{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:32:40Z","timestamp":1783823560943,"version":"3.55.0"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T00:00:00Z","timestamp":1764806400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"the Key Laboratory of Ministry of Public Security for Road Traffic Safety"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s00530-025-02074-z","type":"journal-article","created":{"date-parts":[[2025,12,4]],"date-time":"2025-12-04T08:53:30Z","timestamp":1764838410000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["STGSFormer: a 3d human pose estimation model that integrates GCN and self-attention in the spatio-temporal domain"],"prefix":"10.1007","volume":"32","author":[{"given":"Fanjun","family":"Su","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinyue","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,12,4]]},"reference":[{"key":"2074_CR1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2025.103314","author":"Q Zhang","year":"2025","unstructured":"Zhang, Q., Miao, D., Zhang, Q., et al.: Dynamic frequency selection and Spatial interaction fusion for robust person search. Inf. Fus. (2025). https:\/\/doi.org\/10.1016\/j.inffus.2025.103314","journal-title":"Information Fusion"},{"key":"2074_CR2","doi-asserted-by":"publisher","first-page":"4795","DOI":"10.1109\/TMM.2025.3543029","volume":"27","author":"T Liu","year":"2025","unstructured":"Liu, T., Li, J., Wu, J., Du, B., Zhan, Y., Tao, D.: Facial expression recognition with heatmap neighbor contrastive learning. IEEE Trans. Multimedia 27, 4795\u20134807 (2025)","journal-title":"IEEE Trans. Multimedia"},{"key":"2074_CR3","doi-asserted-by":"crossref","unstructured":"Lu, M., Poston, K., Pfefferbaum, A., et al.: Vision-based estimation of MDS-UPDRS gait scores for assessing Parkinson\u2019s disease motor severity. In International Conference on Medical Image Computing and Computer-Assisted Intervention. Springer, Cham, 637\u2013647 (2020)","DOI":"10.1007\/978-3-030-59716-0_61"},{"key":"2074_CR4","doi-asserted-by":"publisher","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In Thirty-second AAAI Conference on Artificial Intelligence. (2018) https:\/\/doi.org\/10.48550\/arXiv.1801.07455","DOI":"10.48550\/arXiv.1801.07455"},{"key":"2074_CR5","doi-asserted-by":"crossref","unstructured":"Czech, P., Braun, M., Kre\u00dfel, U., Yang, B.: On-board pedestrian trajectory prediction using behavioral features. In: Proceedings of the IEEE International Conference on Machine Learning and Applications (ICMLA). 437\u2013443 (2022)","DOI":"10.1109\/ICMLA55696.2022.00070"},{"key":"2074_CR6","doi-asserted-by":"crossref","unstructured":"Zheng, C., Zhu, S., Mendieta, M., Yang, T., Chen, C., Ding, Z.: 3d human pose estimation with spatial and temporal transformers. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11656\u201311665 (2021)","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"2074_CR7","doi-asserted-by":"crossref","unstructured":"Zhao, Q., Zheng, C., Liu, M., Wang, P., Chen, C.: 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, pp. 8877\u20138886 (2023)","DOI":"10.1109\/CVPR52729.2023.00857"},{"key":"2074_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., Yang, J., Yang, J., Chen, Y., Yuan, J.: MixSTE: Seq2seq mixed spatio-temporal encoder for 3d human pose estimation in video. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 13232\u201313242 (2022)","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"2074_CR9","doi-asserted-by":"crossref","unstructured":"Zhao, L., Peng, X., Tian, Y., Kapadia, M.: Semantic graph convolutional networks for 3d human pose regression. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 3425\u20133435 (2019)","DOI":"10.1109\/CVPR.2019.00354"},{"key":"2074_CR10","doi-asserted-by":"crossref","unstructured":"Doosti, B., Naha, S., Mirbagheri, M., Crandall, D.: HOPE-Net: A graph-based model for hand-object pose estimation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 6608\u20136617 (2020)","DOI":"10.1109\/CVPR42600.2020.00664"},{"key":"2074_CR11","doi-asserted-by":"crossref","unstructured":"Chen, Y., Zhang, Z., Yuan, C., Li, B., Deng, Y., Hu, W.: Channel-wise topology refinement graph convolution for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp. 13359\u201313368 (2021)","DOI":"10.1109\/ICCV48922.2021.01311"},{"key":"2074_CR12","doi-asserted-by":"crossref","unstructured":"Liu, Z., Zhang, H., Chen, Z., Wang, Z., Ouyang, W.: Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 143\u2013152 (2020)","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"2074_CR13","doi-asserted-by":"crossref","unstructured":"Zhao, W., Wang, W., Tian, Y.: GraFormer: Graph-oriented transformer for 3d pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 20438\u201320447 (2022)","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"2074_CR14","first-page":"12","volume":"25","author":"W Li","year":"2023","unstructured":"Li, W., Liu, H., Ding, R., Liu, M., Wang, P., Yang, W.: Exploiting Temporal contexts with strided transformer for 3d human pose Estimation. IEEE Trans. Multimedia. 25,1282-1293 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"2074_CR15","doi-asserted-by":"publisher","unstructured":"Huo, R., Zhang, Y., Guo, Y., Ju, Z., Gao, Q.: GTFormer: 3D driver body pose Estimation in video with graph Convolution network and transformer. IEEE Trans. Intell. Veh. (2023) https:\/\/doi.org\/10.1109\/TIV.2023.3324045","DOI":"10.1109\/TIV.2023.3324045"},{"key":"2074_CR16","doi-asserted-by":"crossref","unstructured":"Zhu, Y., Xu, X., Shen, F., Ji, Y., Gao, L., Shen, H.: PoseGTAC: Graph transformer Encoder-Decoder with atrous Convolution for 3D human pose Estimation. IJCAI, pp. 1359\u20131365 (2021)","DOI":"10.24963\/ijcai.2021\/188"},{"key":"2074_CR17","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110446","volume":"152","author":"Z Chen","year":"2024","unstructured":"Chen, Z., Dai, J., Bai, J., Pan, J.: DGFormer: Dynamic graph transformer for 3D human pose Estimation. Pattern Recognit.152, 110446 (2024)","journal-title":"Pattern Recognition"},{"key":"2074_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110925","volume":"158","author":"W Li","year":"2025","unstructured":"Li, W., Liu, M., Liu, H., Guo, T., Wang, T., Tang, H., Sebe, N.: GraphMLP: A graph MLP-like architecture for 3D human pose Estimation. Pattern Recognit.158, 110925 (2025)","journal-title":"Pattern Recognition"},{"key":"2074_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2024.104174","volume":"101","author":"Z Islam","year":"2024","unstructured":"Islam, Z., Hamza, A.B.: Multi-hop graph transformer network for 3D human pose Estimation. J. Vis. Commun. Image Represent. 101, 104174 (2024)","journal-title":"Journal of Visual Communication and Image Representation"},{"key":"2074_CR20","doi-asserted-by":"crossref","unstructured":"Mehraban, S., Adeli, V., Taati, B.: Motionagformer: Enhancing 3d human pose estimation with a transformer-gcnformer network. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 6920\u20136930 (2024)","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"2074_CR21","doi-asserted-by":"crossref","unstructured":"Wang, T., Liu, H., Ding, R., Li, W., You, Y., Li, X.: Interweaved graph and attention network for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10097259"},{"key":"2074_CR22","doi-asserted-by":"publisher","first-page":"312","DOI":"10.1007\/978-3-030-31456-9_35","volume-title":"Chinese Conference on Biometric Recognition","author":"Q Zhang","year":"2019","unstructured":"Zhang, Q., Zhu, X., Liu, Y., et al.: Iris recognition based on adaptive optimization log-gabor filter and rbf neural network. In: Chinese Conference on Biometric Recognition, pp. 312\u2013320. Springer International Publishing, Cham (2019)"},{"key":"2074_CR23","doi-asserted-by":"publisher","first-page":"112483","DOI":"10.1016\/j.knosys.2024.112483","volume":"304","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Miao, D., Zhang, Q., Wang, C., Li, Y.: Learning adaptive shift and task decoupling for discriminative one-step person search. Knowl. Based Syst. 304, 112483 (2024)","journal-title":"Knowl. Based Syst."},{"key":"2074_CR24","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Daniilidis, K.: Ordinal depth supervision for 3d human pose estimation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 7307\u20137316 (2018)","DOI":"10.1109\/CVPR.2018.00763"},{"key":"2074_CR25","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarseto-fine volumetric prediction for single-image 3D human pose. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"2074_CR26","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Huang, F., Liu, M., Xu, Q., Lin, S.: SRNet: improving generalization in 3D human pose estimation with a split-and-recombine approach. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 507\u2013523 (2020)","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"2074_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2021.108297","volume":"122","author":"J Ma","year":"2022","unstructured":"Ma, J., Li, J., Du, B., Wu, J., Wan, J., Xiao, Y.: Robust face alignment by dual-attentional spatial-aware capsule networks. Pattern Recognition 122, 108297 (2022)","journal-title":"Pattern Recognition"},{"issue":"6","key":"2074_CR28","doi-asserted-by":"publisher","first-page":"3546","DOI":"10.1109\/TCYB.2021.3131569","volume":"53","author":"J Wan","year":"2021","unstructured":"Wan, J., Xi, H., Zhou, J., et al.: Robust and precise facial landmark detection by self-calibrated pose attention network. IEEE Trans. Cybernetics. 53(6), 3546\u20133560 (2021)","journal-title":"IEEE Trans. Cybernetics"},{"key":"2074_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121191","volume":"681","author":"Q Zhang","year":"2024","unstructured":"Zhang, Q., Wu, J., Miao, D., Zhao, C., Zhang, Q.: Attentive multi-granularity perception network for person search. Information Sciences 681, 121191 (2024)","journal-title":"Information Sciences"},{"key":"2074_CR30","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Gool, L.: Mhformer: multi-hypothesis transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13147\u201313156 (2022)","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"2074_CR31","doi-asserted-by":"crossref","unstructured":"Tang, Z., Qiu, Z., Hao, Y., Hong, R., Yao, T.: 3D human pose estimation with spatio-temporal criss-cross attention. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4790\u20134799 (2023)","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"2074_CR32","doi-asserted-by":"crossref","unstructured":"Zou, Z., Tang, W.: Modulated graph convolutional network for 3d human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11477\u201311487 (2021)","DOI":"10.1109\/ICCV48922.2021.01128"},{"key":"2074_CR33","doi-asserted-by":"crossref","unstructured":"Hassan, T., Hamza, A.: Regular splitting graph network for 3D human pose Estimation. IEEE Transactions on Image Processing. 32, 4212-4222 (2023)","DOI":"10.1109\/TIP.2023.3275914"},{"key":"2074_CR34","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., Wang, Y.: Motionbert: A unified perspective on learning human motion representations. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15085\u201315099 (2023)","DOI":"10.1109\/ICCV51070.2023.01385"},{"issue":"7","key":"2074_CR35","doi-asserted-by":"publisher","first-page":"1325","DOI":"10.1109\/TPAMI.2013.248","volume":"36","author":"C Ionescu","year":"2013","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"2074_CR36","doi-asserted-by":"crossref","unstructured":"Mehta, D., Rhodin, H., Casas, D., Fua, P., Sotnychenko, O., Xu, W., Theobalt, C.: Monocular 3d human pose estimation in the wild using improved CNN supervision. In: 2017 International Conference on 3D Vision (3DV), pp. 506\u2013516. IEEE (2017)","DOI":"10.1109\/3DV.2017.00064"},{"key":"2074_CR37","doi-asserted-by":"crossref","unstructured":"Newell, A., Yang, K., Deng, J.: Stacked hourglass networks for human pose estimation. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part VIII 14, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"2074_CR38","doi-asserted-by":"publisher","unstructured":"Qian, X., Tang, Y., Zhang, N., Han, M., Xiao, J., Huang, M., Lin, R.: Hstformer: Hierarchical spatial-temporal Transformers for 3d human pose Estimation. (2023) https:\/\/doi.org\/10.48550\/arXiv.2301.07322","DOI":"10.48550\/arXiv.2301.07322"},{"key":"2074_CR39","doi-asserted-by":"crossref","unstructured":"Chen, H., He, J.Y., Xiang, W., et al.: Hdformer: High-order directed transformer for 3d human pose Estimation.Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence, IJCAI-23, pp. 581\u2013589 (2023)","DOI":"10.24963\/ijcai.2023\/65"},{"key":"2074_CR40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.103992","volume":"243","author":"Y Chen","year":"2024","unstructured":"Chen, Y., Wang, J., Zhou, L.: Slowfastformer for 3d human pose Estimation. Computer Vision and Image Understanding 243, 103992 (2024)","journal-title":"Computer Vision and Image Understanding"},{"key":"2074_CR41","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2024.104258","volume":"251","author":"F Xu","year":"2025","unstructured":"Xu, F., Wang, J., Sun, Y., et al.: Spatio-temporal dynamic interlaced network for 3D human pose Estimation in video. Computer Vision and Image Understanding 251, 104258 (2025)","journal-title":"Computer Vision and Image Understanding"},{"key":"2074_CR42","doi-asserted-by":"crossref","unstructured":"Peng, J., Zhou, Y., Mok, P.Y.: Ktpformer: kinematics and trajectory prior knowledge-enhanced transformer for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1123\u20131132 (2024)","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"2074_CR43","doi-asserted-by":"crossref","unstructured":"Chen, Y., Wang, Z., Peng, Y., Zhang, Z., Yu, G., Sun, J.: Cascaded pyramid network for multi-person pose estimation. In: Proceedings of the IEEE\/ CVF Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"2074_CR44","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\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"},{"key":"2074_CR45","first-page":"1","volume-title":"Computer Vision and Pattern Recognition","author":"A Farhadi","year":"2018","unstructured":"Farhadi, A., Redmon, J.: Yolov3: An incremental improvement. In: Computer Vision and Pattern Recognition, vol. 1804, pp. 1\u20136. Springer, Berlin\/Heidelberg, Germany (2018)"},{"key":"2074_CR46","doi-asserted-by":"crossref","unstructured":"Yu, B.X.B., Zhang, Z., Liu, Y., Zhong, S., Liu, Y., Chen, C.: Gla-gcn: Global-local adaptive graph convolutional network for 3d human pose estimation from monocular video. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8818\u20138829 (2023)","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"2074_CR47","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\/CVF International Conference on Computer Vision, pp. 5693\u20135703 (2019)","DOI":"10.1109\/CVPR.2019.00584"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02074-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-02074-z","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-02074-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T04:19:15Z","timestamp":1770783555000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-02074-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,4]]},"references-count":47,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["2074"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-02074-z","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7065762\/v1","asserted-by":"object"}]},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,4]]},"assertion":[{"value":"7 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"30"}}