{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T19:09:51Z","timestamp":1743016191704,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":26,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819603503"},{"type":"electronic","value":"9789819603510"}],"license":[{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:00:00Z","timestamp":1732060800000},"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\/978-981-96-0351-0_18","type":"book-chapter","created":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T18:48:11Z","timestamp":1732387691000},"page":"243-255","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Real-Time Lightweight 3D Hand-Object Pose Estimation Using Temporal Graph Convolution Networks"],"prefix":"10.1007","author":[{"given":"Yue","family":"Yin","sequence":"first","affiliation":[]},{"given":"Chris","family":"McCarthy","sequence":"additional","affiliation":[]},{"given":"Dana","family":"Rezazadegan","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,11,20]]},"reference":[{"key":"18_CR1","unstructured":"Bai, S., Kolter, J., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Doosti, B., Naha, S., Mirbagheri, M., Crandall, D.J.: 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":"18_CR3","doi-asserted-by":"crossref","unstructured":"Garcia-Hernando, G., Yuan, S., Baek, S., Kim, T.K.: First-person hand action benchmark with RGB-D videos and 3D hand pose annotations. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 409\u2013419 (2018)","DOI":"10.1109\/CVPR.2018.00050"},{"issue":"9","key":"18_CR4","doi-asserted-by":"publisher","first-page":"4422","DOI":"10.1109\/TIP.2018.2834824","volume":"27","author":"L Ge","year":"2018","unstructured":"Ge, L., Liang, H., Yuan, J., Thalmann, D.: Robust 3D hand pose estimation from single depth images using multi-view CNNs. IEEE Trans. Image Process. 27(9), 4422\u20134436 (2018)","journal-title":"IEEE Trans. Image Process."},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Hampali, S., Rad, M., Oberweger, M., Lepetit, V.: Honnotate: a method for 3D annotation of hand and object poses. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3196\u20133206 (2020)","DOI":"10.1109\/CVPR42600.2020.00326"},{"key":"18_CR6","unstructured":"Han, B., et al.: Co-teaching: robust training of deep neural networks with extremely noisy labels. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Han, K., Wang, Y., Tian, Q., Guo, J., Xu, C., Xu, C.: Ghostnet: more features from cheap operations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1580\u20131589 (2020)","DOI":"10.1109\/CVPR42600.2020.00165"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11807\u201311816 (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"18_CR9","doi-asserted-by":"crossref","unstructured":"Howard, A., et\u00a0al.: Searching for mobilenetv3. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1314\u20131324 (2019)","DOI":"10.1109\/ICCV.2019.00140"},{"key":"18_CR10","unstructured":"Howard, A., et al.: Mobilenets: efficient convolutional neural networks for mobile vision applications. arXiv preprint arXiv:1704.04861 (2017)"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Huang, L., Tan, J., Meng, J., Liu, J., Yuan, J.: Hot-net: non-autoregressive transformer for 3d hand-object pose estimation. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 3136\u20133145 (2020)","DOI":"10.1145\/3394171.3413775"},{"key":"18_CR12","unstructured":"Huang, Z., Xu, W., Yu, K.: Bidirectional LSTM-CRF models for sequence tagging. arXiv preprint arXiv:1508.01991 (2015)"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Khaleghi, L., Marshall, J., Etemad, A.: Learning sequential contexts using transformer for 3D hand pose estimation. arXiv preprint arXiv:2206.00171 (2022)","DOI":"10.1109\/ICPR56361.2022.9955633"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Khaleghi, L., Sepas-Moghaddam, A., Marshall, J., Etemad, A.: Multi-view video-based 3D hand pose estimation. IEEE Trans. Artif. Intell. (2022)","DOI":"10.1109\/TAI.2022.3195968"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Lea, C., Flynn, M., Vidal, R., Reiter, A., Hager, G.: Temporal convolutional networks for action segmentation and detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165 (2017)","DOI":"10.1109\/CVPR.2017.113"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Li, M., Gao, Y., Sang, N.: Exploiting learnable joint groups for hand pose estimation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a035, pp. 1921\u20131929 (2021)","DOI":"10.1609\/aaai.v35i3.16287"},{"key":"18_CR17","doi-asserted-by":"crossref","unstructured":"Liu, Z., Li, J., Shen, Z., Huang, G., Yan, S., Zhang, C.: Learning efficient convolutional networks through network slimming. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 2736\u20132744 (2017)","DOI":"10.1109\/ICCV.2017.298"},{"key":"18_CR18","first-page":"64","volume":"5","author":"L Medsker","year":"2001","unstructured":"Medsker, L., Jain, L.: Recurrent neural networks. Des. Appl. 5, 64\u201367 (2001)","journal-title":"Des. Appl."},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: Ganerated hands for real-time 3d hand tracking from monocular RGB. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 49\u201359 (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"issue":"8","key":"18_CR20","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1109\/TPAMI.2019.2907951","volume":"42","author":"M Oberweger","year":"2019","unstructured":"Oberweger, M., Wohlhart, P., Lepetit, V.: Generalized feedback loop for joint hand-object pose estimation. IEEE Trans. Pattern Anal. Mach. Intell. 42(8), 1898\u20131912 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Rayat Imtiaz\u00a0Hossain, M., Little, J.J.: Exploiting temporal information for 3D pose estimation. arXiv e-prints pp. arXiv\u20131711 (2017)","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Tekin, B., Bogo, F., Pollefeys, M.: H+ o: unified egocentric recognition of 3D hand-object poses and interactions. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4511\u20134520 (2019)","DOI":"10.1109\/CVPR.2019.00464"},{"key":"18_CR23","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":"18_CR24","doi-asserted-by":"crossref","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)","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Yin, Y., McCarthy, C., Rezazadegan, D.: Real-time 3D hand-object pose estimation for mobile devices. In: 2021 IEEE International Conference on Image Processing (ICIP), pp. 3288\u20133292. IEEE (2021)","DOI":"10.1109\/ICIP42928.2021.9506135"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4903\u20134911 (2017)","DOI":"10.1109\/ICCV.2017.525"}],"container-title":["Lecture Notes in Computer Science","AI 2024: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-0351-0_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,23]],"date-time":"2024-11-23T19:06:13Z","timestamp":1732388773000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-0351-0_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,20]]},"ISBN":["9789819603503","9789819603510"],"references-count":26,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-0351-0_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,20]]},"assertion":[{"value":"20 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"AI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australasian Joint Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Melbourne, VIC","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","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":"25 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"37","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ausai2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ajcai2024.org\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}