{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T02:47:15Z","timestamp":1771469235038,"version":"3.50.1"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2021,1]]},"DOI":"10.1007\/s11042-020-09700-0","type":"journal-article","created":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T18:45:46Z","timestamp":1598985946000},"page":"127-163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":52,"title":["Hand pose aware multimodal isolated sign language recognition"],"prefix":"10.1007","volume":"80","author":[{"given":"Razieh","family":"Rastgoo","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6582-8691","authenticated-orcid":false,"given":"Kourosh","family":"Kiani","sequence":"additional","affiliation":[]},{"given":"Sergio","family":"Escalera","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,9,1]]},"reference":[{"key":"9700_CR1","doi-asserted-by":"crossref","unstructured":"Asadi-Aghbolaghi M, Bertiche H, Roig V, Kasaei Sh, Escalera S (2017) Action recognition from RGB-D data: comparison and fusion of Spatio-temporal handcrafted features and deep strategies, IEEE International Conference on Computer Vision Workshops (ICCVW), Venice, Italy","DOI":"10.1109\/ICCVW.2017.376"},{"key":"9700_CR2","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1109\/TMM.2018.2856094","volume":"21","author":"D Avola","year":"2019","unstructured":"Avola D, Bernardi M, Cinque L, Foresti GL, Massaroni C (2019) Exploiting Recurrent Neural Networks and Leap Motion Controller for the Recognition of Sign Language and Semaphoric Hand Gestures. IEEE Transact Multimed 21:234\u2013245","journal-title":"IEEE Transact Multimed"},{"key":"9700_CR3","doi-asserted-by":"publisher","first-page":"107410","DOI":"10.1016\/j.patcog.2020.107410","volume":"106","author":"Y Bin","year":"2020","unstructured":"Bin Y, Chen ZM, Wei X-S, Chen X, Gao C, Sang N (2020) Structure-aware human pose estimation with graph convolutional networks. Pattern Recogn 106:107410","journal-title":"Pattern Recogn"},{"key":"9700_CR4","first-page":"10023","volume-title":"Sign language transformers: joint end-to-end sign language recognition and translation","author":"NC Camgoz","year":"2020","unstructured":"Camgoz NC, Koller O, Hadfield S, Bowden R (2020) Sign language transformers: joint end-to-end sign language recognition and translation. CVPR, Washington, US, pp 10023\u201310033"},{"key":"9700_CR5","doi-asserted-by":"publisher","first-page":"1074","DOI":"10.3390\/s20041074","volume":"20","author":"W Chen","year":"2020","unstructured":"Chen W, Yu C, Tu C, Lyu Z, Tang J, Ou S, Fu Y, Xue Z (2020) A survey on hand pose estimation with wearable sensors and computer-vision-based methods. Sensors 20:1074","journal-title":"Sensors"},{"key":"9700_CR6","doi-asserted-by":"publisher","unstructured":"Cippitelli E, Gasparrini S, Gambi E, Spinsante S (2016) A Human Activity Recognition System Using Skeleton Data from RGBD Sensors, Computational Intelligence and Neuroscience, Article ID 4351435, 14 pages, https:\/\/doi.org\/10.1155\/2016\/4351435","DOI":"10.1155\/2016\/4351435"},{"key":"9700_CR7","doi-asserted-by":"crossref","unstructured":"Dabre K, Dholay S (2014) Machine learning model for sign language interpretation using webcam images, International Conference on Circuits, Systems, Communication and Information Technology Applications (CSCITA), Mumbai, India","DOI":"10.1109\/CSCITA.2014.6839279"},{"key":"9700_CR8","doi-asserted-by":"publisher","first-page":"15573","DOI":"10.1007\/s11042-017-5133-8","volume":"77","author":"S Ershadi-Nasab","year":"2018","unstructured":"Ershadi-Nasab S, Noury E, Kasaei S, Sanaei E (2018) Multiple human 3D pose estimation from multiview images. Multimed Tools Appl 77:15573\u201315601. https:\/\/doi.org\/10.1007\/s11042-017-5133-8","journal-title":"Multimed Tools Appl"},{"key":"9700_CR9","doi-asserted-by":"crossref","unstructured":"Escalera S, Gonzalez J, Baro X, Reyes M, Lopes O, Guyon I, Athitsos V, Escalante H (2013) Multi-modal gesture recognition challenge 2013: dataset and results, In Proceedings of the 15th ACM on International conference on multimodal interaction, 445\u2013452","DOI":"10.1145\/2522848.2532595"},{"key":"9700_CR10","unstructured":"Garcia B, Alarcon Viesca S (2016) Real-time American sign language recognition with convolutional neural networks. Report of Standford University"},{"key":"9700_CR11","doi-asserted-by":"publisher","first-page":"327","DOI":"10.1016\/j.eswa.2019.06.055%0A","volume":"136","author":"F Gomez-Donoso","year":"2019","unstructured":"Gomez-Donoso F, Orts-Escolano S, Cazorla M (2019) Accurate and efficient 3D hand pose regression for robot hand teleoperation using a monocular RGB camera. Expert Syst Appl 136:327\u2013337. https:\/\/doi.org\/10.1016\/j.eswa.2019.06.055%0A","journal-title":"Expert Syst Appl"},{"key":"9700_CR12","doi-asserted-by":"crossref","unstructured":"Guo H, Wang G, Chen X, Zhang C (2017) Towards Good Practices for Deep 3D Hand Pose Estimation, arXiv:1707.07248v1","DOI":"10.1016\/j.jvcir.2018.04.005"},{"key":"9700_CR13","doi-asserted-by":"crossref","unstructured":"Hosain AA, Santhalingam PS, Pathak P, Rangwala H, Kosecka J (2020) FineHand: Learning Hand Shapes for American Sign Language Recognition, arXiv:2003.08753","DOI":"10.1109\/DSAA49011.2020.00033"},{"key":"9700_CR14","doi-asserted-by":"crossref","unstructured":"Jaimez M, Souiai M, Gonzalez Jimenez J, Cremers D (2015) A primal-dual framework for real-time dense RGBD scene flow, In Robotics and Automation (ICRA), 2015 IEEE International Conference on, 98\u2013104","DOI":"10.1109\/ICRA.2015.7138986"},{"key":"9700_CR15","doi-asserted-by":"publisher","first-page":"107462","DOI":"10.1016\/j.patcog.2020.107462","volume":"106","author":"Y Kim","year":"2020","unstructured":"Kim Y, Kim D (2020) A CNN-based 3D human pose estimation based on projection of depth and ridge data. Pattern Recogn 106:107462. https:\/\/doi.org\/10.1016\/j.patcog.2020.107462","journal-title":"Pattern Recogn"},{"key":"9700_CR16","doi-asserted-by":"publisher","unstructured":"K\u00f6p\u00fckl\u00fc O, Kose N, Rigoll G (2018) Motion Fused Frames: Data Level Fusion Strategy for Hand Gesture Recognitiontle. IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Salt Lake City, Utah, United States, 2103\u20132111. https:\/\/doi.org\/10.1109\/CVPRW.2018.00284","DOI":"10.1109\/CVPRW.2018.00284"},{"key":"9700_CR17","unstructured":"Krizhevsky A, Sutskever I, Hinton G (2012) ImageNet Classification with Deep Convolutional Neural Networks, Advances in Neural Information Processing Systems 25 (NIPS 2012), Nevada, USA"},{"key":"9700_CR18","doi-asserted-by":"publisher","first-page":"6727","DOI":"10.1007\/s11042-019-08429-9","volume":"79","author":"L Li","year":"2020","unstructured":"Li L, Qin S, Lu Z, Xu K, Hu Z (2020) One-shot learning gesture recognition based on joint training of 3D ResNet and memory module. Multimed Tools Appl 79:6727\u20136757. https:\/\/doi.org\/10.1007\/s11042-019-08429-9","journal-title":"Multimed Tools Appl"},{"key":"9700_CR19","doi-asserted-by":"publisher","first-page":"19917","DOI":"10.1007\/s11042-019-7263-7","volume":"78","author":"KM Lim","year":"2019","unstructured":"Lim KM, Tan AWC, Lee CP, Tan SC (2019) Isolated sign language recognition using convolutional neural network hand modelling and hand energy image. Multimed Tools Appl 78:19917\u201319944. https:\/\/doi.org\/10.1007\/s11042-019-7263-7","journal-title":"Multimed Tools Appl"},{"key":"9700_CR20","unstructured":"Lucas BD, Kanade T (1981) An iterative image registration technique with an application in stereo vision, In Seventh International Joint Conference on Artificial Intelligence, Vancouver, 674\u2013679"},{"key":"9700_CR21","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked Hourglass Networks for Human Pose Estimation, European Conference on Computer Vision (ECCV), 483499","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"9700_CR22","unstructured":"Oberweger M, Wohlhart P, Lepetit V (2015) Hands Deep in Deep Learning for Hand Pose Estimation, arXiv:1502.06807v2"},{"key":"9700_CR23","doi-asserted-by":"crossref","unstructured":"Oberweger M, Wohlhart P, Lepetit V (2016) Efficiently creating 3D training data for fine hand pose estimation, Proceedings of the IEEE conference on computer vision and pattern recognition, USA, 4957\u20134965","DOI":"10.1109\/CVPR.2016.536"},{"key":"9700_CR24","doi-asserted-by":"crossref","unstructured":"Paragios N, Chen Y, Faugeras O (2005) Mathematical models in computer vision: the handbook, Springer, 39\u2013258","DOI":"10.1007\/0-387-28831-7"},{"key":"9700_CR25","doi-asserted-by":"publisher","first-page":"11813","DOI":"10.1007\/s11042-019-08448-6","volume":"79","author":"MA Rahim","year":"2020","unstructured":"Rahim MA, Shin J, Islam MR (2020) Hand gesture recognition-based non-touch character writing system on a virtual keyboard. Multimed Tools Appl 79:11813\u201311836. https:\/\/doi.org\/10.1007\/s11042-019-08448-6","journal-title":"Multimed Tools Appl"},{"key":"9700_CR26","doi-asserted-by":"crossref","unstructured":"Rastgoo R, Kiani K, Escalera S (2018) Multi-modal deep hand sign language recognition in still images using Restricted Boltzmann Machine. Entropy 20:11, 809. https:\/\/www.mdpi.com\/1099-4300\/20\/11\/809.","DOI":"10.3390\/e20110809"},{"key":"9700_CR27","doi-asserted-by":"publisher","first-page":"113336","DOI":"10.1016\/j.eswa.2020.113336","volume":"150","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) Hand sign language recognition using multi-view hand skeleton. Expert Syst Appl 150:113336. https:\/\/doi.org\/10.1016\/j.eswa.2020.113336","journal-title":"Expert Syst Appl"},{"key":"9700_CR28","doi-asserted-by":"publisher","first-page":"22965","DOI":"10.1007\/s11042-020-09048-5","volume":"79","author":"R Rastgoo","year":"2020","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) Video-based isolated hand sign language recognition using a deep cascaded model. Multimed Tools Appl 79:22965\u201322987. https:\/\/doi.org\/10.1007\/s11042-020-09048-5","journal-title":"Multimed Tools Appl"},{"key":"9700_CR29","doi-asserted-by":"publisher","first-page":"1137","DOI":"10.1109\/TPAMI.2016.2577031","volume":"39","author":"S Ren","year":"2017","unstructured":"Ren S, He K, Girshick R, Sun J (2017) Faster R-CNN: towards real-time object detection with region proposal networks. IEEE Trans Pattern Anal Mach Intell 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"9700_CR30","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2016.09.002","volume":"152","author":"N Sarafianos","year":"2016","unstructured":"Sarafianos N, Boteanu B, Ionescu B, Kakadiaris IA (2016) 3D human pose estimation: a review of the literature and analysis of covariates. Comput Vis Image Underst 152:1\u201320","journal-title":"Comput Vis Image Underst"},{"key":"9700_CR31","doi-asserted-by":"publisher","unstructured":"Shahroudy A, Ng T, Gong Y, Wang G (2016) Deep multimodal feature analysis for action recognition in RGB+D videos, IEEE Transactions on Software Engineering 99 https:\/\/doi.org\/10.1109\/TPAMI.2017.2691321","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"9700_CR32","doi-asserted-by":"crossref","unstructured":"Simon T, Joo H, Matthews I, Sheikh Y (2017) Hand Keypoint detection in single images using multiview bootstrapping, CVPR","DOI":"10.1109\/CVPR.2017.494"},{"key":"9700_CR33","unstructured":"Simonyan K, Zisserman A (2014) Two-Stream Convolutional Networks for Action Recognition in Videos, NIPS\u201914 Proceedings of the 27th International Conference on Neural Information Processing Systems, pp. 568\u2013576, Monteral, Canada"},{"key":"9700_CR34","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition, arXiv technical report"},{"key":"9700_CR35","unstructured":"Sung J, Ponce C, Selman B, Saxena A (2012) Unstructured human activity detection from RGBD images, IEEE International Conference on Robotics and Automation, Saint Paul, MN, USA"},{"key":"9700_CR36","doi-asserted-by":"crossref","unstructured":"Supancic JS, Rogez G, Yang Y, Shotton J, Ramanan D (2015) Depth-based hand pose estimation: methods, data, and challenges, IEEE International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2015.217"},{"key":"9700_CR37","doi-asserted-by":"publisher","first-page":"29357","DOI":"10.1007\/s11042-019-7433-7","volume":"78","author":"P Szczuko","year":"2019","unstructured":"Szczuko P (2019) Deep neural networks for human pose estimation from a very low resolution depth image. Multimed Tools Appl 78:29357\u201329377. https:\/\/doi.org\/10.1007\/s11042-019-7433-7","journal-title":"Multimed Tools Appl"},{"key":"9700_CR38","doi-asserted-by":"publisher","first-page":"722","DOI":"10.3390\/app10020722","volume":"10","author":"D-S Tran","year":"2020","unstructured":"Tran D-S, Ho N-H, Yang H-J, Baek E-T, Kim S-H, Lee G (2020) Real-time hand gesture spotting and recognition using RGB-D camera and 3D convolutional neural network. Appl Sci 10:722","journal-title":"Appl Sci"},{"key":"9700_CR39","doi-asserted-by":"crossref","unstructured":"Vedula S, Baker S, Rander P, Collins R, Kanade T (2015) Three-dimensional scene flow, IEEE Trans Pattern Anal Mach Intell, 475\u2013480","DOI":"10.1109\/TPAMI.2005.63"},{"key":"9700_CR40","doi-asserted-by":"crossref","unstructured":"Wan J et al. (2016) ChaLearn looking at people RGB-D isolated and continuous datasets for gesture recognition, IEEE Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), Las Vegas, NV, USA","DOI":"10.1109\/CVPRW.2016.100"},{"key":"9700_CR41","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2012) Mining actionlet ensemble for action recognition with depth cameras, In Computer Vision and Pattern Recognition(CVPR), 2012 IEEE Conference on, pp. 1290\u20131297"},{"key":"9700_CR42","doi-asserted-by":"publisher","first-page":"734","DOI":"10.1016\/j.measurement.2016.09.018","volume":"94","author":"M Wang","year":"2016","unstructured":"Wang M, Chen W-Y, Li XD (2016) Hand gesture recognition using valley circle feature and Hu\u2019s moments technique for robot movement control. Measurement 94:734\u2013744","journal-title":"Measurement"},{"key":"9700_CR43","unstructured":"Zhou X, Wan Q, Zhang W, Xue X, Wei Y (2016) Model-based Deep Hand Pose Estimation, International Joint Conference on Artificial Intelligence (IJCAI), New York, USA"},{"key":"9700_CR44","doi-asserted-by":"crossref","unstructured":"Zimmermann Ch, Brox Th (2017) Learning to Estimate 3D Hand Pose from Single RGB Images, IEEE International Conference on Computer Vision (ICCV)","DOI":"10.1109\/ICCV.2017.525"},{"key":"9700_CR45","doi-asserted-by":"publisher","unstructured":"Rastgoo R, Kiani K, Escalera S (2020) ign Language Recognition: A Deep Survey. Expert Syst Appl 164:113794. https:\/\/doi.org\/10.1016\/j.eswa.2020.113794","DOI":"10.1016\/j.eswa.2020.113794"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09700-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-020-09700-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-020-09700-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,1]],"date-time":"2021-09-01T00:54:38Z","timestamp":1630457678000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-020-09700-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,1]]},"references-count":45,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["9700"],"URL":"https:\/\/doi.org\/10.1007\/s11042-020-09700-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,9,1]]},"assertion":[{"value":"21 March 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 July 2020","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2020","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 September 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"The authors certify that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}