{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T15:23:43Z","timestamp":1787412223321,"version":"build-2736575974"},"reference-count":41,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Image and Vision Computing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.imavis.2026.106143","type":"journal-article","created":{"date-parts":[[2026,7,31]],"date-time":"2026-07-31T23:02:18Z","timestamp":1785538938000},"page":"106143","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["STJDNet: A spatial-temporal joint detail-aware network for skeleton-based two-person interaction recognition"],"prefix":"10.1016","volume":"174","author":[{"given":"Congcong","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Caizhi","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9976-8583","authenticated-orcid":false,"given":"Zhengyou","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuqi","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanran","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanna","family":"Zhuang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.imavis.2026.106143_b1","doi-asserted-by":"crossref","first-page":"3242","DOI":"10.1109\/TIP.2024.3391692","article-title":"Multi-label action anticipation for real-world videos with scene understanding","volume":"33","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"3","key":"10.1016\/j.imavis.2026.106143_b2","doi-asserted-by":"crossref","first-page":"1797","DOI":"10.1007\/s10055-023-00773-4","article-title":"Action recognition based on multimode fusion for VR online platform","volume":"27","author":"Li","year":"2023","journal-title":"Virtual Real."},{"issue":"5","key":"10.1016\/j.imavis.2026.106143_b3","doi-asserted-by":"crossref","first-page":"14885","DOI":"10.1007\/s11042-020-08806-9","article-title":"Human action recognition using fusion of multiview and deep features: an application to video surveillance","volume":"83","author":"Khan","year":"2024","journal-title":"Multimedia Tools Appl."},{"issue":"206","key":"10.1016\/j.imavis.2026.106143_b4","first-page":"1","article-title":"Modelling object mask interaction for compositional action recognition","volume":"11","author":"Li","year":"2025","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.imavis.2026.106143_b5","unstructured":"T.N. Kipf, M. Welling, Semi-Supervised Classification with Graph Convolutional Networks, in: International Conference on Learning Representations, 2017, pp. 1\u201314."},{"key":"10.1016\/j.imavis.2026.106143_b6","doi-asserted-by":"crossref","unstructured":"S. Yan, Y. Xiong, D. Lin, Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition, in: AAAI Conference on Artificial Intelligence, 2018, pp. 7444\u20137452.","DOI":"10.1609\/aaai.v32i1.12328"},{"issue":"3","key":"10.1016\/j.imavis.2026.106143_b7","doi-asserted-by":"crossref","first-page":"2101","DOI":"10.1109\/TCSVT.2024.3491133","article-title":"DSDC-GCN: decoupled static-dynamic co-occurrence graph convolutional networks for skeleton-based action recognition","volume":"35","author":"Zhuang","year":"2025","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106143_b8","doi-asserted-by":"crossref","first-page":"141","DOI":"10.1016\/j.patrec.2025.02.020","article-title":"Selective directed graph convolutional network for skeleton-based action recognition","volume":"190","author":"Ke","year":"2025","journal-title":"Pattern Recognit. Lett."},{"issue":"4","key":"10.1016\/j.imavis.2026.106143_b9","doi-asserted-by":"crossref","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","article-title":"Skeleton-based human action recognition with global context-aware attention LSTM networks","volume":"27","author":"Liu","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"7","key":"10.1016\/j.imavis.2026.106143_b10","doi-asserted-by":"crossref","first-page":"3333","DOI":"10.1109\/TCSVT.2022.3232373","article-title":"Two-person graph convolutional network for skeleton-based human interaction recognition","volume":"33","author":"Li","year":"2023","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106143_b11","doi-asserted-by":"crossref","unstructured":"K. Cheng, Y. Zhang, X. He, W. Chen, J. Cheng, H. Lu, Skeleton-Based Action Recognition With Shift Graph Convolutional Network, in: IEEE Conference on Computer Vision and Pattern Recognition, 2020, pp. 180\u2013189.","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"10.1016\/j.imavis.2026.106143_b12","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.patrec.2021.12.005","article-title":"SparseShift-GCN: High precision skeleton-based action recognition","volume":"153","author":"Zang","year":"2022","journal-title":"Pattern Recognit. Lett."},{"issue":"94","key":"10.1016\/j.imavis.2026.106143_b13","first-page":"1","article-title":"Advancing skeleton-based human behavior recognition: multi-stream fusion spatiotemporal graph convolutional networks","volume":"11","author":"Liu","year":"2024","journal-title":"Complex Intell. Syst."},{"issue":"3","key":"10.1016\/j.imavis.2026.106143_b14","doi-asserted-by":"crossref","first-page":"1403","DOI":"10.1109\/TCSVT.2023.3295084","article-title":"Spatial-temporal synchronous transformer for skeleton-based hand gesture recognition","volume":"34","author":"Zhao","year":"2024","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.imavis.2026.106143_b15","doi-asserted-by":"crossref","first-page":"182","DOI":"10.1016\/j.patrec.2023.11.010","article-title":"Participants-based synchronous optimization network for skeleton-based action recognition","volume":"176","author":"Zhuang","year":"2023","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.imavis.2026.106143_b16","doi-asserted-by":"crossref","unstructured":"L. Shi, Y. Zhang, J. Cheng, H. Lu, Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 12026\u201312035.","DOI":"10.1109\/CVPR.2019.01230"},{"key":"10.1016\/j.imavis.2026.106143_b17","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.107920","article-title":"Dyadic relational graph convolutional networks for skeleton-based human interaction recognition","volume":"115","author":"Zhu","year":"2021","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.imavis.2026.106143_b18","doi-asserted-by":"crossref","unstructured":"H. Zhou, Q. Liu, Y. Wang, Learning discriminative representations for skeleton based action recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2023, pp. 10608\u201310617.","DOI":"10.1109\/CVPR52729.2023.01022"},{"key":"10.1016\/j.imavis.2026.106143_b19","doi-asserted-by":"crossref","first-page":"4391","DOI":"10.1109\/TIP.2024.3433581","article-title":"SelfGCN: graph convolution network with self-attention for skeleton-based action recognition","volume":"33","author":"Wu","year":"2024","journal-title":"IEEE Trans. Image Process."},{"issue":"2","key":"10.1016\/j.imavis.2026.106143_b20","doi-asserted-by":"crossref","first-page":"1474","DOI":"10.1109\/TPAMI.2022.3157033","article-title":"Constructing stronger and faster baselines for skeleton-based action recognition","volume":"45","author":"Song","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2026.106143_b21","doi-asserted-by":"crossref","first-page":"7487","DOI":"10.1007\/s40747-024-01558-1","article-title":"Attention-guided mask learning for self-supervised 3D action recognition","volume":"10","author":"Zhang","year":"2024","journal-title":"Complex Intell. Syst."},{"key":"10.1016\/j.imavis.2026.106143_b22","doi-asserted-by":"crossref","unstructured":"M. Li, S. Chen, X. Chen, Y. Zhang, Y. Wang, Q. Tian, Actional-Structural Graph Convolutional Networks for Skeleton-Based Action Recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2019, pp. 3595\u20133603.","DOI":"10.1109\/CVPR.2019.00371"},{"key":"10.1016\/j.imavis.2026.106143_b23","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2023.104785","article-title":"Temporal information oriented motion accumulation and selection network for RGB-based action recognition","volume":"137","author":"Wang","year":"2023","journal-title":"Image Vis. Comput."},{"issue":"9","key":"10.1016\/j.imavis.2026.106143_b24","doi-asserted-by":"crossref","first-page":"4800","DOI":"10.1109\/TNNLS.2021.3061115","article-title":"Memory attention networks for skeleton-based action recognition","volume":"33","author":"Li","year":"2022","journal-title":"IEEE Trans. Neural Networks Learn. Syst."},{"issue":"387","key":"10.1016\/j.imavis.2026.106143_b25","first-page":"1","article-title":"CNNs, RNNs and transformers in human action recognition: a survey and a hybrid model","volume":"58","author":"Khaled","year":"2025","journal-title":"Artif. Intell. Rev."},{"key":"10.1016\/j.imavis.2026.106143_b26","doi-asserted-by":"crossref","first-page":"366","DOI":"10.1109\/TMM.2021.3050642","article-title":"Interaction relational network for mutual action recognition","volume":"24","author":"Perez","year":"2022","journal-title":"IEEE Trans. Multimed."},{"key":"10.1016\/j.imavis.2026.106143_b27","doi-asserted-by":"crossref","unstructured":"C. Yang, A. Setyoko, H. Tampubolon, K. Hua, Pairwise Adjacency Matrix on Spatial Temporal Graph Convolution Network for Skeleton-Based Two-Person Interaction Recognition, in: IEEE International Conference on Image Processing, 2020, pp. 2166\u20132170.","DOI":"10.1109\/ICIP40778.2020.9190680"},{"key":"10.1016\/j.imavis.2026.106143_b28","doi-asserted-by":"crossref","first-page":"94691","DOI":"10.1109\/ACCESS.2023.3309420","article-title":"Distinct motion-preserving graph convolutional network for two-person interaction recognition","volume":"11","author":"Phuong","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.imavis.2026.106143_b29","doi-asserted-by":"crossref","first-page":"338","DOI":"10.1016\/j.neucom.2019.12.149","article-title":"Knowledge embedded GCN for skeleton-based two-person interaction recognition","volume":"444","author":"Li","year":"2021","journal-title":"Neurocomputing"},{"key":"10.1016\/j.imavis.2026.106143_b30","doi-asserted-by":"crossref","first-page":"110670","DOI":"10.1109\/ACCESS.2021.3102671","article-title":"Multi-stream adaptive graph convolutional network using inter- and intra-body graphs for two-person interaction recognition","volume":"9","author":"Ito","year":"2021","journal-title":"IEEE Access"},{"issue":"5","key":"10.1016\/j.imavis.2026.106143_b31","doi-asserted-by":"crossref","first-page":"145:1","DOI":"10.1145\/3639470","article-title":"Two-stream multi-level dynamic point transformer for two-person interaction recognition","volume":"20","author":"Liu","year":"2024","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl."},{"key":"10.1016\/j.imavis.2026.106143_b32","doi-asserted-by":"crossref","unstructured":"R. Trabelsi, J. Varadarajan, Y. Pei, L. Zhang, I. Jabri, A. Bouallegue, P. Moulin, Robust Multi-Modal Cues for Dyadic Human Interaction Recognition, in: The Workshop on Multimodal Understanding of Social, Affective and Subjective Attributes, 2017, pp. 47\u201353.","DOI":"10.1145\/3132515.3132517"},{"key":"10.1016\/j.imavis.2026.106143_b33","doi-asserted-by":"crossref","unstructured":"A. Shahroudy, J. Liu, T. Ng, G. Wang, NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis, in: IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1010\u20131019.","DOI":"10.1109\/CVPR.2016.115"},{"issue":"10","key":"10.1016\/j.imavis.2026.106143_b34","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","article-title":"NTU RGB+D 120: A large-scale benchmark for 3D human activity understanding","volume":"42","author":"Liu","year":"2020","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2026.106143_b35","doi-asserted-by":"crossref","unstructured":"K. He, X. Zhang, S. Ren, J. Sun, Deep Residual Learning for Image Recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"10.1016\/j.imavis.2026.106143_b36","doi-asserted-by":"crossref","unstructured":"Y. Song, Z. Zhang, C. Shan, L. Wang, Stronger, Faster and More Explainable: A Graph Convolutional Baseline for Skeleton-based Action Recognition, in: ACM International Conference on Multimedia, 2020, pp. 1625\u20131633.","DOI":"10.1145\/3394171.3413802"},{"issue":"12","key":"10.1016\/j.imavis.2026.106143_b37","doi-asserted-by":"crossref","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","article-title":"Skeleton-based action recognition using spatio-temporal LSTM network with trust gates","volume":"40","author":"Liu","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Machine Intell."},{"key":"10.1016\/j.imavis.2026.106143_b38","doi-asserted-by":"crossref","unstructured":"J. Liu, G. Wang, P. Hu, L. Duan, A.C. Kot, Global Context-Aware Attention LSTM Networks for 3D Action Recognition, in: IEEE Conference on Computer Vision and Pattern Recognition, 2017, pp. 3671\u20133680.","DOI":"10.1109\/CVPR.2017.391"},{"key":"10.1016\/j.imavis.2026.106143_b39","doi-asserted-by":"crossref","unstructured":"X.S. Nguyen, GeomNet: A Neural Network Based on Riemannian Geometries of SPD Matrix Space and Cholesky Space for 3D Skeleton-Based Interaction Recognition, in: IEEE International Conference on Computer Vision, 2021, pp. 13359\u201313369.","DOI":"10.1109\/ICCV48922.2021.01313"},{"key":"10.1016\/j.imavis.2026.106143_b40","doi-asserted-by":"crossref","unstructured":"F. Gao, H. Xia, Z. Tang, Attention Interactive Graph Convolutional Network for Skeleton-Based Human Interaction Recognition, in: IEEE International Conference on Multimedia and Expo, 2022, pp. 1\u20136.","DOI":"10.1109\/ICME52920.2022.9859618"},{"key":"10.1016\/j.imavis.2026.106143_b41","doi-asserted-by":"crossref","unstructured":"S. Woo, J. Park, J. Lee, I.S. Kweon, CBAM: Convolutional Block Attention Module, in: European Conference on Computer Vision, 2018, pp. 3\u201319.","DOI":"10.1007\/978-3-030-01234-2_1"}],"container-title":["Image and Vision Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002507?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0262885626002507?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,22]],"date-time":"2026-08-22T14:44:00Z","timestamp":1787409840000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0262885626002507"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":41,"alternative-id":["S0262885626002507"],"URL":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106143","relation":{},"ISSN":["0262-8856"],"issn-type":[{"value":"0262-8856","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"STJDNet: A spatial-temporal joint detail-aware network for skeleton-based two-person interaction recognition","name":"articletitle","label":"Article Title"},{"value":"Image and Vision Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.imavis.2026.106143","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"106143"}}