","year":"2019","unstructured":"Zhou, X., Zhu, M., Pavlakos, G., Leonardos, S., Derpanis, K.G., Daniilidis, K.: MonoCap: monocular human motion capture using a CNN coupled with a geometric prior. IEEE Trans. Pattern Anal. Mach. Intell. 41(4), 901\u2013914 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."}],"container-title":["Lecture Notes in Computer Science","Advances in Computer Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-50069-5_39","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,19]],"date-time":"2024-01-19T06:08:58Z","timestamp":1705644538000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-50069-5_39"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031500688","9783031500695"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-50069-5_39","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"20 January 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CGI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Computer Graphics International Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shanghai","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":"28 August 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cgi2023","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"385","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":"149","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":"39% - 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":"3","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)"}}]}}