{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T08:25:07Z","timestamp":1776068707049,"version":"3.50.1"},"reference-count":55,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T00:00:00Z","timestamp":1723507200000},"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":["Multimedia Systems"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00530-024-01451-4","type":"journal-article","created":{"date-parts":[[2024,8,13]],"date-time":"2024-08-13T11:02:27Z","timestamp":1723546947000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Exploring multi-level transformers with feature frame padding network for 3D human pose estimation"],"prefix":"10.1007","volume":"30","author":[{"given":"Sathiyamoorthi","family":"Arthanari","sequence":"first","affiliation":[]},{"given":"Jae Hoon","family":"Jeong","sequence":"additional","affiliation":[]},{"given":"Young Hoon","family":"Joo","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,8,13]]},"reference":[{"key":"1451_CR1","doi-asserted-by":"publisher","first-page":"360","DOI":"10.1016\/j.neunet.2023.08.019","volume":"167","author":"S Moorthy","year":"2023","unstructured":"Moorthy, S., Joo, Y.H.: Learning dynamic spatial-temporal regularized correlation filter tracking with response deviation suppression via multi-feature fusion. Neural Netw. 167, 360\u2013379 (2023)","journal-title":"Neural Netw."},{"key":"1451_CR2","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-024-19465-5","author":"KS Sachin Sakthi","year":"2024","unstructured":"Sachin Sakthi, K.S., Jeong, J.H., Joo, Y.H.: A multi-level hybrid Siamese network using box adaptive and classification approach for robust tracking. Multimed. Tools Appl. (2024). https:\/\/doi.org\/10.1007\/s11042-024-19465-5","journal-title":"Multimed. Tools Appl."},{"key":"1451_CR3","doi-asserted-by":"publisher","first-page":"502","DOI":"10.1016\/j.ins.2023.02.009","volume":"629","author":"D Elayaperumal","year":"2023","unstructured":"Elayaperumal, D., Joo, Y.H.: Learning spatial variance-key surrounding-aware tracking via multi-expert deep feature fusion. Inf. Sci. 629, 502\u2013519 (2023)","journal-title":"Inf. Sci."},{"key":"1451_CR4","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109457","volume":"139","author":"S Moorthy","year":"2023","unstructured":"Moorthy, S., Joo, Y.H.: Adaptive spatial-temporal surrounding-aware correlation filter tracking via ensemble learning. Pattern Recogn. 139, 109457 (2023)","journal-title":"Pattern Recogn."},{"issue":"14","key":"1451_CR5","doi-asserted-by":"publisher","first-page":"2279","DOI":"10.3390\/math12142279","volume":"12","author":"SS Kuppusami Sakthivel","year":"2024","unstructured":"Kuppusami Sakthivel, S.S., Moorthy, S., Arthanari, S., Jeong, J.H., Joo, Y.H.: Learning a context-aware environmental residual correlation filter via deep convolution features for visual object tracking. Mathematics 12(14), 2279 (2024)","journal-title":"Mathematics"},{"key":"1451_CR6","doi-asserted-by":"publisher","first-page":"467","DOI":"10.1016\/j.ins.2021.06.084","volume":"577","author":"D Elayaperumal","year":"2021","unstructured":"Elayaperumal, D., Joo, Y.H.: Robust visual object tracking using context-based spatial variation via multi-feature fusion. Inf. Sci. 577, 467\u2013482 (2021)","journal-title":"Inf. Sci."},{"key":"1451_CR7","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":"1451_CR8","doi-asserted-by":"crossref","unstructured":"Zhang, J., Tu, Z., 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":"1451_CR9","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Van\u00a0Gool, 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":"1451_CR10","unstructured":"Li, W., Liu, H., Guo, T., Ding, R., Tang, H.: Graphmlp: A graph mlp-like architecture for 3d human pose estimation. arXiv preprint arXiv:2206.06420 (2022)"},{"key":"1451_CR11","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/j.neucom.2021.11.007","volume":"487","author":"Y Wu","year":"2022","unstructured":"Wu, Y., Kong, D., Wang, S., Li, J., Yin, B.: Hpgcn: Hierarchical poselet-guided graph convolutional network for 3d pose estimation. Neurocomputing 487, 243\u2013256 (2022)","journal-title":"Neurocomputing"},{"key":"1451_CR12","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S.-h., Liu, Y., Chen, C.W.: 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":"1451_CR13","doi-asserted-by":"publisher","first-page":"4212","DOI":"10.1109\/TIP.2023.3275914","volume":"32","author":"MT Hassan","year":"2023","unstructured":"Hassan, M.T., Hamza, A.B.: Regular splitting graph network for 3d human pose estimation. IEEE Trans. Image Process. 32, 4212\u20134222 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"1451_CR14","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"},{"issue":"6","key":"1451_CR15","doi-asserted-by":"publisher","first-page":"7853","DOI":"10.1109\/TPAMI.2022.3223955","volume":"45","author":"Q Zhou","year":"2022","unstructured":"Zhou, Q., Li, X., He, L., Yang, Y., Cheng, G., Tong, Y., Ma, L., Tao, D.: Transvod: end-to-end video object detection with spatial-temporal transformers. IEEE Trans. Pattern Anal. Mach. Intell. 45(6), 7853\u20137869 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"2","key":"1451_CR16","doi-asserted-by":"publisher","first-page":"615","DOI":"10.1007\/s00530-022-00998-4","volume":"29","author":"X Tian","year":"2023","unstructured":"Tian, X., Jin, Y., Tang, X.: Local-global transformer neural network for temporal action segmentation. Multimed. Syst. 29(2), 615\u2013626 (2023)","journal-title":"Multimed. Syst."},{"issue":"3","key":"1451_CR17","doi-asserted-by":"publisher","first-page":"1375","DOI":"10.1007\/s10044-023-01166-8","volume":"26","author":"X Tian","year":"2023","unstructured":"Tian, X., Jin, Y., Tang, X.: Tsrn: two-stage refinement network for temporal action segmentation. Pattern Anal. Appl. 26(3), 1375\u20131393 (2023)","journal-title":"Pattern Anal. Appl."},{"key":"1451_CR18","doi-asserted-by":"crossref","unstructured":"Kim, D., Xie, J., Wang, H., Qiao, S., Yu, Q., Kim, H.-S., Adam, H., Kweon, I.S., Chen, L.-C.: Tubeformer-deeplab: Video mask transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13914\u201313924 (2022)","DOI":"10.1109\/CVPR52688.2022.01354"},{"key":"1451_CR19","doi-asserted-by":"crossref","unstructured":"Li, X., Zhang, W., Pang, J., Chen, K., Cheng, G., Tong, Y., Loy, C.C.: Video k-net: A simple, strong, and unified baseline for video segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18847\u201318857 (2022)","DOI":"10.1109\/CVPR52688.2022.01828"},{"key":"1451_CR20","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":"1451_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Z., Nie, X., Qu, X., Chen, Y., Liu, S.: Distribution-aware single-stage models for multi-person 3d pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13096\u201313105 (2022)","DOI":"10.1109\/CVPR52688.2022.01275"},{"key":"1451_CR22","doi-asserted-by":"crossref","unstructured":"Sun, S., Liu, D., Dong, J., Qu, X., Gao, J., Yang, X., Wang, X., Wang, M.: Unified multi-modal unsupervised representation learning for skeleton-based action understanding. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 2973\u20132984 (2023)","DOI":"10.1145\/3581783.3612449"},{"key":"1451_CR23","doi-asserted-by":"crossref","unstructured":"Huang, W., Liu, D., Hu, W.: Dense object grounding in 3d scenes. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 5017\u20135026 (2023)","DOI":"10.1145\/3581783.3611902"},{"key":"1451_CR24","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 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, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1451_CR25","doi-asserted-by":"crossref","unstructured":"Zhou, J., Zhang, T., Hayder, Z., Petersson, L., Harandi, M.: Diff3dhpe: A diffusion model for 3d human pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2092\u20132102 (2023)","DOI":"10.1109\/ICCVW60793.2023.00223"},{"key":"1451_CR26","doi-asserted-by":"crossref","unstructured":"Meinhardt, T., Kirillov, A., Leal-Taixe, L., Feichtenhofer, C.: Trackformer: Multi-object tracking with transformers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8844\u20138854 (2022)","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"1451_CR27","doi-asserted-by":"crossref","unstructured":"He, L., Zhou, Q., Li, X., Niu, L., Cheng, G., Li, X., Liu, W., Tong, Y., Ma, L., Zhang, L.: End-to-end video object detection with spatial-temporal transformers. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 1507\u20131516 (2021)","DOI":"10.1145\/3474085.3475285"},{"key":"1451_CR28","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1109\/TMM.2022.3141231","volume":"25","author":"W Li","year":"2022","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. Multimed. 25, 1282\u20131293 (2022)","journal-title":"IEEE Trans. Multimed."},{"key":"1451_CR29","doi-asserted-by":"crossref","unstructured":"Chen, H., He, J.-Y., Xiang, W., Cheng, Z.-Q., Liu, W., Liu, H., Luo, B., Geng, Y., Xie, X.: Hdformer: High-order directed transformer for 3d human pose estimation. arXiv preprint arXiv:2302.01825 (2023)","DOI":"10.24963\/ijcai.2023\/65"},{"key":"1451_CR30","doi-asserted-by":"crossref","unstructured":"Shan, W., Liu, Z., Zhang, X., Wang, Z., Han, K., Wang, S., Ma, S., Gao, W.: Diffusion-based 3d human pose estimation with multi-hypothesis aggregation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 14761\u201314771 (2023)","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"1451_CR31","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. In: Advances in neural information processing systems 30 (2017)"},{"key":"1451_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108871","volume":"250","author":"B Yu","year":"2022","unstructured":"Yu, B., Jiao, L., Liu, X., Li, L., Liu, F., Yang, S., Tang, X.: Entire deformable convnets for semantic segmentation. Knowl. Based Syst. 250, 108871 (2022)","journal-title":"Knowl. Based Syst."},{"issue":"7","key":"1451_CR33","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":"1451_CR34","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 (2017). IEEE","DOI":"10.1109\/3DV.2017.00064"},{"key":"1451_CR35","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 Conference on Computer Vision and Pattern Recognition, pp. 7103\u20137112 (2018)","DOI":"10.1109\/CVPR.2018.00742"},{"key":"1451_CR36","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 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, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"1451_CR37","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: Computer Vision\u2013ECCV 2020: 16th European Conference, Glasgow, UK, August 23\u201328, 2020, Proceedings, Part XIV 16, pp. 507\u2013523 (2020). Springer","DOI":"10.1007\/978-3-030-58568-6_30"},{"key":"1451_CR38","doi-asserted-by":"crossref","unstructured":"Shan, W., Lu, H., Wang, S., Zhang, X., Gao, W.: Improving robustness and accuracy via relative information encoding in 3d human pose estimation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3446\u20133454 (2021)","DOI":"10.1145\/3474085.3475504"},{"issue":"1","key":"1451_CR39","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1109\/TCSVT.2021.3057267","volume":"32","author":"T Chen","year":"2021","unstructured":"Chen, T., Fang, C., Shen, X., Zhu, Y., Chen, Z., Luo, J.: Anatomy-aware 3d human pose estimation with bone-based pose decomposition. IEEE Trans Circuits Syst. Video Technol. 32(1), 198\u2013209 (2021)","journal-title":"IEEE Trans Circuits Syst. Video Technol."},{"key":"1451_CR40","doi-asserted-by":"crossref","unstructured":"Hu, W., Zhang, C., Zhan, F., Zhang, L., Wong, T.-T.: Conditional directed graph convolution for 3d human pose estimation. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 602\u2013611 (2021)","DOI":"10.1145\/3474085.3475219"},{"key":"1451_CR41","doi-asserted-by":"crossref","unstructured":"Zhan, Y., Li, F., Weng, R., Choi, W.: Ray3d: ray-based 3d human pose estimation for monocular absolute 3d localization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13116\u201313125 (2022)","DOI":"10.1109\/CVPR52688.2022.01277"},{"key":"1451_CR42","doi-asserted-by":"publisher","first-page":"1282","DOI":"10.1109\/TMM.2022.3141231","volume":"25","author":"W Li","year":"2022","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. Multimed. 25, 1282\u20131293 (2022)","journal-title":"IEEE Trans. Multimed."},{"key":"1451_CR43","doi-asserted-by":"publisher","first-page":"4278","DOI":"10.1109\/TIP.2022.3182269","volume":"31","author":"Y Xue","year":"2022","unstructured":"Xue, Y., Chen, J., Gu, X., Ma, H., Ma, H.: Boosting monocular 3d human pose estimation with part aware attention. IEEE Trans. Image Process. 31, 4278\u20134291 (2022)","journal-title":"IEEE Trans. Image Process."},{"key":"1451_CR44","doi-asserted-by":"crossref","unstructured":"Shan, W., Liu, Z., Zhang, X., Wang, S., Ma, S., Gao, W.: P-stmo: Pre-trained spatial temporal many-to-one model for 3d human pose estimation. In: European Conference on Computer Vision, pp. 461\u2013478 (2022). Springer","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"1451_CR45","doi-asserted-by":"publisher","first-page":"8712","DOI":"10.1109\/TMM.2023.3240455","volume":"25","author":"Z Tang","year":"2023","unstructured":"Tang, Z., Li, J., Hao, Y., Hong, R.: Mlp-jcg: multi-layer perceptron with joint-coordinate gating for efficient 3d human pose estimation. IEEE Trans. Multimed. 25, 8712\u20138724 (2023). https:\/\/doi.org\/10.1109\/TMM.2023.3240455","journal-title":"IEEE Trans. Multimed."},{"key":"1451_CR46","doi-asserted-by":"publisher","first-page":"4212","DOI":"10.1109\/TIP.2023.3275914","volume":"32","author":"MT Hassan","year":"2023","unstructured":"Hassan, M.T., Ben Hamza, A.: Regular splitting graph network for 3d human pose estimation. IEEE Trans. Image Process. 32, 4212\u20134222 (2023). https:\/\/doi.org\/10.1109\/TIP.2023.3275914","journal-title":"IEEE Trans. Image Process."},{"key":"1451_CR47","unstructured":"Qian, X., Tang, Y., Zhang, N., Han, M., Xiao, J., Huang, M.-C., Lin, R.-S.: Hstformer: Hierarchical spatial-temporal transformers for 3d human pose estimation. arXiv preprint arXiv:2301.07322 (2023)"},{"key":"1451_CR48","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109631","volume":"141","author":"W Li","year":"2023","unstructured":"Li, W., Liu, H., Tang, H., Wang, P.: Multi-hypothesis representation learning for transformer-based 3d human pose estimation. Pattern Recogn. 141, 109631 (2023)","journal-title":"Pattern Recogn."},{"key":"1451_CR49","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110116","volume":"147","author":"S Du","year":"2024","unstructured":"Du, S., Yuan, Z., Lai, P., Ikenaga, T.: Joypose: Jointly learning evolutionary data augmentation and anatomy-aware global-local representation for 3d human pose estimation. Pattern Recogn. 147, 110116 (2024)","journal-title":"Pattern Recogn."},{"key":"1451_CR50","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":"1451_CR51","doi-asserted-by":"crossref","unstructured":"Peng, Q., Zheng, C., Chen, C.: A dual-augmentor framework for domain generalization in 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2240\u20132249 (2024)","DOI":"10.1109\/CVPR52733.2024.00218"},{"key":"1451_CR52","doi-asserted-by":"crossref","unstructured":"Yu, B.X., Zhang, Z., Liu, Y., Zhong, S.-h., Liu, Y., Chen, C.W.: 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":"1451_CR53","doi-asserted-by":"crossref","unstructured":"Einfalt, M., Ludwig, K., Lienhart, R.: Uplift and upsample: Efficient 3d human pose estimation with uplifting transformers. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2903\u20132913 (2023)","DOI":"10.1109\/WACV56688.2023.00292"},{"key":"1451_CR54","doi-asserted-by":"publisher","DOI":"10.1016\/j.jvcir.2023.103890","volume":"95","author":"X Xiang","year":"2023","unstructured":"Xiang, X., Zhang, K., Qiao, Y., El Saddik, A.: Emhiformer: An enhanced multi-hypothesis interaction transformer for 3d human pose estimation in video. J. Vis. Commun. Image Represent. 95, 103890 (2023)","journal-title":"J. Vis. Commun. Image Represent."},{"key":"1451_CR55","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104863","volume":"140","author":"X Liu","year":"2023","unstructured":"Liu, X., Tang, H.: Strformer: Spatial-temporal-retemporal transformer for 3d human pose estimation. Image Vis. Comput. 140, 104863 (2023)","journal-title":"Image Vis. Comput."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01451-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-024-01451-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-024-01451-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T18:07:39Z","timestamp":1730138859000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-024-01451-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,8,13]]},"references-count":55,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["1451"],"URL":"https:\/\/doi.org\/10.1007\/s00530-024-01451-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,8,13]]},"assertion":[{"value":"19 June 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 August 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2024","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 author declares that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"243"}}