{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:17:46Z","timestamp":1779380266712,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819964970","type":"print"},{"value":"9789819964987","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-981-99-6498-7_16","type":"book-chapter","created":{"date-parts":[[2023,10,12]],"date-time":"2023-10-12T20:41:21Z","timestamp":1697143281000},"page":"176-187","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["3D Human Pose Estimation in\u00a0Video for\u00a0Human-Computer\/Robot Interaction"],"prefix":"10.1007","author":[{"given":"Rongtian","family":"Huo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Qi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaojie","family":"Ju","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,10,13]]},"reference":[{"issue":"4","key":"16_CR1","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1080\/10911359.2013.831288","volume":"24","author":"FB Mandal","year":"2014","unstructured":"Mandal, F.B.: Nonverbal communication in humans. J. Hum. Behav. Soc. Environ. 24(4), 417\u2013421 (2014)","journal-title":"J. Hum. Behav. Soc. Environ."},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Fankhauser, P., Bloesch, M., Rodriguez, D., Kaestner, R., Hutter, M., Siegwart, R.: Kinect v2 for mobile robot navigation: evaluation and modeling. In: 2015 International Conference on Advanced Robotics (ICAR), pp. 388\u2013394. IEEE (2015)","DOI":"10.1109\/ICAR.2015.7251485"},{"key":"16_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"332","DOI":"10.1007\/978-3-319-16808-1_23","volume-title":"Computer Vision \u2013 ACCV 2014","author":"S Li","year":"2015","unstructured":"Li, S., Chan, A.B.: 3D human pose estimation from monocular images with deep convolutional neural network. In: Cremers, D., Reid, I., Saito, H., Yang, M.-H. (eds.) ACCV 2014. LNCS, vol. 9004, pp. 332\u2013347. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-16808-1_23"},{"key":"16_CR4","doi-asserted-by":"crossref","unstructured":"Martinez, J., Hossain, R., Romero, J., Little, J.J.: A simple yet effective baseline for 3D human pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2640\u20132649 (2017)","DOI":"10.1109\/ICCV.2017.288"},{"key":"16_CR5","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":"16_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":"16_CR7","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1007\/978-3-030-58601-0_45","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Wang","year":"2020","unstructured":"Wang, J., Yan, S., Xiong, Y., Lin, D.: Motion guided 3D pose estimation from videos. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12358, pp. 764\u2013780. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58601-0_45"},{"key":"16_CR8","doi-asserted-by":"crossref","unstructured":"Tekin, B., M\u00e1rquez-Neila, P., Salzmann, M., Fua, P.: Learning to fuse 2D and 3D image cues for monocular body pose estimation. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3941\u20133950 (2017)","DOI":"10.1109\/ICCV.2017.425"},{"key":"16_CR9","unstructured":"Qammaz, A., Argyros, A.A.: MocapNET: ensemble of SNN encoders for 3D human pose estimation in RGB images. In: BMVC, p. 46 (2019)"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Li, W., Liu, H., Tang, H., Wang, P., Van 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":"16_CR11","doi-asserted-by":"crossref","unstructured":"Ge, L., et al.: 3D hand shape and pose estimation from a single RGB image. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10833\u201310842 (2019)","DOI":"10.1109\/CVPR.2019.01109"},{"key":"16_CR12","doi-asserted-by":"crossref","unstructured":"Zeng, A., Sun, X., Yang, L., Zhao, N., Liu, M., Xu, Q.: Learning skeletal graph neural networks for hard 3D pose estimation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11436\u201311445 (2021)","DOI":"10.1109\/ICCV48922.2021.01124"},{"key":"16_CR13","doi-asserted-by":"crossref","unstructured":"Pullen, K., Bregler, C.: Motion capture assisted animation: texturing and synthesis. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 501\u2013508 (2002)","DOI":"10.1145\/566570.566608"},{"key":"16_CR14","doi-asserted-by":"crossref","unstructured":"Wei, Y.: Deep-learning-based motion capture technology in film and television animation production. Secur. Commun. Netw. 2022 (2022)","DOI":"10.1155\/2022\/6040371"},{"issue":"4","key":"16_CR15","doi-asserted-by":"publisher","first-page":"1822","DOI":"10.1109\/TCYB.2019.2940276","volume":"51","author":"X Yu","year":"2019","unstructured":"Yu, X., et al.: Bayesian estimation of human impedance and motion intention for human-robot collaboration. IEEE Trans. Cybernet. 51(4), 1822\u20131834 (2019)","journal-title":"IEEE Trans. Cybernet."},{"issue":"12","key":"16_CR16","doi-asserted-by":"publisher","first-page":"9663","DOI":"10.1109\/TIE.2019.2898624","volume":"66","author":"Q Gao","year":"2019","unstructured":"Gao, Q., Liu, J., Ju, Z., Zhang, X.: Dual-hand detection for human-robot interaction by a parallel network based on hand detection and body pose estimation. IEEE Trans. Industr. Electron. 66(12), 9663\u20139672 (2019)","journal-title":"IEEE Trans. Industr. Electron."},{"issue":"1","key":"16_CR17","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1109\/TPAMI.2015.2430335","volume":"38","author":"HS Koppula","year":"2015","unstructured":"Koppula, H.S., Saxena, A.: Anticipating human activities using object affordances for reactive robotic response. IEEE Trans. Pattern Anal. Mach. Intell. 38(1), 14\u201329 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"16_CR18","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1016\/j.neucom.2019.02.066","volume":"390","author":"Q Gao","year":"2020","unstructured":"Gao, Q., Liu, J., Ju, Z.: Robust real-time hand detection and localization for space human-robot interaction based on deep learning. Neurocomputing 390, 198\u2013206 (2020)","journal-title":"Neurocomputing"},{"key":"16_CR19","doi-asserted-by":"crossref","unstructured":"Cheng, Y., Yi, P., Liu, R., Dong, J., Zhou, D., Zhang, Q.: Human-robot interaction method combining human pose estimation and motion intention recognition. In: 2021 IEEE 24th International Conference on Computer Supported Cooperative Work in Design (CSCWD), pp. 958\u2013963. IEEE (2021)","DOI":"10.1109\/CSCWD49262.2021.9437772"},{"issue":"5","key":"16_CR20","doi-asserted-by":"publisher","first-page":"e12490","DOI":"10.1111\/exsy.12490","volume":"38","author":"Q Gao","year":"2021","unstructured":"Gao, Q., Liu, J., Ju, Z.: Hand gesture recognition using multimodal data fusion and multiscale parallel convolutional neural network for human-robot interaction. Expert. Syst. 38(5), e12490 (2021)","journal-title":"Expert. Syst."},{"key":"16_CR21","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":"16_CR22","unstructured":"Kipf, T.N., Welling, M.: Semi-supervised classification with graph convolutional networks. arXiv preprint: arXiv:1609.02907 (2016)"},{"issue":"7","key":"16_CR23","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":"16_CR24","doi-asserted-by":"crossref","unstructured":"Lutz, S., Blythman, R., Ghosal, K., Moynihan, M., Simms, C., Smolic, A.: Jointformer: single-frame lifting transformer with error prediction and refinement for 3d human pose estimation. In: 2022 26th International Conference on Pattern Recognition (ICPR), pp. 1156\u20131163. IEEE (2022)","DOI":"10.1109\/ICPR56361.2022.9956366"},{"key":"16_CR25","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 2272\u20132281 (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"16_CR26","doi-asserted-by":"crossref","unstructured":"Lin, H., Chiu, Y., Wu, P.: AMPose: alternately mixed global-local attention model for 3D human pose estimation. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095351"},{"key":"16_CR27","doi-asserted-by":"crossref","unstructured":"Zhai, K., Nie, Q., Ouyang, B., Li, X., Yang, S.: HopFIR: hop-wise GraphFormer with intragroup joint refinement for 3D human pose estimation. arXiv preprint: arXiv:2302.14581 (2023)","DOI":"10.1109\/ICCV51070.2023.01376"},{"key":"16_CR28","unstructured":"Redmon, J., Farhadi, A.: YOLOV3: an incremental improvement. arXiv preprint: arXiv:1804.02767 (2018)"},{"key":"16_CR29","doi-asserted-by":"crossref","unstructured":"Fang, H.S., et al.: AlphaPose: whole-body regional multi-person pose estimation and tracking in real-time. IEEE Trans. Pattern Anal. Mach. Intell. (2022)","DOI":"10.1109\/TPAMI.2022.3222784"}],"container-title":["Lecture Notes in Computer Science","Intelligent Robotics and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-6498-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,8]],"date-time":"2025-02-08T09:57:27Z","timestamp":1739008647000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-6498-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819964970","9789819964987"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-6498-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"13 October 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIRA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Robotics and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icira2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icira2023.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}