{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T04:18:45Z","timestamp":1783052325972,"version":"3.54.6"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013804","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013804","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1016\/j.jvcir.2026.104881","type":"journal-article","created":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T15:22:03Z","timestamp":1782400923000},"page":"104881","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["3D human pose estimation based on multi-view feature fusion and dynamic voxelization"],"prefix":"10.1016","volume":"119","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6210-2534","authenticated-orcid":false,"given":"Lianping","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohui","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3028-4378","authenticated-orcid":false,"given":"Yuanyuan","family":"Ai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wuming","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"01","key":"10.1016\/j.jvcir.2026.104881_b1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1142\/S0219622019300052","article-title":"A review on human-computer interaction and intelligent robots","volume":"19","author":"Ren","year":"2020","journal-title":"Int. J. Inf. Technol. Decis. Mak."},{"issue":"10","key":"10.1016\/j.jvcir.2026.104881_b2","doi-asserted-by":"crossref","first-page":"3343","DOI":"10.1016\/j.patcog.2014.04.018","article-title":"A survey on still image based human action recognition","volume":"47","author":"Guo","year":"2014","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104881_b3","series-title":"CVPR 2011","first-page":"1961","article-title":"From 3d scene geometry to human workspace","author":"Gupta","year":"2011"},{"key":"10.1016\/j.jvcir.2026.104881_b4","doi-asserted-by":"crossref","unstructured":"R. Urtasun, T. Darrell, Local probabilistic regression foractivity-independent human pose inference, in: Proc. CVPR, Vol. 1, 2008.","DOI":"10.1109\/CVPR.2008.4587360"},{"key":"10.1016\/j.jvcir.2026.104881_b5","series-title":"2009 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1014","article-title":"Pictorial structures revisited: People detection and articulated pose estimation","author":"Andriluka","year":"2009"},{"key":"10.1016\/j.jvcir.2026.104881_b6","series-title":"2011 International Conference on Computer Vision","first-page":"2220","article-title":"Latent structured models for human pose estimation","author":"Ionescu","year":"2011"},{"key":"10.1016\/j.jvcir.2026.104881_b7","series-title":"Skinned multi-person linear model","author":"Black","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104881_b8","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part V 14","first-page":"561","article-title":"Keep it SMPL: Automatic estimation of 3D human pose and shape from a single image","author":"Bogo","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104881_b9","series-title":"Indirect deep structured learning for 3d human body shape and pose prediction","author":"Tan","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104881_b10","article-title":"Self-supervised learning of motion capture","volume":"30","author":"Tung","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104881_b11","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, L. Zhu, X. Zhou, K. Daniilidis, 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, 2018, pp. 459\u2013468.","DOI":"10.1109\/CVPR.2018.00055"},{"key":"10.1016\/j.jvcir.2026.104881_b12","series-title":"2018 International Conference on 3D Vision","first-page":"484","article-title":"Neural body fitting: Unifying deep learning and model based human pose and shape estimation","author":"Omran","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104881_b13","series-title":"2017 International Conference on 3D Vision","first-page":"506","article-title":"Monocular 3d human pose estimation in the wild using improved cnn supervision","author":"Mehta","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104881_b14","series-title":"2017 IEEE International Conference on Computer Vision","first-page":"3467","article-title":"Monocular 3d human pose estimation by predicting depth on joints","author":"Nie","year":"2017"},{"key":"10.1016\/j.jvcir.2026.104881_b15","series-title":"Computer Vision\u2013ECCV 2016 Workshops: Amsterdam, the Netherlands, October 8-10 and 15-16, 2016, Proceedings, Part III 14","first-page":"186","article-title":"Deep kinematic pose regression","author":"Zhou","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104881_b16","doi-asserted-by":"crossref","unstructured":"D. Pavllo, C. Feichtenhofer, D. Grangier, M. Auli, 3d human pose estimation in video with temporal convolutions and semi-supervised training, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 7753\u20137762.","DOI":"10.1109\/CVPR.2019.00794"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104881_b17","doi-asserted-by":"crossref","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","article-title":"Anatomy-aware 3d human pose estimation with bone-based pose decomposition","volume":"32","author":"Chen","year":"2021","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2026.104881_b18","doi-asserted-by":"crossref","unstructured":"R. Liu, J. Shen, H. Wang, C. Chen, S.-c. Cheung, V. Asari, Attention mechanism exploits temporal contexts: Real-time 3d human pose reconstruction, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 5064\u20135073.","DOI":"10.1109\/CVPR42600.2020.00511"},{"key":"10.1016\/j.jvcir.2026.104881_b19","doi-asserted-by":"crossref","unstructured":"C. Zheng, S. Zhu, M. Mendieta, T. Yang, C. Chen, Z. Ding, 3d human pose estimation with spatial and temporal transformers, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11656\u201311665.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"10.1016\/j.jvcir.2026.104881_b20","doi-asserted-by":"crossref","unstructured":"Q. Zhao, C. Zheng, M. Liu, P. Wang, C. Chen, PoseFormerV2: Exploring Frequency Domain for Efficient and Robust 3D Human Pose Estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 8877\u20138886.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"10.1016\/j.jvcir.2026.104881_b21","series-title":"Graformer: Graph convolution transformer for 3d pose estimation","author":"Zhao","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104881_b22","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.jvcir.2026.104881_b23","doi-asserted-by":"crossref","unstructured":"Y. He, R. Yan, K. Fragkiadaki, S.-I. Yu, Epipolar transformers, in: Proceedings of the Ieee\/Cvf Conference on Computer Vision and Pattern Recognition, 2020, pp. 7779\u20137788.","DOI":"10.1109\/CVPR42600.2020.00780"},{"key":"10.1016\/j.jvcir.2026.104881_b24","doi-asserted-by":"crossref","unstructured":"G. Moon, J.Y. Chang, K.M. Lee, V2v-posenet: Voxel-to-voxel prediction network for accurate 3d hand and human pose estimation from a single depth map, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 5079\u20135088.","DOI":"10.1109\/CVPR.2018.00533"},{"key":"10.1016\/j.jvcir.2026.104881_b25","series-title":"Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, the Netherlands, October 11-14, 2016, Proceedings, Part VIII 14","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"Newell","year":"2016"},{"key":"10.1016\/j.jvcir.2026.104881_b26","doi-asserted-by":"crossref","unstructured":"H. Qiu, C. Wang, J. Wang, N. Wang, W. Zeng, Cross view fusion for 3d human pose estimation, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 4342\u20134351.","DOI":"10.1109\/ICCV.2019.00444"},{"key":"10.1016\/j.jvcir.2026.104881_b27","doi-asserted-by":"crossref","unstructured":"K. Sun, B. Xiao, D. Liu, J. Wang, Deep high-resolution representation learning for human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2019, pp. 5693\u20135703.","DOI":"10.1109\/CVPR.2019.00584"},{"key":"10.1016\/j.jvcir.2026.104881_b28","series-title":"Transfusion: Cross-view fusion with transformer for 3d human pose estimation","author":"Ma","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104881_b29","doi-asserted-by":"crossref","first-page":"703","DOI":"10.1007\/s11263-020-01398-9","article-title":"Adafuse: Adaptive multiview fusion for accurate human pose estimation in the wild","volume":"129","author":"Zhang","year":"2021","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104881_b30","doi-asserted-by":"crossref","unstructured":"K. Iskakov, E. Burkov, V. Lempitsky, Y. Malkov, Learnable triangulation of human pose, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2019, pp. 7718\u20137727.","DOI":"10.1109\/ICCV.2019.00781"},{"key":"10.1016\/j.jvcir.2026.104881_b31","series-title":"View consistency aware holistic triangulation for 3D human pose estimation","author":"Wan","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104881_b32","series-title":"Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part I 16","first-page":"197","article-title":"Voxelpose: Towards multi-camera 3d human pose estimation in wild environment","author":"Tu","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104881_b33","doi-asserted-by":"crossref","unstructured":"S. Wu, S. Jin, W. Liu, L. Bai, C. Qian, D. Liu, W. Ouyang, Graph-based 3d multi-person pose estimation using multi-view images, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11148\u201311157.","DOI":"10.1109\/ICCV48922.2021.01096"},{"key":"10.1016\/j.jvcir.2026.104881_b34","doi-asserted-by":"crossref","unstructured":"J. Hu, L. Shen, G. Sun, Squeeze-and-excitation networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7132\u20137141.","DOI":"10.1109\/CVPR.2018.00745"},{"key":"10.1016\/j.jvcir.2026.104881_b35","article-title":"Spatial transformer networks","volume":"28","author":"Jaderberg","year":"2015","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104881_b36","doi-asserted-by":"crossref","unstructured":"X. Wang, R. Girshick, A. Gupta, K. He, Non-local neural networks, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"10.1016\/j.jvcir.2026.104881_b37","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104881_b38","series-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104881_b39","doi-asserted-by":"crossref","unstructured":"K. Gu, L. Yang, A. Yao, Removing the bias of integral pose regression, in: Proceedings of the IEEE\/CVF International Conference on Computer Vision, 2021, pp. 11067\u201311076.","DOI":"10.1109\/ICCV48922.2021.01088"},{"key":"10.1016\/j.jvcir.2026.104881_b40","series-title":"Multiple View Geometry in Computer Vision","author":"Hartley","year":"2003"},{"issue":"7","key":"10.1016\/j.jvcir.2026.104881_b41","doi-asserted-by":"crossref","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","article-title":"Human3. 6m: Large scale datasets and predictive methods for 3d human sensing in natural environments","volume":"36","author":"Ionescu","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2026.104881_b42","doi-asserted-by":"crossref","unstructured":"J. Martinez, R. Hossain, J. Romero, J.J. Little, A simple yet effective baseline for 3d human pose estimation, in: Proceedings of the IEEE International Conference on Computer Vision, 2017, pp. 2640\u20132649.","DOI":"10.1109\/ICCV.2017.288"},{"key":"10.1016\/j.jvcir.2026.104881_b43","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K.G. Derpanis, K. Daniilidis, Harvesting multiple views for marker-less 3d human pose annotations, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 6988\u20136997.","DOI":"10.1109\/CVPR.2017.138"},{"key":"10.1016\/j.jvcir.2026.104881_b44","series-title":"2018 International Conference on 3D Vision","first-page":"474","article-title":"Rethinking pose in 3d: Multi-stage refinement and recovery for markerless motion capture","author":"Tome","year":"2018"},{"key":"10.1016\/j.jvcir.2026.104881_b45","doi-asserted-by":"crossref","unstructured":"R. Xie, C. Wang, Y. Wang, Metafuse: A pre-trained fusion model for human pose estimation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 13686\u201313695.","DOI":"10.1109\/CVPR42600.2020.01370"},{"issue":"3","key":"10.1016\/j.jvcir.2026.104881_b46","doi-asserted-by":"crossref","first-page":"869","DOI":"10.1007\/s11263-021-01570-9","article-title":"Consensus-based optimization for 3D human pose estimation in camera coordinates","volume":"130","author":"Luvizon","year":"2022","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104881_b47","doi-asserted-by":"crossref","unstructured":"K. Bartol, D. Bojani\u0107, T. Petkovi\u0107, T. Pribani\u0107, Generalizable Human Pose Triangulation, in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 11028\u201311037.","DOI":"10.1109\/CVPR52688.2022.01075"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001768?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001768?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T03:44:06Z","timestamp":1783050246000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001768"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":47,"alternative-id":["S1047320326001768"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104881","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,8]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"3D human pose estimation based on multi-view feature fusion and dynamic voxelization","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104881","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Inc. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"104881"}}