{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,13]],"date-time":"2025-11-13T07:21:04Z","timestamp":1763018464881,"version":"3.37.3"},"reference-count":39,"publisher":"Springer Science and Business Media LLC","issue":"18","license":[{"start":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T00:00:00Z","timestamp":1648080000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T00:00:00Z","timestamp":1648080000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFC0309400"],"award-info":[{"award-number":["2018YFC0309400"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61871188"],"award-info":[{"award-number":["61871188"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangzhou city science and technology research projects","award":["201902020008"],"award-info":[{"award-number":["201902020008"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,7]]},"DOI":"10.1007\/s11042-022-12780-9","type":"journal-article","created":{"date-parts":[[2022,3,24]],"date-time":"2022-03-24T01:02:22Z","timestamp":1648083742000},"page":"25745-25763","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["Cascaded hierarchical CNN for 2D hand pose estimation from a single color image"],"prefix":"10.1007","volume":"81","author":[{"given":"Mingyue","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4040-0175","authenticated-orcid":false,"given":"Zhiheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Deng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,24]]},"reference":[{"key":"12780_CR1","doi-asserted-by":"crossref","unstructured":"Cai Y, Ge L, Cai J, Yuan J (2018) Weakly-supervised 3d hand pose estimation from monocular rgb images. In: Proceedings of the European conference on computer vision (ECCV), pp 666\u2013682","DOI":"10.1007\/978-3-030-01231-1_41"},{"issue":"5","key":"12780_CR2","doi-asserted-by":"publisher","first-page":"115909","DOI":"10.1016\/j.image.2020.115909","volume":"87","author":"Z Chen","year":"2020","unstructured":"Chen Z, Du K, Sun Y, Lin X, Ma X (2020) Hierarchical neural network for hand pose estimation. Signal Process Image Commun 87(5):115909","journal-title":"Signal Process Image Commun"},{"key":"12780_CR3","doi-asserted-by":"crossref","unstructured":"Chen Y, Ma H, Kong D, Yan X, Wu J, Fan W, Xie X (2020) Nonparametric structure regularization machine for 2d hand pose estimation. In: IEEE Winter Conference on applications of computer vision (WACV), pp 3258\u20133268","DOI":"10.1109\/WACV45572.2020.9093271"},{"key":"12780_CR4","doi-asserted-by":"publisher","first-page":"138","DOI":"10.1016\/j.neucom.2018.06.097","volume":"395","author":"X Chen","year":"2020","unstructured":"Chen X, Wang G, Guo H, Zhang C (2020) Pose guided structured region ensemble network for cascaded hand pose estimation. Neurocomputing 395:138\u2013149","journal-title":"Neurocomputing"},{"key":"12780_CR5","unstructured":"Clark E (2006) A multicamera system for gesture tracking with three dimensional hand pose estimation. Rochester Institute of Technology"},{"key":"12780_CR6","doi-asserted-by":"crossref","unstructured":"Du K, Lin X, Sun Y, Ma X (2019) Crossinfonet: multi-task information sharing based hand pose estimation. In: IEEE\/CVF Conference on computer vision and pattern recognition (CVPR), pp 9888\u20139897","DOI":"10.1109\/CVPR.2019.01013"},{"issue":"39","key":"12780_CR7","doi-asserted-by":"publisher","first-page":"28925","DOI":"10.1007\/s11042-020-09370-y","volume":"79","author":"A Elboushaki","year":"2020","unstructured":"Elboushaki A, Hannane R, Afdel K, Koutti L (2020) Improving articulated hand pose detection for static finger sign recognition in rgb-d images. Multimed Tools Appl 79(39):28925\u201328969","journal-title":"Multimed Tools Appl"},{"key":"12780_CR8","unstructured":"EricLee (2021) https:\/\/codechina.csdn.net\/ericlee\/handpose_x"},{"issue":"1-2","key":"12780_CR9","doi-asserted-by":"publisher","first-page":"52","DOI":"10.1016\/j.cviu.2006.10.012","volume":"108","author":"A Erol","year":"2007","unstructured":"Erol A, Bebis G, Nicolescu M, Boyle RD, Twombly X (2007) Vision-based hand pose estimation: a review. Comput Vis Image Underst 108(1-2):52\u201373","journal-title":"Comput Vis Image Underst"},{"issue":"2","key":"12780_CR10","doi-asserted-by":"publisher","first-page":"649","DOI":"10.3390\/s21020649","volume":"21","author":"L Fan","year":"2021","unstructured":"Fan L, Rao H, Yang W (2021) 3d hand pose estimation based on five-layer ensemble cnn. Sensors 21(2):649\u2013665","journal-title":"Sensors"},{"issue":"3","key":"12780_CR11","first-page":"1","volume":"2020","author":"L Fan","year":"2020","unstructured":"Fan L, Zhang J, Dai S, Yang W, Liu W (2020) Cascaded hierarchical cnn for rgb-based 3d hand pose estimation. Math Probl Eng 2020(3):1\u201313","journal-title":"Math Probl Eng"},{"key":"12780_CR12","doi-asserted-by":"publisher","first-page":"25","DOI":"10.1016\/j.imavis.2018.12.001","volume":"81","author":"F Gomez-Donoso","year":"2019","unstructured":"Gomez-Donoso F, Orts-Escolano S, Cazorla M (2019) Large-scale multiview 3d hand pose dataset. Image Vis Comput 81:25\u201333","journal-title":"Image Vis Comput"},{"key":"12780_CR13","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"12780_CR14","doi-asserted-by":"crossref","unstructured":"Huang XY, Tsai MS, Huang CC (2019) 3d virtual-reality interaction system. In: IEEE International conference on consumer electronics(ICCE), pp 1\u20132","DOI":"10.1109\/ICCE-TW46550.2019.8991800"},{"key":"12780_CR15","unstructured":"Jia D, Wei D, Socher R, Li LJ, Kai L, Li FF (2009) Imagenet: a large-scale hierarchical image database. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 248\u2013255"},{"issue":"1","key":"12780_CR16","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TPAMI.2017.2782743","volume":"41","author":"H Joo","year":"2017","unstructured":"Joo H, Simon T, Li X, Liu H, Tan L, Gui L, Banerjee S, Godisart T, Nabbe B, Matthews I (2017) Panoptic studio: a massively multiview system for social interaction capture. IEEE Trans Pattern Anal Mach Intell 41 (1):190\u2013204","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"12780_CR17","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization, arXiv:1412.6980"},{"key":"12780_CR18","doi-asserted-by":"crossref","unstructured":"Kourbane I, Genc Y (2021) Skeleton-aware multi-scale heatmap regression for 2d hand pose estimation, arXiv:2105.10904","DOI":"10.31449\/inf.v45i4.3470"},{"key":"12780_CR19","doi-asserted-by":"crossref","unstructured":"Kulon D, G\u00fcler R, Kokkinos I, Bronstein M, Zafeiriou S (2020) Weakly-supervised mesh-convolutional hand reconstruction in the wild. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition (CVPR), pp 4990\u20135000","DOI":"10.1109\/CVPR42600.2020.00504"},{"key":"12780_CR20","unstructured":"Madadi M, Escalera S, Baro X, Gonzalez J (2017) End-to-end global to local cnn learning for hand pose recovery in depth data, arXiv:1705.09606"},{"issue":"4","key":"12780_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073596","volume":"36","author":"D Mehta","year":"2017","unstructured":"Mehta D, Sridhar S, Sotnychenko O, Rhodin H, Theobalt C (2017) Vnect: real-time 3d human pose estimation with a single rgb camera. ACM Trans Graph (TOG) 36(4):1\u201314","journal-title":"ACM Trans Graph (TOG)"},{"key":"12780_CR22","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision (ECCV), pp 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"12780_CR23","doi-asserted-by":"crossref","unstructured":"Panteleris P, Oikonomidis I, Argyros A (2018) Using a single rgb frame for real time 3d hand pose estimation in the wild. In: IEEE Winter conference on applications of computer vision (WACV), pp 436\u2013445","DOI":"10.1109\/WACV.2018.00054"},{"issue":"14","key":"12780_CR24","doi-asserted-by":"publisher","first-page":"8137","DOI":"10.1007\/s11042-015-2729-8","volume":"75","author":"A Rosa-Pujazon","year":"2016","unstructured":"Rosa-Pujazon A, Barbancho I, Tardon LJ, Barbancho AM (2016) Fast-gesture recognition and classification using kinect: an application for a virtual reality drumkit. Multimed Tools Appl 75(14):8137\u20138164","journal-title":"Multimed Tools Appl"},{"key":"12780_CR25","unstructured":"Ruder S (2017) An overview of multi-task learning in deep neural networks, arXiv:1706.05098"},{"key":"12780_CR26","doi-asserted-by":"crossref","unstructured":"Simon T, Joo H, Matthews I, Sheikh Y (2017) Hand keypoint detection in single images using multiview bootstrapping. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 1145\u20131153","DOI":"10.1109\/CVPR.2017.494"},{"key":"12780_CR27","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv:1409.1556"},{"key":"12780_CR28","doi-asserted-by":"crossref","unstructured":"Sun X, Wei Y, Liang S, Tang X, Sun J (2015) Cascaded hand pose regression. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 824\u2013832","DOI":"10.1109\/CVPR.2015.7298683"},{"key":"12780_CR29","doi-asserted-by":"crossref","unstructured":"Tang D, Jin Chang H, Tejani A, Kim TK (2014) Latent regression forest: Structured estimation of 3d articulated hand posture. In: Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR), pp 3786\u20133793","DOI":"10.1109\/CVPR.2014.490"},{"issue":"5","key":"12780_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2629500","volume":"33","author":"J Tompson","year":"2014","unstructured":"Tompson J, Stein M, Lecun Y, Perlin K (2014) Real-time continuous pose recovery of human hands using convolutional networks. ACM Trans Graph (ToG) 33(5):1\u201310","journal-title":"ACM Trans Graph (ToG)"},{"key":"12780_CR31","unstructured":"Wan J (2021) Gesture recognition and information recommendation based on machine learning and virtual reality in distance education. Journal of Intelligent and Fuzzy Systems (Preprint), 1\u201311"},{"key":"12780_CR32","doi-asserted-by":"crossref","unstructured":"Wan C, Yao A, Van Gool L (2016) Hand pose estimation from local surface normals. In: European conference on computer vision (ECCV), pp 554\u2013569","DOI":"10.1007\/978-3-319-46487-9_34"},{"issue":"11","key":"12780_CR33","doi-asserted-by":"publisher","first-page":"3258","DOI":"10.1109\/TCSVT.2018.2879980","volume":"29","author":"Y Wang","year":"2018","unstructured":"Wang Y, Cong P, Liu Y (2018) Mask-pose cascaded cnn for 2d hand pose estimation from single color image. IEEE Trans Circuits Syst Video Technol 29(11):3258\u20133268","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"12780_CR34","doi-asserted-by":"publisher","first-page":"2977","DOI":"10.1109\/TIP.2019.2955280","volume":"29","author":"Y Wang","year":"2019","unstructured":"Wang Y, Zhang B, Peng C (2019) Srhandnet: real-time 2d hand pose estimation with simultaneous region localization. IEEE Trans Image Process 29:2977\u20132986","journal-title":"IEEE Trans Image Process"},{"key":"12780_CR35","doi-asserted-by":"crossref","unstructured":"Wei SE, Ramakrishna V, Kanade T, Sheikh Y (2016) Convolutional pose machines. In: IEEE Conference on computer vision and pattern recognition (CVPR), pp 4724\u20134732","DOI":"10.1109\/CVPR.2016.511"},{"issue":"12","key":"12780_CR36","first-page":"2878","volume":"35","author":"Y Yi","year":"2013","unstructured":"Yi Y, Ramanan D (2013) Articulated human detection with flexible mixtures of parts. IEEE Trans Softw Eng 35(12):2878\u20132890","journal-title":"IEEE Trans Softw Eng"},{"key":"12780_CR37","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1016\/j.patcog.2015.07.014","volume":"49","author":"Y Zhou","year":"2016","unstructured":"Zhou Y, Jiang G, Lin Y (2016) A novel finger and hand pose estimation technique for real-time hand gesture recognition. Pattern Recogn 49:102\u2013114","journal-title":"Pattern Recogn"},{"key":"12780_CR38","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Brox T (2017) Learning to estimate 3d hand pose from single rgb images. In: IEEE International conference on computer vision (ICCV), pp 4913\u20134921","DOI":"10.1109\/ICCV.2017.525"},{"key":"12780_CR39","doi-asserted-by":"crossref","unstructured":"Zimmermann C, Ceylan D, Yang J, Russell B, Argus M, Brox T (2019) Freihand: a dataset for markerless capture of hand pose and shape from single rgb images. In: Proceedings of the IEEE\/CVF international conference on computer vision (ICCV), pp 813\u2013822","DOI":"10.1109\/ICCV.2019.00090"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12780-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-12780-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-12780-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,1]],"date-time":"2022-07-01T07:15:37Z","timestamp":1656659737000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-12780-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,24]]},"references-count":39,"journal-issue":{"issue":"18","published-print":{"date-parts":[[2022,7]]}},"alternative-id":["12780"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-12780-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"type":"print","value":"1380-7501"},{"type":"electronic","value":"1573-7721"}],"subject":[],"published":{"date-parts":[[2022,3,24]]},"assertion":[{"value":"5 August 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 December 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 March 2022","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declared there is no conflict of interest in terms with this submission.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}