{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T18:14:39Z","timestamp":1781633679571,"version":"3.54.5"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031784552","type":"print"},{"value":"9783031784569","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,3]],"date-time":"2024-12-03T00:00:00Z","timestamp":1733184000000},"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":[[2025]]},"DOI":"10.1007\/978-3-031-78456-9_30","type":"book-chapter","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T11:24:36Z","timestamp":1733138676000},"page":"470-486","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["SPiKE: 3D Human Pose from Point Cloud Sequences"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0219-9063","authenticated-orcid":false,"given":"Irene","family":"Ballester","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-7231-0430","authenticated-orcid":false,"given":"Ond\u0159ej","family":"Peterka","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5217-2854","authenticated-orcid":false,"given":"Martin","family":"Kampel","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,3]]},"reference":[{"key":"30_CR1","doi-asserted-by":"crossref","unstructured":"Arnab, A., Doersch, C., Zisserman, A.: Exploiting temporal context for 3D human pose estimation in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3395\u20133404 (2019)","DOI":"10.1109\/CVPR.2019.00351"},{"key":"30_CR2","doi-asserted-by":"crossref","unstructured":"Ballester, I., Kampel, M.: Action Recognition from 4D Point Clouds for Privacy-Sensitive Scenarios in Assistive Contexts. In: International Conference on Computers Helping People with Special Needs. pp. 359\u2013364. Springer (2024)","DOI":"10.1007\/978-3-031-62849-8_44"},{"key":"30_CR3","doi-asserted-by":"crossref","unstructured":"Carreira, J., Agrawal, P., Fragkiadaki, K., Malik, J.: Human Pose Estimation with Iterative Error Feedback. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 4733\u20134742 (2016)","DOI":"10.1109\/CVPR.2016.512"},{"key":"30_CR4","doi-asserted-by":"crossref","unstructured":"Choy, C., Gwak, J., Savarese, S.: 4D Spatio-Temporal ConvNets: Minkowski Convolutional Neural Networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 3075\u20133084 (2019)","DOI":"10.1109\/CVPR.2019.00319"},{"issue":"2","key":"30_CR5","doi-asserted-by":"publisher","first-page":"722","DOI":"10.1109\/TITS.2020.3023541","volume":"23","author":"Y Cui","year":"2021","unstructured":"Cui, Y., Chen, R., Chu, W., Chen, L., Tian, D., Li, Y., Cao, D.: Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Review. IEEE Trans. Intell. Transp. Syst. 23(2), 722\u2013739 (2021)","journal-title":"IEEE Trans. Intell. Transp. Syst."},{"key":"30_CR6","doi-asserted-by":"crossref","unstructured":"D\u2019Eusanio, A., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: RefiNet: 3D Human Pose Refinement with Depth Maps. In: 2020 25th International Conference on Pattern Recognition (ICPR). pp. 2320\u20132327. IEEE (2021)","DOI":"10.1109\/ICPR48806.2021.9412451"},{"key":"30_CR7","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/j.patrec.2023.03.005","volume":"171","author":"A D\u2019Eusanio","year":"2023","unstructured":"D\u2019Eusanio, A., Simoni, A., Pini, S., Borghi, G., Vezzani, R., Cucchiara, R.: Depth-based 3D human pose refinement: Evaluating the RefiNet framework. Pattern Recogn. Lett. 171, 185\u2013191 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"30_CR8","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In: NAACL-HLT. pp. 4171\u20134186. Association for Computational Linguistics (2019)"},{"key":"30_CR9","doi-asserted-by":"crossref","unstructured":"Diller, C., Funkhouser, T., Dai, A.: Forecasting Characteristic 3D Poses of Human Actions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 15914\u201315923 (2022)","DOI":"10.1109\/CVPR52688.2022.01545"},{"key":"30_CR10","unstructured":"Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: Knowledge Discovery and Data Mining. p. 226-231. AAAI Press (1996)"},{"key":"30_CR11","unstructured":"Fan, B., Zheng, W., Feng, J., Zhou, J.: LiDAR-HMR: 3D Human Mesh Recovery from LiDAR. arXiv preprint arXiv:2311.11971 (2023)"},{"key":"30_CR12","doi-asserted-by":"crossref","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point 4D Transformer Networks for Spatio-Temporal Modeling in Point Cloud Videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 14204\u201314213 (2021)","DOI":"10.1109\/CVPR46437.2021.01398"},{"issue":"2","key":"30_CR13","doi-asserted-by":"publisher","first-page":"2181","DOI":"10.1109\/TPAMI.2022.3161735","volume":"45","author":"H Fan","year":"2023","unstructured":"Fan, H., Yang, Y., Kankanhalli, M.: Point Spatio-Temporal Transformer Networks for Point Cloud Video Modeling. IEEE Trans. Pattern Anal. Mach. Intell. 45(2), 2181\u20132192 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR14","unstructured":"Fan, H., Yu, X., Ding, Y., Yang, Y., Kankanhalli, M.: PSTNet: Point Spatio-Temporal Convolution on Point Cloud Sequences. In: International Conference on Learning Representations (2021)"},{"issue":"4","key":"30_CR15","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TPAMI.2016.2558148","volume":"39","author":"B Fernando","year":"2016","unstructured":"Fernando, B., Gavves, E., Oramas, J., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 773\u2013787 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR16","doi-asserted-by":"crossref","unstructured":"Garau, N., Bisagno, N., Br\u00f3dka, P., Conci, N.: DECA: Deep viewpoint-Equivariant human pose estimation using Capsule Autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 11677\u201311686 (2021)","DOI":"10.1109\/ICCV48922.2021.01147"},{"key":"30_CR17","doi-asserted-by":"crossref","unstructured":"Graham, B., Van\u00a0der Maaten, L.: Submanifold Sparse Convolutional Networks. arXiv preprint arXiv:1706.01307 (2017)","DOI":"10.1109\/CVPR.2018.00961"},{"issue":"3","key":"30_CR18","doi-asserted-by":"publisher","first-page":"1034","DOI":"10.1109\/JBHI.2021.3107532","volume":"26","author":"X Gu","year":"2021","unstructured":"Gu, X., Guo, Y., Yang, G.Z., Lo, B.: Cross-Domain Self-Supervised Complete Geometric Representation Learning for Real-Scanned Point Cloud Based Pathological Gait Analysis. IEEE J. Biomed. Health Inform. 26(3), 1034\u20131044 (2021)","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"30_CR19","doi-asserted-by":"crossref","unstructured":"Haque, A., Peng, B., Luo, Z., Alahi, A., Yeung, S., Fei-Fei, L.: Towards Viewpoint Invariant 3D Human Pose Estimation. arXiv preprint arXiv:1603.07076 (2016)","DOI":"10.1007\/978-3-319-46448-0_10"},{"key":"30_CR20","unstructured":"Hinton, G.E., Sabour, S., Frosst, N.: Matrix capsules with EM routing. In: International Conference on Learning Representations (2018)"},{"key":"30_CR21","unstructured":"Jeong, D.C., Liu, H., Salazar, S., Jiang, J., Kitts, C.A.: SoloPose: One-Shot Kinematic 3D Human Pose Estimation with Video Data Augmentation. arXiv preprint arXiv:2312.10195 (2023)"},{"key":"30_CR22","doi-asserted-by":"crossref","unstructured":"Liu, X., Yan, M., Bohg, J.: Meteornet: Deep Learning on Dynamic 3D Point Cloud Sequences. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 9246\u20139255 (2019)","DOI":"10.1109\/ICCV.2019.00934"},{"key":"30_CR23","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":"30_CR24","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J.Y., Lee, K.M.: V2V-PoseNet: Voxel-to-Voxel Prediction Network for Accurate 3D Hand and Human Pose Estimation from a Single Depth Map. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 5079\u20135088 (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"30_CR25","doi-asserted-by":"crossref","unstructured":"Mucha, W., Kampel, M.: Addressing privacy concerns in depth sensors. In: International Conference on Computers Helping People with Special Needs. pp. 526\u2013533. Springer (2022)","DOI":"10.1007\/978-3-031-08645-8_62"},{"key":"30_CR26","doi-asserted-by":"crossref","unstructured":"Pavlakos, G., Zhou, X., Derpanis, K.G., Daniilidis, K.: Coarse-to-Fine Volumetric Prediction for Single-Image 3D Human Pose. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 7025\u20137034 (2017)","DOI":"10.1109\/CVPR.2017.139"},{"key":"30_CR27","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: Deep Learning on Point Sets for 3D Classification and Segmentation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 652\u2013660 (2017)"},{"key":"30_CR28","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: Deep Hierarchical Feature Learning on Point Sets in a Metric Space. Advances in Neural Information Processing Systems 30 (2017)"},{"key":"30_CR29","doi-asserted-by":"crossref","unstructured":"Rempe, D., Birdal, T., Hertzmann, A., Yang, J., Sridhar, S., Guibas, L.J.: HuMoR: 3D Human Motion Model for Robust Pose Estimation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11488\u201311499 (2021)","DOI":"10.1109\/ICCV48922.2021.01129"},{"issue":"2","key":"30_CR30","doi-asserted-by":"publisher","first-page":"2163","DOI":"10.1609\/aaai.v37i2.25310","volume":"37","author":"P Ren","year":"2023","unstructured":"Ren, P., Chen, Y., Hao, J., Sun, H., Qi, Q., Wang, J., Liao, J.: Two Heads Are Better than One: Image-Point Cloud Network for Depth-Based 3D Hand Pose Estimation. Proceedings of the AAAI Conference on Artificial Intelligence 37(2), 2163\u20132171 (2023)","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence"},{"issue":"3","key":"30_CR31","first-page":"3200","volume":"45","author":"Z Sun","year":"2022","unstructured":"Sun, Z., Ke, Q., Rahmani, H., Bennamoun, M., Wang, G., Liu, J.: Human Action Recognition from Various Data Modalities: A Review. IEEE Trans. Pattern Anal. Mach. Intell. 45(3), 3200\u20133225 (2022)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"30_CR32","doi-asserted-by":"crossref","unstructured":"Teepe, T., Gilg, J., Herzog, F., H\u00f6rmann, S., Rigoll, G.: Towards a Deeper Understanding of Skeleton-based Gait Recognition. arXiv:2204.07855 (2022)","DOI":"10.1109\/CVPRW56347.2022.00163"},{"key":"30_CR33","doi-asserted-by":"crossref","unstructured":"Uhrig, J., Schneider, N., Schneider, L., Franke, U., Brox, T., Geiger, A.: Sparsity Invariant CNNs. In: 2017 International Conference on 3D Vision. pp. 11\u201320 (2017)","DOI":"10.1109\/3DV.2017.00012"},{"key":"30_CR34","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is All you Need. Advances in Neural Information Processing systems 30 (2017)"},{"key":"30_CR35","doi-asserted-by":"crossref","unstructured":"Wang, K., Lin, L., Ren, C., Zhang, W., Sun, W.: Convolutional Memory Blocks for Depth Data Representation Learning. In: IJCAI. pp. 2790\u20132797 (2018)","DOI":"10.24963\/ijcai.2018\/387"},{"key":"30_CR36","doi-asserted-by":"crossref","unstructured":"Wang, K., Zhai, S., Cheng, H., Liang, X., Lin, L.: Human Pose Estimation from Depth Images via Inference Embedded Multi-task Learning. In: Proceedings of the ACM International Conference on Multimedia. pp. 1227\u20131236 (2016)","DOI":"10.1145\/2964284.2964322"},{"key":"30_CR37","doi-asserted-by":"crossref","unstructured":"Wang, Y., Xiao, Y., Xiong, F., Jiang, W., Cao, Z., Zhou, J.T., Yuan, J.: 3D Dynamic Voxel for Action Recognition in Depth Video. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 511\u2013520 (2020)","DOI":"10.1109\/CVPR42600.2020.00059"},{"issue":"5","key":"30_CR38","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3326362","volume":"38","author":"Y Wang","year":"2019","unstructured":"Wang, Y., Sun, Y., Liu, Z., Sarma, S.E., Bronstein, M.M., Solomon, J.M.: Dynamic Graph CNN for Learning on Point Clouds. ACM Transactions on Graphics 38(5), 1\u201312 (2019)","journal-title":"ACM Transactions on Graphics"},{"key":"30_CR39","doi-asserted-by":"crossref","unstructured":"Wen, H., Liu, Y., Huang, J., Duan, B., Yi, L.: Point Primitive Transformer for Long-Term 4D Point Cloud Video Understanding. In: European Conference on Computer Vision. pp. 19\u201335. Springer (2022)","DOI":"10.1007\/978-3-031-19818-2_2"},{"key":"30_CR40","doi-asserted-by":"crossref","unstructured":"Wen, Y., Pan, H., Yang, L., Pan, J., Komura, T., Wang, W.: Hierarchical Temporal Transformer for 3D Hand Pose Estimation and Action Recognition from Egocentric RGB Videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 21243\u201321253 (2023)","DOI":"10.1109\/CVPR52729.2023.02035"},{"key":"30_CR41","doi-asserted-by":"crossref","unstructured":"Weng, Z., Gorban, A.S., Ji, J., Najibi, M., Zhou, Y., Anguelov, D.: 3D Human Keypoints Estimation From Point Clouds in the Wild Without Human Labels. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 1158\u20131167 (2023)","DOI":"10.1109\/CVPR52729.2023.00118"},{"key":"30_CR42","doi-asserted-by":"crossref","unstructured":"Xiong, F., Zhang, B., Xiao, Y., Cao, Z., Yu, T., Zhou, J.T., Yuan, J.: A2J: Anchor-to-Joint Regression Network for 3D Articulated Pose Estimation from a Single Depth Image. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 793\u2013802 (2019)","DOI":"10.1109\/ICCV.2019.00088"},{"key":"30_CR43","doi-asserted-by":"crossref","unstructured":"Ye, D., Xie, Y., Chen, W., Zhou, Z., Ge, L., Foroosh, H.: LPFormer: LiDAR pose estimation transformer with multi-task network. In: 2024 IEEE International Conference on Robotics and Automation (ICRA). pp. 16432\u201316438. IEEE (2024)","DOI":"10.1109\/ICRA57147.2024.10611405"},{"issue":"5","key":"30_CR44","doi-asserted-by":"publisher","first-page":"1851","DOI":"10.1109\/TVCG.2020.2973076","volume":"26","author":"Z Zhang","year":"2020","unstructured":"Zhang, Z., Hu, L., Deng, X., Xia, S.: Weakly Supervised Adversarial Learning for 3D Human Pose Estimation from Point Clouds. IEEE Trans. Visual Comput. Graphics 26(5), 1851\u20131859 (2020)","journal-title":"IEEE Trans. Visual Comput. Graphics"},{"key":"30_CR45","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Hu, L., Deng, X., Xia, S.: Sequential 3D Human Pose Estimation Using Adaptive Point Cloud Sampling Strategy. In: Proceedings of the Thirtieth International Joint Conference on Artificial Intelligence, IJCAI-21. pp. 1330\u20131337 (2021)","DOI":"10.24963\/ijcai.2021\/184"},{"key":"30_CR46","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"},{"issue":"1","key":"30_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3603618","volume":"56","author":"C Zheng","year":"2023","unstructured":"Zheng, C., Wu, W., Chen, C., Yang, T., Zhu, S., Shen, J., Kehtarnavaz, N., Shah, M.: Deep Learning-Based Human Pose Estimation: A Survey. ACM Comput. Surv. 56(1), 1\u201337 (2023)","journal-title":"ACM Comput. Surv."},{"key":"30_CR48","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Dong, H., El\u00a0Saddik, A.: Learning to Estimate 3D Human Pose From Point Cloud. IEEE Sensors Journal pp.\u00a01\u20131 (2020)","DOI":"10.1109\/JSEN.2020.2999849"},{"key":"30_CR49","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"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-78456-9_30","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T12:14:52Z","timestamp":1733141692000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-78456-9_30"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,3]]},"ISBN":["9783031784552","9783031784569"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-78456-9_30","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,3]]},"assertion":[{"value":"3 December 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"1 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icpr2024.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}