{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T02:17:41Z","timestamp":1783131461396,"version":"3.54.6"},"reference-count":57,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T00:00:00Z","timestamp":1780272000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T00:00:00Z","timestamp":1777420800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100021133","name":"CY Cergy Paris University","doi-asserted-by":"publisher","award":["EUTOPIA-PhD-2021-0000000061"],"award-info":[{"award-number":["EUTOPIA-PhD-2021-0000000061"]}],"id":[{"id":"10.13039\/100021133","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100000780","name":"European Commission","doi-asserted-by":"publisher","award":["EUTOPIA-PhD-2021-0000000061"],"award-info":[{"award-number":["EUTOPIA-PhD-2021-0000000061"]}],"id":[{"id":"10.13039\/501100000780","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":[[2026,6]]},"DOI":"10.1016\/j.jvcir.2026.104829","type":"journal-article","created":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T20:13:09Z","timestamp":1777579989000},"page":"104829","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ADGT: Enhancing 3D human pose estimation with attention-driven graph-transformers"],"prefix":"10.1016","volume":"118","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5849-1889","authenticated-orcid":false,"given":"Shuo","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6062-207X","authenticated-orcid":false,"given":"Anh Tuan","family":"Luu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2776-2254","authenticated-orcid":false,"given":"Xuan Son","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3029-4412","authenticated-orcid":false,"given":"Aymeric","family":"Histace","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8042-6834","authenticated-orcid":false,"given":"Bart","family":"Jansen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1774-2970","authenticated-orcid":false,"given":"Hichem","family":"Sahli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104829_b1","series-title":"DG-STGCN: dynamic spatial-temporal modeling for skeleton-based action recognition","author":"Duan","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104829_b2","doi-asserted-by":"crossref","unstructured":"H. Duan, Y. Zhao, K. Chen, D. Lin, B. Dai, Revisiting skeleton-based action recognition, in: CVPR, 2022, pp. 2969\u20132978.","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"10.1016\/j.jvcir.2026.104829_b3","doi-asserted-by":"crossref","unstructured":"J. Lee, M. Lee, D. Lee, S. Lee, Hierarchically decomposed graph convolutional networks for skeleton-based action recognition, in: ICCV, 2023, pp. 10444\u201310453.","DOI":"10.1109\/ICCV51070.2023.00958"},{"key":"10.1016\/j.jvcir.2026.104829_b4","series-title":"Language knowledge-assisted representation learning for skeleton-based action recognition","author":"Xu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104829_b5","doi-asserted-by":"crossref","unstructured":"S. Li, W. Zhang, A.B. Chan, Maximum-margin structured learning with deep networks for 3d human pose estimation, in: ICCV, 2015, pp. 2848\u20132856.","DOI":"10.1109\/ICCV.2015.326"},{"key":"10.1016\/j.jvcir.2026.104829_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2025.104409","article-title":"Capsule network with using shifted windows for 3D human pose estimation","volume":"108","author":"Liu","year":"2025","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104829_b7","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K. Daniilidis, Ordinal depth supervision for 3d human pose estimation, in: CVPR, 2018, pp. 7307\u20137316.","DOI":"10.1109\/CVPR.2018.00763"},{"key":"10.1016\/j.jvcir.2026.104829_b8","doi-asserted-by":"crossref","unstructured":"G. Pavlakos, X. Zhou, K.G. Derpanis, K. Daniilidis, Coarse-to-fine volumetric prediction for single-image 3D human pose, in: CVPR, 2017, pp. 7025\u20137034.","DOI":"10.1109\/CVPR.2017.139"},{"key":"10.1016\/j.jvcir.2026.104829_b9","doi-asserted-by":"crossref","unstructured":"X. Sun, J. Shang, S. Liang, Y. Wei, Compositional human pose regression, in: ICCV, 2017, pp. 2602\u20132611.","DOI":"10.1109\/ICCV.2017.284"},{"key":"10.1016\/j.jvcir.2026.104829_b10","doi-asserted-by":"crossref","DOI":"10.1016\/j.jvcir.2024.104174","article-title":"Multi-hop graph transformer network for 3D human pose estimation","volume":"101","author":"Islam","year":"2024","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2026.104829_b11","series-title":"HopFIR: Hop-wise GraphFormer with intragroup joint refinement for 3D human pose estimation","author":"Zhai","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104829_b12","doi-asserted-by":"crossref","unstructured":"L. Zhao, X. Peng, Y. Tian, M. Kapadia, D.N. Metaxas, Semantic Graph Convolutional Networks for 3D Human Pose Regression, in: CVPR, 2019, pp. 3425\u20133435.","DOI":"10.1109\/CVPR.2019.00354"},{"key":"10.1016\/j.jvcir.2026.104829_b13","doi-asserted-by":"crossref","unstructured":"W. Zhao, W. Wang, Y. Tian, Graformer: Graph-oriented transformer for 3d pose estimation, in: CVPR, 2022, pp. 20438\u201320447.","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"10.1016\/j.jvcir.2026.104829_b14","doi-asserted-by":"crossref","unstructured":"Q. Li, Z. Han, X.-M. Wu, Deeper insights into graph convolutional networks for semi-supervised learning, in: AAAI, 2018, pp. 3538\u20133545.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"10.1016\/j.jvcir.2026.104829_b15","unstructured":"U. Alon, E. Yahav, On the Bottleneck of Graph Neural Networks and its Practical Implications, in: ICLR, 2021."},{"key":"10.1016\/j.jvcir.2026.104829_b16","unstructured":"D. Kreuzer, D. Beaini, W. Hamilton, V. L\u00e9tourneau, P. Tossou, Rethinking Graph Transformers with Spectral Attention, in: NeurIPS, 2021, pp. 21618\u201321629."},{"key":"10.1016\/j.jvcir.2026.104829_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.110446","article-title":"DGFormer: Dynamic graph transformer for 3D human pose estimation","volume":"152","author":"Chen","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.jvcir.2026.104829_b18","doi-asserted-by":"crossref","unstructured":"S. Mehraban, V. Adeli, B. Taati, Motionagformer: Enhancing 3d human pose estimation with a transformer-gcnformer network, in: WACV, 2024, pp. 6920\u20136930.","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"10.1016\/j.jvcir.2026.104829_b19","series-title":"AnchorGT: Efficient and flexible attention architecture for scalable graph transformers","author":"Zhu","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104829_b20","series-title":"Memory transformer","author":"Burtsev","year":"2020"},{"key":"10.1016\/j.jvcir.2026.104829_b21","unstructured":"T. Darcet, M. Oquab, J. Mairal, P. Bojanowski, Vision Transformers Need Registers, in: ICLR, 2024."},{"key":"10.1016\/j.jvcir.2026.104829_b22","unstructured":"Y. Rao, W. Zhao, B. Liu, J. Lu, J. Zhou, C.-J. Hsieh, DynamicViT: Efficient Vision Transformers with Dynamic Token Sparsification, in: NeurIPS, 2021."},{"issue":"7","key":"10.1016\/j.jvcir.2026.104829_b23","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":"2014","journal-title":"IEEE PAMI"},{"key":"10.1016\/j.jvcir.2026.104829_b24","doi-asserted-by":"crossref","unstructured":"D. Mehta, H. Rhodin, D. Casas, P. Fua, O. Sotnychenko, W. Xu, C. Theobalt, Monocular 3D Human Pose Estimation in the Wild Using Improved CNN Supervision, in: 3DV, 2017, pp. 506\u2013516.","DOI":"10.1109\/3DV.2017.00064"},{"key":"10.1016\/j.jvcir.2026.104829_b25","doi-asserted-by":"crossref","unstructured":"Y. Chen, Z. Wang, Y. Peng, Z. Zhang, G. Yu, J. Sun, Cascaded pyramid network for multi-person pose estimation, in: CVPR, 2018, pp. 7103\u20137112.","DOI":"10.1109\/CVPR.2018.00742"},{"key":"10.1016\/j.jvcir.2026.104829_b26","doi-asserted-by":"crossref","unstructured":"H. Ci, C. Wang, X. Ma, Y. Wang, Optimizing network structure for 3d human pose estimation, in: ICCV, 2019, pp. 2262\u20132271.","DOI":"10.1109\/ICCV.2019.00235"},{"key":"10.1016\/j.jvcir.2026.104829_b27","doi-asserted-by":"crossref","unstructured":"A. Newell, K. Yang, J. Deng, Stacked hourglass networks for human pose estimation, in: ECCV, 2016, pp. 483\u2013499.","DOI":"10.1007\/978-3-319-46484-8_29"},{"issue":"11","key":"10.1016\/j.jvcir.2026.104829_b28","doi-asserted-by":"crossref","first-page":"5801","DOI":"10.1109\/TAI.2024.3430260","article-title":"Hierarchical spatial-temporal masked contrast for skeleton action recognition","volume":"5","author":"Cao","year":"2024","journal-title":"IEEE Trans. Artif. Intell."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104829_b29","doi-asserted-by":"crossref","first-page":"662","DOI":"10.5829\/IJE.2024.37.04A.08","article-title":"Umpire\u2019s signal recognition in cricket using an attention based DC-GRU network","volume":"37","author":"Dey","year":"2024","journal-title":"Int. J. Eng."},{"issue":"2","key":"10.1016\/j.jvcir.2026.104829_b30","first-page":"3067","article-title":"Workout action recognition in video streams using an attention driven residual DC-GRU network","volume":"79","author":"Arnab Dey","year":"2024","journal-title":"Comput. Mater. Contin."},{"key":"10.1016\/j.jvcir.2026.104829_b31","unstructured":"T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: ICLR, 2017."},{"key":"10.1016\/j.jvcir.2026.104829_b32","series-title":"Convolution on graph: A high-order and adaptive approach","author":"Zhou","year":"2017"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104829_b33","doi-asserted-by":"crossref","first-page":"599","DOI":"10.1007\/s13042-024-02262-9","article-title":"HOGFormer: high-order graph convolution transformer for 3D human pose estimation","volume":"16","author":"Xie","year":"2025","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.jvcir.2026.104829_b34","article-title":"Stacked capsule graph autoencoders for geometry-aware 3D head pose estimation","volume":"208\u2013209","author":"Hong","year":"2021","journal-title":"Comput. Vis. Image Un Derstanding"},{"key":"10.1016\/j.jvcir.2026.104829_b35","unstructured":"A. Vaswani, N. Shazeer, N. Parmar, J. Uszkoreit, L. Jones, A.N. Gomez, \u0141. Kaiser, I. Polosukhin, Attention is all you need, in: NIPS, 2017, pp. 6000\u20136010."},{"key":"10.1016\/j.jvcir.2026.104829_b36","doi-asserted-by":"crossref","unstructured":"Y. Zhu, X. Xu, F. Shen, Y. Ji, L. Gao, H.T. Shen, PoseGTAC: Graph Transformer Encoder-Decoder with Atrous Convolution for 3D Human Pose Estimation, in: IJCAI, 2021, pp. 1359\u20131365.","DOI":"10.24963\/ijcai.2021\/188"},{"key":"10.1016\/j.jvcir.2026.104829_b37","first-page":"1","article-title":"A simple and efficient channel MLP on token for human pose estimation","author":"Huang","year":"2024","journal-title":"Int. J. Mach. Learn. Cybern."},{"key":"10.1016\/j.jvcir.2026.104829_b38","doi-asserted-by":"crossref","unstructured":"Y. Li, S. Zhang, Z. Wang, S. Yang, W. Yang, S.-T. Xia, E. Zhou, Tokenpose: Learning keypoint tokens for human pose estimation, in: ICCV, 2021, pp. 11313\u201311322.","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"10.1016\/j.jvcir.2026.104829_b39","unstructured":"P. Veli\u010dkovi\u0107, G. Cucurull, A. Casanova, A. Romero, P. Li\u00f2, Y. Bengio, Graph Attention Networks, in: ICLR, 2018."},{"key":"10.1016\/j.jvcir.2026.104829_b40","series-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104829_b41","series-title":"European Conference on Computer Vision","first-page":"516","article-title":"Deit iii: Revenge of the vit","author":"Touvron","year":"2022"},{"issue":"4","key":"10.1016\/j.jvcir.2026.104829_b42","doi-asserted-by":"crossref","first-page":"901","DOI":"10.1109\/TPAMI.2018.2816031","article-title":"Monocap: Monocular human motion capture using a cnn coupled with a geometric prior","volume":"41","author":"Zhou","year":"2018","journal-title":"IEEE PAMI"},{"key":"10.1016\/j.jvcir.2026.104829_b43","series-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"10.1016\/j.jvcir.2026.104829_b44","doi-asserted-by":"crossref","unstructured":"K. Liu, R. Ding, Z. Zou, L. Wang, W. Tang, A comprehensive study of weight sharing in graph networks for 3d human pose estimation, in: ECCV, 2020, pp. 318\u2013334.","DOI":"10.1007\/978-3-030-58607-2_19"},{"key":"10.1016\/j.jvcir.2026.104829_b45","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: ICCV, 2017, pp. 2640\u20132649.","DOI":"10.1109\/ICCV.2017.288"},{"key":"10.1016\/j.jvcir.2026.104829_b46","doi-asserted-by":"crossref","unstructured":"T. Xu, W. Takano, Graph Stacked Hourglass Networks for 3D Human Pose Estimation, in: CVPR, 2021, pp. 16105\u201316114.","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"10.1016\/j.jvcir.2026.104829_b47","doi-asserted-by":"crossref","unstructured":"W. Yang, W. Ouyang, X. Wang, J. Ren, H. Li, X. Wang, 3d human pose estimation in the wild by adversarial learning, in: CVPR, 2018, pp. 5255\u20135264.","DOI":"10.1109\/CVPR.2018.00551"},{"key":"10.1016\/j.jvcir.2026.104829_b48","doi-asserted-by":"crossref","unstructured":"J. Xu, Z. Yu, B. Ni, J. Yang, X. Yang, W. Zhang, Deep kinematics analysis for monocular 3d human pose estimation, in: CVPR, 2020, pp. 899\u2013908.","DOI":"10.1109\/CVPR42600.2020.00098"},{"key":"10.1016\/j.jvcir.2026.104829_b49","unstructured":"B.X. Yu, Z. Zhang, Y. Liu, S.-h. Zhong, Y. Liu, C.W. Chen, Gla-gcn: Global-local adaptive graph convolutional network for 3d human pose estimation from monocular video, in: ICCV, 2023, pp. 8818\u20138829."},{"key":"10.1016\/j.jvcir.2026.104829_b50","doi-asserted-by":"crossref","unstructured":"J. Zhang, Z. Tu, J. Yang, Y. Chen, J. Yuan, Mixste: Seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video, in: CVPR, 2022, pp. 13232\u201313242.","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"10.1016\/j.jvcir.2026.104829_b51","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: CVPR, 2023, pp. 8877\u20138886.","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"10.1016\/j.jvcir.2026.104829_b52","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: ICCV, 2021, pp. 11656\u201311665.","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"10.1016\/j.jvcir.2026.104829_b53","doi-asserted-by":"crossref","unstructured":"M. Andriluka, L. Pishchulin, P. Gehler, B. Schiele, 2d human pose estimation: New benchmark and state of the art analysis, in: CVPR, 2014, pp. 3686\u20133693.","DOI":"10.1109\/CVPR.2014.471"},{"issue":"5","key":"10.1016\/j.jvcir.2026.104829_b54","doi-asserted-by":"crossref","first-page":"1250","DOI":"10.1007\/s11263-023-01749-2","article-title":"Lifting 2D human pose to 3D with domain adapted 3D body concept","volume":"131","author":"Nie","year":"2023","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.jvcir.2026.104829_b55","doi-asserted-by":"crossref","unstructured":"A. Zeng, X. Sun, F. Huang, M. Liu, Q. Xu, S. Lin, Srnet: Improving generalization in 3d human pose estimation with a split-and-recombine approach, in: ECCV, 2020, pp. 507\u2013523.","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"10.1016\/j.jvcir.2026.104829_b56","doi-asserted-by":"crossref","unstructured":"Z. Zou, W. Tang, Modulated Graph Convolutional Network for 3D Human Pose Estimation, in: ICCV, 2021, pp. 11477\u201311487.","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"10.1016\/j.jvcir.2026.104829_b57","unstructured":"M. Defferrard, X. Bresson, P. Vandergheynst, Convolutional neural networks on graphs with fast localized spectral filtering, in: NIPS, 2016, pp. 3844\u20133852."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001240?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326001240?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T01:29:13Z","timestamp":1783128553000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326001240"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6]]},"references-count":57,"alternative-id":["S1047320326001240"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104829","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ADGT: Enhancing 3D human pose estimation with attention-driven graph-transformers","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.2026.104829","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104829"}}