{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T14:28:51Z","timestamp":1742999331880,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819785070"},{"type":"electronic","value":"9789819785087"}],"license":[{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,3]],"date-time":"2024-11-03T00:00:00Z","timestamp":1730592000000},"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":[[2025]]},"DOI":"10.1007\/978-981-97-8508-7_41","type":"book-chapter","created":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:10:25Z","timestamp":1730527825000},"page":"593-605","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal Token Fusion and\u00a0Optimization for\u00a03D Human Mesh Reconstruction with\u00a0Transformers"],"prefix":"10.1007","author":[{"given":"Yang","family":"Jiang","sequence":"first","affiliation":[]},{"given":"Sunli","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingyang","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Dongliang","family":"Kou","sequence":"additional","affiliation":[]},{"given":"Qiangbin","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Lihuang","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,3]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Cho, J., Youwang, K., Oh, T.H.: Cross-attention of disentangled modalities for 3d human mesh recovery with transformers. In: European Conference on Computer Vision, pp. 342\u2013359. Springer (2022)","DOI":"10.1007\/978-3-031-19769-7_20"},{"key":"41_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1007\/978-3-030-58571-6_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"H Choi","year":"2020","unstructured":"Choi, H., Moon, G., Lee, K.M.: Pose2Mesh: Graph Convolutional Network for 3D Human Pose and Mesh Recovery from a 2D Human Pose. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12352, pp. 769\u2013787. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58571-6_45"},{"key":"41_CR3","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1007\/BF02291478","volume":"40","author":"JC Gower","year":"1975","unstructured":"Gower, J.C.: Generalized procrustes analysis. Psychometrika 40, 33\u201351 (1975)","journal-title":"Psychometrika"},{"issue":"4","key":"41_CR4","first-page":"733","volume":"9","author":"MH Guo","year":"2023","unstructured":"Guo, M.H., Lu, C.Z., Liu, Z.N., Cheng, M.M., Hu, S.M.: Visual attention network. Comput. Vis. Media 9(4), 733\u2013752 (2023)","journal-title":"Media"},{"key":"41_CR5","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":"41_CR6","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":"41_CR7","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":"41_CR8","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5253\u20135263 (2020)","DOI":"10.1109\/CVPR42600.2020.00530"},{"key":"41_CR9","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\/CVF International Conference on Computer Vision, pp. 2252\u20132261 (2019)","DOI":"10.1109\/ICCV.2019.00234"},{"key":"41_CR10","doi-asserted-by":"crossref","unstructured":"Kolotouros, N., Pavlakos, G., Daniilidis, K.: Convolutional mesh regression for single-image human shape reconstruction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4501\u20134510 (2019)","DOI":"10.1109\/CVPR.2019.00463"},{"key":"41_CR11","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. In: European Conference on Computer Vision, pp. 590\u2013606. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_34"},{"key":"41_CR12","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1954\u20131963 (2021)","DOI":"10.1109\/CVPR46437.2021.00199"},{"key":"41_CR13","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., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: 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":"41_CR14","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: A skinned multi-person linear model. In: Seminal Graphics Papers: Pushing the Boundaries, vol. 2, pp. 851\u2013866 (2023)","DOI":"10.1145\/3596711.3596800"},{"key":"41_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":"41_CR16","doi-asserted-by":"crossref","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: A sparse trained articulated human body regressor. In: European Conference on Computer Vision (ECCV), pp. 598\u2013613 (2020). https:\/\/star.is.tue.mpg.de","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Choutas, V., Ghorbani, N., Bolkart, T., Osman, A.A., Tzionas, D., Black, M.J.: Expressive body capture: 3d hands, face, and body from a single image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10975\u201310985 (2019)","DOI":"10.1109\/CVPR.2019.01123"},{"key":"41_CR18","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":"41_CR19","doi-asserted-by":"crossref","unstructured":"Saito, S., Huang, Z., Natsume, R., Morishima, S., Kanazawa, A., Li, H.: Pifu: Pixel-aligned implicit function for high-resolution clothed human digitization. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2304\u20132314 (2019)","DOI":"10.1109\/ICCV.2019.00239"},{"key":"41_CR20","doi-asserted-by":"crossref","unstructured":"Saito, S., Simon, T., Saragih, J., Joo, H.: Pifuhd: Multi-level pixel-aligned implicit function for high-resolution 3d human digitization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 84\u201393 (2020)","DOI":"10.1109\/CVPR42600.2020.00016"},{"key":"41_CR21","unstructured":"Sun, K., Zhao, Y., Jiang, B., Cheng, T., Xiao, B., Liu, D., Mu, Y., Wang, X., Liu, W., Wang, J.: High-resolution representations for labeling pixels and regions (2019)"},{"key":"41_CR22","doi-asserted-by":"crossref","unstructured":"Von\u00a0Marcard, 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: Proceedings of the European Conference on Computer Vision (ECCV), pp. 601\u2013617 (2018)","DOI":"10.1007\/978-3-030-01249-6_37"},{"issue":"1","key":"41_CR23","doi-asserted-by":"publisher","first-page":"104","DOI":"10.1109\/TCSVT.2022.3199201","volume":"33","author":"L Wang","year":"2022","unstructured":"Wang, L., Liu, X., Ma, X., Wu, J., Cheng, J., Zhou, M.: A progressive quadric graph convolutional network for 3d human mesh recovery. IEEE Trans. Circuits Syst. Video Technol. 33(1), 104\u2013117 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"41_CR24","doi-asserted-by":"crossref","unstructured":"Xiu, Y., Yang, J., Tzionas, D., Black, M.J.: Icon: Implicit clothed humans obtained from normals. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13286\u201313296. IEEE (2022)","DOI":"10.1109\/CVPR52688.2022.01294"},{"issue":"6","key":"41_CR25","doi-asserted-by":"publisher","first-page":"3170","DOI":"10.1109\/TPAMI.2021.3050505","volume":"44","author":"Z Zheng","year":"2021","unstructured":"Zheng, Z., Yu, T., Liu, Y., Dai, Q.: Pamir: Parametric model-conditioned implicit representation for image-based human reconstruction. IEEE Trans. Pattern Anal. Mach. Intell. 44(6), 3170\u20133184 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"41_CR26","doi-asserted-by":"publisher","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","volume":"41","author":"X Zhou","year":"2018","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 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: Freihand: A dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 813\u2013822 (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"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\/978-981-97-8508-7_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,2]],"date-time":"2024-11-02T06:20:01Z","timestamp":1730528401000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-8508-7_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,3]]},"ISBN":["9789819785070","9789819785087"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-8508-7_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,3]]},"assertion":[{"value":"3 November 2024","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":"Urumqi","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2024.prcv.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}