{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T12:25:00Z","timestamp":1784204700713,"version":"3.55.0"},"publisher-location":"Cham","reference-count":47,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585648","type":"print"},{"value":"9783030585655","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\/978-3-030-58565-5_33","type":"book-chapter","created":{"date-parts":[[2020,11,11]],"date-time":"2020-11-11T12:03:19Z","timestamp":1605096199000},"page":"548-564","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":235,"title":["InterHand2.6M: A Dataset and Baseline for 3D Interacting Hand Pose Estimation from a Single RGB Image"],"prefix":"10.1007","author":[{"given":"Gyeongsik","family":"Moon","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shoou-I","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"He","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Takaaki","family":"Shiratori","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyoung Mu","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,11,12]]},"reference":[{"key":"33_CR1","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"640","DOI":"10.1007\/978-3-642-33783-3_46","volume-title":"Computer Vision \u2013 ECCV 2012","author":"L Ballan","year":"2012","unstructured":"Ballan, L., Taneja, A., Gall, J., Van Gool, L., Pollefeys, M.: Motion capture of hands in action using discriminative salient points. In: Fitzgibbon, A., Lazebnik, S., Perona, P., Sato, Y., Schmid, C. (eds.) ECCV 2012. LNCS, vol. 7577, pp. 640\u2013653. Springer, Heidelberg (2012). https:\/\/doi.org\/10.1007\/978-3-642-33783-3_46"},{"key":"33_CR2","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"678","DOI":"10.1007\/978-3-030-01231-1_41","volume-title":"ECCV 2018","author":"Y Cai","year":"2018","unstructured":"Cai, Y., Ge, L., Cai, J., Yuan, J.: Weakly-supervised 3D hand pose estimation from monocular RGB images. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 678\u2013694. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_41"},{"key":"33_CR3","unstructured":"Chen, L., et al.: Generating realistic training images based on tonality-alignment generative adversarial networks for hand pose estimation. arXiv preprint arXiv:1811.09916 (2018)"},{"issue":"3\u20134","key":"33_CR4","first-page":"131","volume":"17","author":"R Arrabales","year":"2010","unstructured":"Arrabales, R., Ledezma, A., Sanchis, A.: ConsScale: a pragmatic scale for measuring the level of consciousness in artificial agents. J. Conscious. Stud. 17(3\u20134), 131\u2013164 (2010)","journal-title":"J. Conscious. Stud."},{"key":"33_CR5","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":"33_CR6","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":"33_CR7","doi-asserted-by":"crossref","unstructured":"Guo, H., Wang, G., Chen, X., Zhang, C., Qiao, F., Yand, H.: Region ensemble network: improving convolutional network for hand pose estimation. ICIP (2017)","DOI":"10.1109\/ICIP.2017.8297136"},{"key":"33_CR8","doi-asserted-by":"crossref","unstructured":"Ha, H., Perdoch, M., Alismail, H., So Kweon, I., Sheikh, Y.: Deltille grids for geometric camera calibration. In: CVPR (2017)","DOI":"10.1109\/ICCV.2017.571"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: CVPR (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"33_CR10","unstructured":"Ioffe, S., Szegedy, C.: Batch normalization: accelerating deep network training by reducing internal covariate shift. In: ICML (2015)"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1007\/978-3-030-01252-6_8","volume-title":"Computer Vision \u2013 ECCV 2018","author":"U Iqbal","year":"2018","unstructured":"Iqbal, U., Molchanov, P., Breuel, T., Gall, J., Kautz, J.: Hand pose estimation via latent 2.5D heatmap regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11215, pp. 125\u2013143. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01252-6_8"},{"key":"33_CR12","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: ICLR (2014)"},{"key":"33_CR13","doi-asserted-by":"crossref","unstructured":"de La Gorce, M., Fleet, D.J., Paragios, N.: Model-based 3D hand pose estimation from monocular video. In: IEEE TPAMI (2011)","DOI":"10.1109\/TPAMI.2011.33"},{"key":"33_CR14","unstructured":"Li, W., et al.: Rethinking on multi-stage networks for human pose estimation. arXiv preprint arXiv:1901.00148 (2019)"},{"key":"33_CR15","unstructured":"Moon, G., Ju, Y.C., 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)"},{"key":"33_CR16","doi-asserted-by":"crossref","unstructured":"Moon, G., Ju, Y.C., Lee, K.M.: Camera distance-aware top-down approach for 3D multi-person pose estimation from a single RGB image. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.01023"},{"key":"33_CR17","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":"33_CR18","doi-asserted-by":"crossref","unstructured":"Mueller, F., et al.: Real-time pose and shape reconstruction of two interacting hands with a single depth camera. In: ACM TOG (2019)","DOI":"10.1145\/3306346.3322958"},{"key":"33_CR19","doi-asserted-by":"crossref","unstructured":"Mueller, F., Mehta, D., Sotnychenko, O., Sridhar, S., Casas, D., Theobalt, C.: Real-time hand tracking under occlusion from an egocentric RGB-D sensor. In: ICCV (2017)","DOI":"10.1109\/ICCV.2017.131"},{"key":"33_CR20","doi-asserted-by":"crossref","unstructured":"Oikonomidis, I., Kyriazis, N., Argyros, A.A.: Tracking the articulated motion of two strongly interacting hands. In: CVPR (2012)","DOI":"10.1109\/CVPR.2012.6247885"},{"key":"33_CR21","unstructured":"Paszke, A., et al.: Automatic differentiation in pytorch (2017)"},{"key":"33_CR22","doi-asserted-by":"crossref","unstructured":"Qian, C., Sun, X., Wei, Y., Tang, X., Sun, J.: Realtime and robust hand tracking from depth. In: CVPR (2014)","DOI":"10.1109\/CVPR.2014.145"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Romero, J., Tzionas, D., Black, M.J.: Embodied hands: modeling and capturing hands and bodies together. In: ACM TOG (2017)","DOI":"10.1145\/3130800.3130883"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Russakovsky, O., et al.: ImageNet large scale visual recognition challenge. IJCV (2015)","DOI":"10.1007\/s11263-015-0816-y"},{"key":"33_CR25","doi-asserted-by":"crossref","unstructured":"Sharp, T., et al.: Accurate, robust, and flexible real-time hand tracking. In: ACM Conference on Human Factors in Computing Systems (2015)","DOI":"10.1145\/2702123.2702179"},{"key":"33_CR26","doi-asserted-by":"crossref","unstructured":"Simon, T., Joo, H., Matthews, I., Sheikh, Y.: Hand keypoint detection in single images using multiview bootstrapping. In: CVPR (2017)","DOI":"10.1109\/CVPR.2017.494"},{"key":"33_CR27","doi-asserted-by":"crossref","unstructured":"Spurr, A., Song, J., Park, S., Hilliges, O.: Cross-modal deep variational hand pose estimation. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00017"},{"key":"33_CR28","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/978-3-319-46475-6_19","volume-title":"ECCV 2016","author":"S Sridhar","year":"2016","unstructured":"Sridhar, S., Mueller, F., Zollh\u00f6fer, M., Casas, D., Oulasvirta, A., Theobalt, C.: Real-time joint tracking of a hand manipulating an object from RGB-D input. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 294\u2013310. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_19"},{"key":"33_CR29","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":"33_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1007\/978-3-030-01231-1_33","volume-title":"Computer Vision \u2013 ECCV 2018","author":"X Sun","year":"2018","unstructured":"Sun, X., Xiao, B., Wei, F., Liang, S., Wei, Y.: Integral human pose regression. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11210, pp. 536\u2013553. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01231-1_33"},{"key":"33_CR31","doi-asserted-by":"crossref","unstructured":"Tagliasacchi, A., Schr\u00f6der, M., Tkach, A., Bouaziz, S., Botsch, M., Pauly, M.: Robust articulated-ICP for real-time hand tracking. In: Computer Graphics Forum (2015)","DOI":"10.1111\/cgf.12700"},{"key":"33_CR32","unstructured":"Tan, M., Le, Q.V.: EfficientNet: rethinking model scaling for convolutional neural networks. In: ICML (2019)"},{"key":"33_CR33","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"},{"key":"33_CR34","doi-asserted-by":"crossref","unstructured":"Tang, D., Taylor, J., Kohli, P., Keskin, C., Kim, T.K., Shotton, J.: Opening the black box: hierarchical sampling optimization for estimating human hand pose. In: ICCV (2015)","DOI":"10.1109\/ICCV.2015.380"},{"key":"33_CR35","doi-asserted-by":"crossref","unstructured":"Taylor, J., et al.: Efficient and precise interactive hand tracking through joint, continuous optimization of pose and correspondences. ACM Trans. Graph. (TOG) 35, 143 (2016)","DOI":"10.1145\/2897824.2925965"},{"key":"33_CR36","doi-asserted-by":"crossref","unstructured":"Tompson, J., Stein, M., Lecun, Y., Perlin, K.: Real-time continuous pose recovery of human hands using convolutional networks. ACM TOG (2014)","DOI":"10.1145\/2629500"},{"key":"33_CR37","doi-asserted-by":"crossref","unstructured":"Tzionas, D., Ballan, L., Srikantha, A., Aponte, P., Pollefeys, M., Gall, J.: Capturing hands in action using discriminative salient points and physics simulation. IJCV (2016)","DOI":"10.1007\/s11263-016-0895-4"},{"key":"33_CR38","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":"33_CR39","unstructured":"Wu, Y., Lin, J., Huang, T.S.: Analyzing and capturing articulated hand motion in image sequences. IEEE TPAMI (2005)"},{"key":"33_CR40","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":"33_CR41","doi-asserted-by":"crossref","unstructured":"Yang, L., Yao, A.: Disentangling latent hands for image synthesis and pose estimation. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.01011"},{"key":"33_CR42","doi-asserted-by":"crossref","unstructured":"Yuan, S., et al.: Depth-based 3D hand pose estimation: from current achievements to future goals. In: CVPR (2018)","DOI":"10.1109\/CVPR.2018.00279"},{"key":"33_CR43","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":"33_CR44","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":"33_CR45","unstructured":"Zhang, J., Jiao, J., Chen, M., Qu, L., Xu, X., Yang, Q.: 3D hand pose tracking and estimation using stereo matching. arXiv preprint arXiv:1610.07214 (2016)"},{"key":"33_CR46","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"},{"key":"33_CR47","doi-asserted-by":"crossref","unstructured":"Zimmermann, C., Ceylan, D., Yang, J., Russell, B., Argus, M., Brox, T.: FreiHand: a dataset for markerless capture of hand pose and shape from single RGB images. In: ICCV (2019)","DOI":"10.1109\/ICCV.2019.00090"}],"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\/978-3-030-58565-5_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T00:10:27Z","timestamp":1731283827000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58565-5_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585648","9783030585655"],"references-count":47,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58565-5_33","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":"12 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.","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)"}}]}}