{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T00:27:06Z","timestamp":1760056026906,"version":"build-2065373602"},"publisher-location":"Cham","reference-count":50,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723377"},{"type":"electronic","value":"9783031723384"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-3-031-72338-4_8","type":"book-chapter","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T10:03:01Z","timestamp":1726480981000},"page":"103-117","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["DT2S-Pose: A Deeper Temporal-Spatial Skeleton Refine Model for\u00a0Pedestrian Pose Estimation"],"prefix":"10.1007","author":[{"given":"Zheyan","family":"Gao","sequence":"first","affiliation":[]},{"given":"Jinyan","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Yuxin","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yucheng","family":"Jin","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Pishchulin, L., Gehler, P., Schiele, B.: 2d human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3686\u20133693 (2014)","DOI":"10.1109\/CVPR.2014.471"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka, M., Roth, S., Schiele, B.: Pictorial structures revisited: people detection and articulated pose estimation. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1014\u20131021. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"8_CR3","unstructured":"Bertasius, G., Feichtenhofer, C., Tran, D., Shi, J., Torresani, L.: Learning temporal pose estimation from sparsely-labeled videos. Advances in neural information processing systems 32 (2019)"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Cao, X., et al.: Aggpose: deep aggregation vision transformer for infant pose estimation. arXiv preprint arXiv:2205.05277 (2022)","DOI":"10.24963\/ijcai.2022\/700"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Cheng, B., Xiao, B., Wang, J., Shi, H., Huang, T.S., Zhang, L.: Higherhrnet: Scale-aware representation learning for bottom-up human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5386\u20135395 (2020)","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Duan, H., Zhao, Y., Chen, K., Lin, D., Dai, B.: Revisiting skeleton-based action recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2969\u20132978 (2022)","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Girdhar, R., Gkioxari, G., Torresani, L., Paluri, M., Tran, D.: Detect-and-track: efficient pose estimation in videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 350\u2013359 (2018)","DOI":"10.1109\/CVPR.2018.00044"},{"key":"8_CR8","doi-asserted-by":"crossref","unstructured":"Guo, H., Tang, T., Luo, G., Chen, R., Lu, Y., Wen, L.: Multi-domain pose network for multi-person pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV) Workshops (2018)","DOI":"10.1007\/978-3-030-11012-3_17"},{"key":"8_CR9","doi-asserted-by":"crossref","unstructured":"Hua, G., Liu, H., Li, W., Zhang, Q., Ding, R., Xu, X.: Weakly-supervised 3d human pose estimation with cross-view u-shaped graph convolutional network. IEEE Trans. Multimed. (2022)","DOI":"10.1109\/TMM.2022.3171102"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Milan, A., Gall, J.: Posetrack: joint multi-person pose estimation and tracking. In: IEEE Conference on Computer Vision and Pattern Recognition (2017)","DOI":"10.1109\/CVPR.2017.495"},{"key":"8_CR11","unstructured":"Johnson, S., Everingham, M.: Clustered pose and nonlinear appearance models for human pose estimation. In: BMVC, vol.\u00a02, p.\u00a05. Aberystwyth, UK (2010)"},{"key":"8_CR12","doi-asserted-by":"publisher","first-page":"1108","DOI":"10.1109\/TIP.2023.3239192","volume":"32","author":"J Li","year":"2023","unstructured":"Li, J., Wang, Y., Zhang, S.: Polarpose: single-stage multi-person pose estimation in polar coordinates. IEEE Trans. Image Process. 32, 1108\u20131119 (2023)","journal-title":"IEEE Trans. Image Process."},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, C., Zhu, H., Mao, Y., Fang, H.S., Lu, C.: Crowdpose: efficient crowded scenes pose estimation and a new benchmark. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10863\u201310872 (2019)","DOI":"10.1109\/CVPR.2019.01112"},{"key":"8_CR14","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. Multimedia 25, 1282\u20131293 (2022)","journal-title":"IEEE Trans. Multimedia"},{"key":"8_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.107069","volume":"98","author":"R Liao","year":"2020","unstructured":"Liao, R., Yu, S., An, W., Huang, Y.: A model-based gait recognition method with body pose and human prior knowledge. Pattern Recogn. 98, 107069 (2020)","journal-title":"Pattern Recogn."},{"key":"8_CR16","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"740","DOI":"10.1007\/978-3-319-10602-1_48","volume-title":"Computer Vision \u2013 ECCV 2014","author":"T-Y Lin","year":"2014","unstructured":"Lin, T.-Y., Maire, M., Belongie, S., Hays, J., Perona, P., Ramanan, D., Doll\u00e1r, P., Zitnick, C.L.: Microsoft COCO: common objects in context. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) ECCV 2014. LNCS, vol. 8693, pp. 740\u2013755. Springer, Cham (2014). https:\/\/doi.org\/10.1007\/978-3-319-10602-1_48"},{"key":"8_CR17","doi-asserted-by":"publisher","unstructured":"Lin, X., Yan, Z., Deng, X., Zheng, C., Yu, L.: Convformer: Plug-and-play cnn-style transformers for improving medical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention, pp. 642\u2013651. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-43901-8_61","DOI":"10.1007\/978-3-031-43901-8_61"},{"key":"8_CR18","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."},{"key":"8_CR19","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chen, H., Feng, R., Wu, S., Ji, S., Yang, B., Wang, X.: Deep dual consecutive network for human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 525\u2013534 (2021)","DOI":"10.1109\/CVPR46437.2021.00059"},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., Feng, R., Chen, H., Wu, S., Gao, Y., Gao, Y., Wang, X.: Temporal feature alignment and mutual information maximization for video-based human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11006\u201311016 (2022)","DOI":"10.1109\/CVPR52688.2022.01073"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ren, J., Wang, Z., Sun, W., Pan, J., Liu, J., Pang, J., Lin, L.: Lstm pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 5207\u20135215 (2018)","DOI":"10.1109\/CVPR.2018.00546"},{"key":"8_CR22","doi-asserted-by":"crossref","unstructured":"Ma, H., Wang, Z., Chen, Y., Kong, D., Chen, L., Liu, X., Yan, X., Tang, H., Xie, X.: Ppt: token-pruned pose transformer for monocular and multi-view human pose estimation. In: European Conference on Computer Vision, pp. 424\u2013442. Springer (2022)","DOI":"10.1007\/978-3-031-20065-6_25"},{"key":"8_CR23","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 11-14, 2016, Proceedings, Part VIII 14, pp. 483\u2013499. Springer (2016)","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"8_CR24","doi-asserted-by":"crossref","unstructured":"Peng, Z., Huang, W., Gu, S., Xie, L., Wang, Y., Jiao, J., Ye, Q.: Conformer: local features coupling global representations for visual recognition. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 367\u2013376 (2021)","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"8_CR25","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Poselet conditioned pictorial structures. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 588\u2013595 (2013)","DOI":"10.1109\/CVPR.2013.82"},{"key":"8_CR26","doi-asserted-by":"crossref","unstructured":"Pishchulin, L., Andriluka, M., Gehler, P., Schiele, B.: Strong appearance and expressive spatial models for human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3487\u20133494 (2013)","DOI":"10.1109\/ICCV.2013.433"},{"key":"8_CR27","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1007\/978-3-030-58565-5_3","volume-title":"Computer Vision \u2013 ECCV 2020","author":"U Rafi","year":"2020","unstructured":"Rafi, U., Doering, A., Leibe, B., Gall, J.: Self-supervised keypoint correspondences for multi-person pose estimation and tracking in videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12365, pp. 36\u201352. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58565-5_3"},{"issue":"4","key":"8_CR28","doi-asserted-by":"publisher","first-page":"4122","DOI":"10.1109\/TPAMI.2022.3188716","volume":"45","author":"H Shuai","year":"2022","unstructured":"Shuai, H., Wu, L., Liu, Q.: Adaptive multi-view and temporal fusing transformer for 3d human pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4122\u20134135 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"8_CR29","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":"8_CR30","unstructured":"Vaswani, A., et al.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"8_CR31","doi-asserted-by":"crossref","unstructured":"Wang, F., Li, Y.: Beyond physical connections: tree models in human pose estimation. In: Proceedings of the IEEE Conference on Computer Vsion and Pattern Recognition, pp. 596\u2013603 (2013)","DOI":"10.1109\/CVPR.2013.83"},{"key":"8_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103500","volume":"222","author":"L Wang","year":"2022","unstructured":"Wang, L., Chen, J., Liu, Y.: Frame-level refinement networks for skeleton-based gait recognition. Comput. Vis. Image Underst. 222, 103500 (2022)","journal-title":"Comput. Vis. Image Underst."},{"issue":"5","key":"8_CR33","doi-asserted-by":"publisher","first-page":"3941","DOI":"10.1007\/s11063-022-10794-w","volume":"54","author":"R Wang","year":"2022","unstructured":"Wang, R., Geng, F., Wang, X.: Mtpose: human pose estimation with high-resolution multi-scale transformers. Neural Process. Lett. 54(5), 3941\u20133964 (2022)","journal-title":"Neural Process. Lett."},{"key":"8_CR34","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.neucom.2022.06.033","volume":"501","author":"T Wang","year":"2022","unstructured":"Wang, T., Zhang, X.: Simplified-attention enhanced graph convolutional network for 3d human pose estimation. Neurocomputing 501, 231\u2013243 (2022)","journal-title":"Neurocomputing"},{"key":"8_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1007\/978-3-540-88690-7_53","volume-title":"Computer Vision \u2013 ECCV 2008","author":"Y Wang","year":"2008","unstructured":"Wang, Y., Mori, G.: Multiple tree models for occlusion and spatial constraints in human pose estimation. In: Forsyth, D., Torr, P., Zisserman, A. (eds.) ECCV 2008. LNCS, vol. 5304, pp. 710\u2013724. Springer, Heidelberg (2008). https:\/\/doi.org\/10.1007\/978-3-540-88690-7_53"},{"key":"8_CR36","doi-asserted-by":"crossref","unstructured":"Wei, S.E., Ramakrishna, V., Kanade, T., Sheikh, Y.: Convolutional pose machines. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4724\u20134732 (2016)","DOI":"10.1109\/CVPR.2016.511"},{"key":"8_CR37","doi-asserted-by":"publisher","unstructured":"Wu, Y., Cai, Y., Feng, R., Jin, C.: St 2 pe: spatial and temporal transformer for pose estimation. In: International Conference on Artificial Neural Networks, pp. 670\u2013681. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-15931-2_55","DOI":"10.1007\/978-3-031-15931-2_55"},{"key":"8_CR38","doi-asserted-by":"crossref","unstructured":"Xiao, B., Wu, H., Wei, Y.: Simple baselines for human pose estimation and tracking. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 466\u2013481 (2018)","DOI":"10.1007\/978-3-030-01231-1_29"},{"issue":"5","key":"8_CR39","doi-asserted-by":"publisher","first-page":"2005","DOI":"10.1007\/s00371-022-02460-y","volume":"39","author":"J Xu","year":"2023","unstructured":"Xu, J., Liu, W., Xing, W., Wei, X.: Mspenet: multi-scale adaptive fusion and position enhancement network for human pose estimation. Vis. Comput. 39(5), 2005\u20132019 (2023)","journal-title":"Vis. Comput."},{"key":"8_CR40","doi-asserted-by":"crossref","unstructured":"Xu, T., Takano, W.: Graph stacked hourglass networks for 3d human pose estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16105\u201316114 (2021)","DOI":"10.1109\/CVPR46437.2021.01584"},{"key":"8_CR41","first-page":"38571","volume":"35","author":"Y Xu","year":"2022","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose: simple vision transformer baselines for human pose estimation. Adv. Neural. Inf. Process. Syst. 35, 38571\u201338584 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"8_CR42","doi-asserted-by":"crossref","unstructured":"Xu, Y., Zhang, J., Zhang, Q., Tao, D.: Vitpose++: Vision transformer for generic body pose estimation. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)","DOI":"10.1109\/TPAMI.2023.3330016"},{"key":"8_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Y., Ren, Z., Li, H., Zhou, C., Wang, X., Hua, G.: Learning dynamics via graph neural networks for human pose estimation and tracking. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8074\u20138084 (2021)","DOI":"10.1109\/CVPR46437.2021.00798"},{"key":"8_CR44","unstructured":"Yu, S., Tan, D., Tan, T.: A framework for evaluating the effect of view angle, clothing and carrying condition on gait recognition. In: 18th international conference on pattern recognition (ICPR\u201906). vol.\u00a04, pp. 441\u2013444. IEEE (2006)"},{"key":"8_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, H., Hu, Z., Sun, Z., Zhao, M., Bi, S., Di, J.: A fused convolutional spatio-temporal progressive approach for 3d human pose estimation. The Visual Computer, pp. 1\u201313 (2023)","DOI":"10.1007\/s00371-023-03088-2"},{"key":"8_CR46","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":"8_CR47","doi-asserted-by":"crossref","unstructured":"Zhang, S.H., et al.: Pose2seg: detection free human instance segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 889\u2013898 (2019)","DOI":"10.1109\/CVPR.2019.00098"},{"key":"8_CR48","unstructured":"Zhao, Q., Zheng, C., Liu, M., Chen, C.: A single 2d pose with context is worth hundreds for 3d human pose estimation. Advances in Neural Information Processing Systems 36 (2024)"},{"key":"8_CR49","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":"8_CR50","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"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72338-4_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,9]],"date-time":"2025-10-09T07:49:58Z","timestamp":1759996198000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72338-4_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723377","9783031723384"],"references-count":50,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72338-4_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}