{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T11:42:25Z","timestamp":1783597345894,"version":"3.55.0"},"publisher-location":"Cham","reference-count":57,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585945","type":"print"},{"value":"9783030585952","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58595-2_2","type":"book-chapter","created":{"date-parts":[[2020,11,20]],"date-time":"2020-11-20T03:29:28Z","timestamp":1605842968000},"page":"17-33","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":82,"title":["Hand-Transformer: Non-Autoregressive Structured Modeling for 3D Hand Pose Estimation"],"prefix":"10.1007","author":[{"given":"Lin","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianchao","family":"Tan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junsong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,20]]},"reference":[{"key":"2_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)"},{"key":"2_CR2","unstructured":"Bengio, S., Vinyals, O., Jaitly, N., Shazeer, N.: Scheduled sampling for sequence prediction with recurrent neural networks. In: NIPS (2015)"},{"key":"2_CR3","doi-asserted-by":"crossref","unstructured":"Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01231-1_41"},{"key":"2_CR4","doi-asserted-by":"crossref","unstructured":"Cai, Y., et al.: Exploiting spatial-temporal relationships for 3D pose estimation via graph convolutional networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00236"},{"key":"2_CR5","unstructured":"Chaudhari, S., Polatkan, G., Ramanath, R., Mithal, V.: An attentive survey of attention models. arXiv preprint arXiv:1904.02874 (2019)"},{"key":"2_CR6","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.neucom.2018.06.097","volume":"395","author":"X Chen","year":"2019","unstructured":"Chen, X., Wang, G., Guo, H., Zhang, C.: Pose guided structured region ensemble network for cascaded hand pose estimation. Neurocomputing 395, 138\u2013149 (2019)","journal-title":"Neurocomputing"},{"key":"2_CR7","doi-asserted-by":"publisher","first-page":"43425","DOI":"10.1109\/ACCESS.2018.2863540","volume":"6","author":"X Chen","year":"2018","unstructured":"Chen, X., Wang, G., Zhang, C., Kim, T.K., Ji, X.: Shpr-net: deep semantic hand pose regression from point clouds. IEEE Access 6, 43425\u201343439 (2018)","journal-title":"IEEE Access"},{"key":"2_CR8","doi-asserted-by":"crossref","unstructured":"Chen, Y., Tu, Z., Ge, L., Zhang, D., Chen, R., Yuan, J.: SO-HandNet: self-organizing network for 3D hand pose estimation with semi-supervised learning. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00706"},{"key":"2_CR9","doi-asserted-by":"crossref","unstructured":"Cho, K., et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv preprint arXiv:1406.1078 (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"2_CR10","unstructured":"Cordonnier, J.B., Loukas, A., Jaggi, M.: On the relationship between self-attention and convolutional layers. In: ICLR (2019)"},{"key":"2_CR11","unstructured":"Deng, X., Yang, S., Zhang, Y., Tan, P., Chang, L., Wang, H.: Hand3D: hand pose estimation using 3D neural network. arXiv preprint arXiv:1704.02224 (2017)"},{"key":"2_CR12","doi-asserted-by":"crossref","unstructured":"Du, K., Lin, X., Sun, Y., Ma, X.: Crossinfonet: multi-task information sharing based hand pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01013"},{"key":"2_CR13","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: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00050"},{"key":"2_CR14","doi-asserted-by":"crossref","unstructured":"Ge, L., Cai, Y., Weng, J., Yuan, J.: Hand pointnet: 3D hand pose estimation using point sets. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00878"},{"key":"2_CR15","doi-asserted-by":"crossref","unstructured":"Ge, L., Liang, H., Yuan, J., Thalmann, D.: Robust 3D hand pose estimation in single depth images: from single-view CNN to multi-view CNNs. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.391"},{"key":"2_CR16","doi-asserted-by":"crossref","unstructured":"Ge, L., Liang, H., Yuan, J., Thalmann, D.: 3D convolutional neural networks for efficient and robust hand pose estimation from single depth images. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.602"},{"key":"2_CR17","doi-asserted-by":"crossref","unstructured":"Ge, L., et al.: 3D hand shape and pose estimation from a single RGB image. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01109"},{"key":"2_CR18","doi-asserted-by":"crossref","unstructured":"Ge, L., Ren, Z., Yuan, J.: Point-to-point regression pointnet for 3D hand pose estimation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01261-8_29"},{"key":"2_CR19","unstructured":"Gu, J., Bradbury, J., Xiong, C., Li, V.O., Socher, R.: Non-autoregressive neural machine translation. arXiv preprint arXiv:1711.02281 (2017)"},{"key":"2_CR20","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, G., Chen, X., Zhang, C., Qiao, F., Yang, H.: Region ensemble network: improving convolutional network for hand pose estimation. In: ICIP (2017)","DOI":"10.1109\/ICIP.2017.8297136"},{"key":"2_CR21","doi-asserted-by":"crossref","unstructured":"Guo, J., Tan, X., He, D., Qin, T., Xu, L., Liu, T.Y.: Non-autoregressive neural machine translation with enhanced decoder input. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33013723"},{"key":"2_CR22","doi-asserted-by":"crossref","unstructured":"Hasson, Y., et al.: Learning joint reconstruction of hands and manipulated objects. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01208"},{"key":"2_CR23","doi-asserted-by":"crossref","unstructured":"Iqbal, U., Molchanov, P., Breuel Juergen Gall, T., Kautz, J.: Hand pose estimation via latent 2.5 d heatmap regression. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01252-6_8"},{"key":"2_CR24","unstructured":"Kim, Y., Denton, C., Hoang, L., Rush, A.M.: Structured attention networks. arXiv preprint arXiv:1702.00887 (2017)"},{"key":"2_CR25","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"2_CR26","doi-asserted-by":"crossref","unstructured":"Li, S., Lee, D.: Point-to-pose voting based hand pose estimation using residual permutation equivariant layer. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01220"},{"key":"2_CR27","unstructured":"Lin, J., Wu, Y., Huang, T.S.: Modeling the constraints of human hand motion. In: Proceedings Workshop on Human Motion (2000)"},{"key":"2_CR28","doi-asserted-by":"crossref","unstructured":"Moon, G., Chang, J., Lee, K.M.: V2V-PoseNet: voxel-to-voxel prediction network for accurate 3D hand and human pose estimation from a single depth map. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00533"},{"key":"2_CR29","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: Ganerated hands for real-time 3D hand tracking from monocular RGB. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00013"},{"key":"2_CR30","doi-asserted-by":"crossref","unstructured":"Oberweger, M., Lepetit, V.: DeepPrior++: improving fast and accurate 3D hand pose estimation. In: ICCV Workshop (2017)","DOI":"10.1109\/ICCVW.2017.75"},{"key":"2_CR31","unstructured":"Oberweger, M., Wohlhart, P., Lepetit, V.: Hands deep in deep learning for hand pose estimation. In: CVWW (2015)"},{"key":"2_CR32","doi-asserted-by":"crossref","unstructured":"Oberweger, M., Wohlhart, P., Lepetit, V.: Training a feedback loop for hand pose estimation. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.379"},{"key":"2_CR33","unstructured":"Qi, C.R., Su, H., Mo, K., Guibas, L.J.: PointNet: deep learning on point sets for 3D classification and segmentation. In: CVPR (2017)"},{"key":"2_CR34","unstructured":"Qi, C.R., Yi, L., Su, H., Guibas, L.J.: PointNet++: deep hierarchical feature learning on point sets in a metric space. In: NIPS (2017)"},{"key":"2_CR35","unstructured":"Ramachandran, P., Parmar, N., Vaswani, A., Bello, I., Levskaya, A., Shlens, J.: Stand-alone self-attention in vision models. In: NIPS (2019)"},{"key":"2_CR36","doi-asserted-by":"crossref","unstructured":"Sun, X., Wei, Y., Liang, S., Tang, X., Sun, J.: Cascaded hand pose regression. In: CVPR (2015)","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"2_CR37","unstructured":"Sun, Z., Li, Z., Wang, H., He, D., Lin, Z., Deng, Z.: Fast structured decoding for sequence models. In: NIPS (2019)"},{"key":"2_CR38","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: NIPS (2014)"},{"key":"2_CR39","doi-asserted-by":"crossref","unstructured":"Tang, D., Jin Chang, H., Tejani, A., Kim, T.K.: Latent regression forest: structured estimation of 3D articulated hand posture. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.490"},{"issue":"5","key":"2_CR40","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1145\/2629500","volume":"33","author":"J Tompson","year":"2014","unstructured":"Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans. Graph. (TOG) 33(5), 169 (2014)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"2_CR41","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS (2017)"},{"key":"2_CR42","doi-asserted-by":"crossref","unstructured":"Wan, C., Probst, T., Gool, L.V., Yao, A.: Self-supervised 3D hand pose estimation through training by fitting. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01111"},{"key":"2_CR43","doi-asserted-by":"crossref","unstructured":"Wan, C., Probst, T., Van Gool, L., Yao, A.: Crossing nets: dual generative models with a shared latent space for hand pose estimation. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.132"},{"key":"2_CR44","doi-asserted-by":"crossref","unstructured":"Wan, C., Probst, T., Van Gool, L., Yao, A.: Dense 3D regression for hand pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00540"},{"key":"2_CR45","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"2_CR46","doi-asserted-by":"crossref","unstructured":"Wang, Y., Tian, F., He, D., Qin, T., Zhai, C., Liu, T.Y.: Non-autoregressive machine translation with auxiliary regularization. In: AAAI (2019)","DOI":"10.1609\/aaai.v33i01.33015377"},{"key":"2_CR47","doi-asserted-by":"crossref","unstructured":"Xiong, F., et al.: A2J: anchor-to-joint regression network for 3D articulated pose estimation from a single depth image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00088"},{"key":"2_CR48","unstructured":"Xu, K., et al.: Show, attend and tell: neural image caption generation with visual attention. In: ICML (2015)"},{"key":"2_CR49","doi-asserted-by":"crossref","unstructured":"Yang, L., Li, S., Lee, D., Yao, A.: Aligning latent spaces for 3D hand pose estimation. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00242"},{"key":"2_CR50","unstructured":"Yuan, S., Ye, Q., Garcia-Hernando, G., Kim, T.K.: The 2017 hands in the million challenge on 3D hand pose estimation. arXiv preprint arXiv:1707.02237 (2017)"},{"key":"2_CR51","doi-asserted-by":"crossref","unstructured":"Yuan, S., Ye, Q., Stenger, B., Jain, S., Kim, T.K.: BigHand2.2M benchmark: hand pose dataset and state of the art analysis. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.279"},{"key":"2_CR52","doi-asserted-by":"crossref","unstructured":"Zhang, X., Li, Q., Mo, H., Zhang, W., Zheng, W.: End-to-end hand mesh recovery from a monocular RGB image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00244"},{"key":"2_CR53","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"186","DOI":"10.1007\/978-3-319-49409-8_17","volume-title":"Computer Vision \u2013 ECCV 2016 Workshops","author":"X Zhou","year":"2016","unstructured":"Zhou, X., Sun, X., Zhang, W., Liang, S., Wei, Y.: Deep kinematic pose regression. In: Hua, G., J\u00e9gou, H. (eds.) ECCV 2016. LNCS, vol. 9915, pp. 186\u2013201. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-49409-8_17"},{"key":"2_CR54","unstructured":"Zhou, X., Wan, Q., Zhang, W., Xue, X., Wei, Y.: Model-based deep hand pose estimation. In: IJCAI (2016)"},{"key":"2_CR55","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Lu, J., Du, K., Lin, X., Sun, Y., Ma, X.: HBE: hand branch ensemble network for real-time 3D hand pose estimation. In: ECCV (2018)","DOI":"10.1007\/978-3-030-01264-9_31"},{"key":"2_CR56","doi-asserted-by":"crossref","unstructured":"Zhu, X., Cheng, D., Zhang, Z., Lin, S., Dai, J.: An empirical study of spatial attention mechanisms in deep networks. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00679"},{"key":"2_CR57","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Brox, T.: Learning to estimate 3D hand pose from single RGB images. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.525"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58595-2_2","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,20]],"date-time":"2024-11-20T00:03:44Z","timestamp":1732061024000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58595-2_2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585945","9783030585952"],"references-count":57,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58595-2_2","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"20 November 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1360","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"27% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"7","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}