{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,2]],"date-time":"2026-04-02T15:51:07Z","timestamp":1775145067863,"version":"3.50.1"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T00:00:00Z","timestamp":1689292800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T00:00:00Z","timestamp":1689292800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61731001"],"award-info":[{"award-number":["61731001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LY21E050017"],"award-info":[{"award-number":["LY21E050017"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-023-16130-1","type":"journal-article","created":{"date-parts":[[2023,7,14]],"date-time":"2023-07-14T09:01:31Z","timestamp":1689325291000},"page":"16275-16312","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Real-time continuous detection and recognition of dynamic hand gestures in untrimmed sequences based on end-to-end architecture with 3D DenseNet and LSTM"],"prefix":"10.1007","volume":"83","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0440-9175","authenticated-orcid":false,"given":"Zhi","family":"Lu","sequence":"first","affiliation":[]},{"given":"Shiyin","family":"Qin","sequence":"additional","affiliation":[]},{"given":"Pin","family":"Lv","sequence":"additional","affiliation":[]},{"given":"Liguo","family":"Sun","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Tang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,7,14]]},"reference":[{"issue":"2","key":"16130_CR1","doi-asserted-by":"publisher","first-page":"71","DOI":"10.1109\/MSP.2015.2502784","volume":"33","author":"MG Amin","year":"2016","unstructured":"Amin MG, Zhang YD, Ahmad F, Ho KD (2016) Radar signal processing for elderly fall detection: the future for in-home monitoring. IEEE Signal Process Mag 33(2):71\u201380","journal-title":"IEEE Signal Process Mag"},{"key":"16130_CR2","doi-asserted-by":"publisher","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","volume":"39","author":"V Badrinarayanan","year":"2017","unstructured":"Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: A deep convolutional encoder-decoder architecture for image segmentation. IEEE Trans Pattern Anal 39:2481\u20132495","journal-title":"IEEE Trans Pattern Anal"},{"key":"16130_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.asoc.2020.106616","volume":"96","author":"O Barron","year":"2020","unstructured":"Barron O, Raison M, Gaudet G, Achiche S (2020) Recurrent neural network for electromyographic gesture recognition in transhumeral amputees. Appl Soft Comput 96:1\u20139","journal-title":"Appl Soft Comput"},{"key":"16130_CR4","doi-asserted-by":"publisher","first-page":"227","DOI":"10.1007\/978-3-642-76153-9_28","volume":"68","author":"JS Bridle","year":"1990","unstructured":"Bridle JS (1990) Probabilistic interpretation of feed forward classification network outputs, with relationships to statistical pattern recognition. Neurocomputing 68:227\u2013236","journal-title":"Neurocomputing"},{"issue":"2","key":"16130_CR5","doi-asserted-by":"publisher","first-page":"27309","DOI":"10.1007\/s11042-019-07827-3","volume":"78","author":"F Carrara","year":"2019","unstructured":"Carrara F, Elias P, Sedmidubsky J, Zezula P (2019) LSTM-based real-time action detection and prediction in human motion streams. Multimed Tools Appl 78(2):27309\u201327331","journal-title":"Multimed Tools Appl"},{"key":"16130_CR6","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? A new model and the kinetics dataset. In: CVPR. pp 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"16130_CR7","doi-asserted-by":"crossref","unstructured":"Chai X, Liu Z, Yin F, Liu Z, Chen X (2017) Two streams recurrent neural networks for large-scale continuous gesture recognition. In: ICPR. pp 31\u201336","DOI":"10.1109\/ICPR.2016.7899603"},{"key":"16130_CR8","doi-asserted-by":"crossref","unstructured":"Chalasani, T., Smolic, A.: Simultaneous segmentation and recognition: Towards more accurate ego gesture recognition. In: ICCV. pp 4367\u20134375 (2019)","DOI":"10.1109\/ICCVW.2019.00537"},{"key":"16130_CR9","doi-asserted-by":"crossref","unstructured":"Dhingra N, Kunz A (2019) Res3ATN-deep 3D residual attention network for hand gesture recognition in videos. In: 2019 International Conference on 3D Vision. pp 491\u2013501","DOI":"10.1109\/3DV.2019.00061"},{"issue":"7","key":"16130_CR10","doi-asserted-by":"publisher","first-page":"1272","DOI":"10.1109\/JPROC.2002.801449","volume":"90","author":"Z Duric","year":"2002","unstructured":"Duric Z, Gray WD, Heishman R, Fayin L, Rosenfeld A, Schoelles MJ, Schunn C, Wechsler H (2002) Integrating perceptual and cognitive modeling for adaptive and intelligent human-computer interaction. P IEEE 90(7):1272\u20131289","journal-title":"P IEEE"},{"key":"16130_CR11","doi-asserted-by":"crossref","unstructured":"Farneback G (2003) Two-frame motion estimation based on polynomial expansion. Scandinavian Conference on Image Analysis 363\u2013370","DOI":"10.1007\/3-540-45103-X_50"},{"key":"16130_CR12","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: CVPR. pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"16130_CR13","doi-asserted-by":"crossref","unstructured":"Graves A, Fern\u00e1ndez S, Gomez F, Schmidhuber J (2006) Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In: ICML. pp 369\u2013376","DOI":"10.1145\/1143844.1143891"},{"key":"16130_CR14","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1007\/978-3-642-24797-2_2","volume":"385","author":"S Hadfield","year":"2012","unstructured":"Hadfield S, Bowden R (2012) Supervised sequence labelling with recurrent neural networks. Stud Computat Intell 385:5\u201313","journal-title":"Stud Computat Intell"},{"key":"16130_CR15","doi-asserted-by":"publisher","first-page":"1984","DOI":"10.1109\/TIFS.2016.2569061","volume":"11","author":"M Haghighat","year":"2016","unstructured":"Haghighat M, Abdel-Mottaleb M, Alhalabi W (2016) Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans Inf Foren Sec 11:1984\u20131996","journal-title":"IEEE Trans Inf Foren Sec"},{"key":"16130_CR16","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: CVPR. pp 2261\u20132269","DOI":"10.1109\/CVPR.2017.243"},{"key":"16130_CR17","unstructured":"Kingma DP, Ba JL (2015) Adam: a method for stochastic optimization. In: International Conference on Learning Representations. pp 1\u201315"},{"issue":"2","key":"16130_CR18","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1109\/TBIOM.2020.2968216","volume":"2","author":"O K\u00f6p\u00fckl\u00fc","year":"2020","unstructured":"K\u00f6p\u00fckl\u00fc O, Gunduz A, Kose N, Rigoll G (2020) Online dynamic hand gesture recognition including efficiency analysis. IEEE Trans Biom Behav Identity Sci 2(2):85\u201397","journal-title":"IEEE Trans Biom Behav Identity Sci"},{"key":"16130_CR19","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc O, Gunduz A, Kose N, Rigoll G (2019) Real-time hand gesture detection and classification using convolutional neural networks. In: 14th IEEE International Conference on Automatic Face and Gesture Recognition. pp 1\u20138","DOI":"10.1109\/FG.2019.8756576"},{"key":"16130_CR20","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. Adv Neural Inf Proces Syst 1106\u20131114"},{"key":"16130_CR21","doi-asserted-by":"crossref","unstructured":"Liu Z, Chai X, Liu Z, Chen X (2017) Continuous gesture recognition with hand-oriented spatiotemporal feature. In: ICPR. pp 3056\u20133064","DOI":"10.1109\/ICCVW.2017.361"},{"key":"16130_CR22","unstructured":"Liu L, Shao L (2013) Learning discriminative representations from RGB-D video data. In: Proceedings of the Twenty-Third International Joint Conference on Artificial Intelligence. pp 1493\u20131500"},{"issue":"3","key":"16130_CR23","doi-asserted-by":"publisher","first-page":"1157","DOI":"10.1007\/s00138-019-01043-7","volume":"30","author":"Z Lu","year":"2019","unstructured":"Lu Z, Qin S, Li X, Li L, Zhang D (2019) One-shot learning hand gesture recognition based on modified 3D convolutional neural networks. Mach Vision Appl 30(3):1157\u20131180","journal-title":"Mach Vision Appl"},{"key":"16130_CR24","doi-asserted-by":"publisher","first-page":"131732","DOI":"10.1109\/ACCESS.2019.2940997","volume":"7","author":"Z Lu","year":"2019","unstructured":"Lu Z, Qin S, Li L, Zhang D, Xu K, Hu Z (2019) One-shot learning hand gesture recognition based on lightweight 3D convolutional neural networks for portable applications on mobile systems. IEEE Access 7:131732\u2013131748","journal-title":"IEEE Access"},{"key":"16130_CR25","doi-asserted-by":"crossref","unstructured":"Molchanov P, Gupta S, Kim K, Pulli K (2015) Multi-sensor system for driver\u2019s hand gesture recognition. In: 2015 11th IEEE International Conference and Workshops on Automatic Face and Gesture Recognition. pp 1\u20138","DOI":"10.1109\/FG.2015.7163132"},{"key":"16130_CR26","doi-asserted-by":"crossref","unstructured":"Molchanov P, Yang X, Gupta S, Kim K, Tyree S, Kautz J (2016) Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural networks. In: NIPS. pp 4207\u20134215","DOI":"10.1109\/CVPR.2016.456"},{"key":"16130_CR27","doi-asserted-by":"crossref","unstructured":"Murakami K, Taguchi H (1991) Gesture recognition using recurrent neural networks. In: Proceedings of the SIGCHI Conference on Human Factors in Computing Systems. pp 237\u2013242","DOI":"10.1145\/108844.108900"},{"key":"16130_CR28","doi-asserted-by":"crossref","unstructured":"Narayana P, Beveridge JR, Draper BA (2018) Gesture recognition: focus on the hands. In: CVPR. pp 5235\u20135244","DOI":"10.1109\/CVPR.2018.00549"},{"key":"16130_CR29","doi-asserted-by":"crossref","unstructured":"Nishida N, Nakayama H (2015) Multimodal gesture recognition using multi-stream recurrent neural network. In: Pacific-Rim Symposium on Image and Video Technology. pp 682\u2013694","DOI":"10.1007\/978-3-319-29451-3_54"},{"key":"16130_CR30","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.patcog.2017.10.033","volume":"76","author":"JC N\u00fa\u00f1ez","year":"2018","unstructured":"N\u00fa\u00f1ez JC, Cabido R, Pantrigo JJ, Montemayor AS, V\u00e9lez JF (2018) Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition. Pattern Recogn 76:80\u201394","journal-title":"Pattern Recogn"},{"key":"16130_CR31","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TITS.2014.2298352","volume":"15","author":"E Ohn-Bar","year":"2014","unstructured":"Ohn-Bar E, Trivedi MM (2014) Hand gesture recognition in real time for automotive interfaces: A multimodal vision-based approach and evaluations. IEEE Trans Intell Trans 15:1\u201310","journal-title":"IEEE Trans Intell Trans"},{"key":"16130_CR32","doi-asserted-by":"crossref","unstructured":"Park E, Han X, Berg TL, Berg AC (2016) Combining multiple sources of knowledge in deep CNNs for action recognition. IEEE Winter Conf Appl Comput Vis 1\u20138","DOI":"10.1109\/WACV.2016.7477589"},{"key":"16130_CR33","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 39:1137\u20131149","journal-title":"IEEE Trans Pattern Anal"},{"key":"16130_CR34","doi-asserted-by":"crossref","unstructured":"Ronnebergerhick O, Fischer P, Brox T (2015) U-Net: convolutional networks for biomedical image segmentation. In: International Conference on Medical Image Computing and Computer-Assisted Intervention. pp 234\u2013241","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"16130_CR35","doi-asserted-by":"crossref","unstructured":"Ryoo MS (2011) Human activity prediction: early recognition of ongoing activities from streaming videos. In: ICCV. pp 1036\u20131043","DOI":"10.1109\/ICCV.2011.6126349"},{"key":"16130_CR36","unstructured":"Shelhamer E, Long J, Darrell T (2015) Fully convolutional networks for semantic segmentation. In: CVPR. pp 3431\u20133440"},{"key":"16130_CR37","doi-asserted-by":"crossref","unstructured":"Shou Z, Wang D, Chang SF (2016) Temporal action localization in untrimmed videos via multi-stage CNNs. In: CVPR. pp 1049\u20131058","DOI":"10.1109\/CVPR.2016.119"},{"key":"16130_CR38","unstructured":"Simonyan K, Zisserman A (2017) Two-stream convolutional networks for action recognition in videos. In: NIPS. pp 568\u2013576"},{"key":"16130_CR39","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2016) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. pp 4263\u20134270","DOI":"10.1609\/aaai.v31i1.11212"},{"issue":"12","key":"16130_CR40","doi-asserted-by":"publisher","first-page":"2437","DOI":"10.1016\/j.patcog.2004.12.013","volume":"38","author":"D Tran","year":"2005","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2005) A new method of feature fusion and its application in image recognition. Pattern Recogn 38(12):2437\u20132448","journal-title":"Pattern Recogn"},{"key":"16130_CR41","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: ICCV. pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"16130_CR42","doi-asserted-by":"crossref","unstructured":"Tung PT, Ngoc LQ (2014) Elliptical density shape model for hand gesture recognition. In: Proceedings of the Fifth Symposium on Information and Communication Technology. pp 186\u2013191","DOI":"10.1145\/2676585.2676600"},{"key":"16130_CR43","unstructured":"Twentybn Jester Dataset (2017) A hand gesture dataset. https:\/\/www.twentybn.com\/datasets\/jester"},{"key":"16130_CR44","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang H, Oneata D, Verbeek J, Schmid C (2016) A robust and efficient video representation for action recognition. Int J Comput Vision 119:219\u2013238","journal-title":"Int J Comput Vision"},{"key":"16130_CR45","doi-asserted-by":"crossref","unstructured":"Wang Y, Yu T, Shi L, Li Z (2008) Using human body gestures as inputs for gaming via depth analysis. In: Proceedings of the IEEE International Conference on Multimedia and Expo. pp 993\u2013996","DOI":"10.1109\/ICME.2008.4607604"},{"issue":"8","key":"16130_CR46","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1109\/TPAMI.2016.2537340","volume":"38","author":"D Wu","year":"2016","unstructured":"Wu D, Pigou L, Kindermans PJ, Le N, Shao L, Dambre J, Odobez JM (2016) Deep dynamic neural networks for multimodal gesture segmentation and recognition. IEEE Trans Pattern Anal 38(8):1583\u20131597","journal-title":"IEEE Trans Pattern Anal"},{"issue":"16","key":"16130_CR47","doi-asserted-by":"publisher","first-page":"2051","DOI":"10.1016\/j.patrec.2013.06.022","volume":"34","author":"HD Yang","year":"2013","unstructured":"Yang HD, Lee SW (2013) Robust sign language recognition by combining manual and non-manual features based on conditional random field and support vector machine. Pattern Recogn Lett 34(16):2051\u20132056","journal-title":"Pattern Recogn Lett"},{"key":"16130_CR48","unstructured":"Yang W, Wang Y, Mori G (2009) Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks. In: ICCV. pp 3138\u20133146"},{"key":"16130_CR49","doi-asserted-by":"publisher","first-page":"91","DOI":"10.3390\/fi11040091","volume":"11","author":"X Zhang","year":"2016","unstructured":"Zhang X, Li X (2016) Dynamic gesture recognition based on MEMP network. Future Internet 11:91\u2013101","journal-title":"Future Internet"},{"key":"16130_CR50","doi-asserted-by":"publisher","first-page":"1511","DOI":"10.3390\/electronics8121511","volume":"8","author":"E Zhang","year":"2019","unstructured":"Zhang E, Xue B, Cao F, Duan J, Lin G, Lei Y (2019) Fusion of 2D CNN and 3D DenseNet for dynamic gesture recognition. Electronics 8:1511\u20131525","journal-title":"Electronics"},{"key":"16130_CR51","doi-asserted-by":"crossref","unstructured":"Zhang L, Zhu G, Shen P, Song J (2017) Learning spatiotemporal features using 3D CNN and convolutional LSTM for gesture recognition. In: Proceedings of the IEEE International Conference on Computer Vision. pp 3120\u20133128","DOI":"10.1109\/ICCVW.2017.369"},{"key":"16130_CR52","doi-asserted-by":"crossref","unstructured":"Zhao H, Shi J, Qi X, Wang X, Jia J (2017) Pyramid scene parsing network. In: CVPR. pp 2881\u20132890","DOI":"10.1109\/CVPR.2017.660"},{"key":"16130_CR53","doi-asserted-by":"crossref","unstructured":"Zhao Y, Xiong Y, Wang L, Wu Z, Lin D, Tang X (2017) Temporal action detection with structured segment networks. In: ICCV. pp 2933\u20132942","DOI":"10.1109\/ICCV.2017.317"},{"key":"16130_CR54","doi-asserted-by":"publisher","first-page":"4517","DOI":"10.1109\/ACCESS.2017.2684186","volume":"5","author":"G Zhu","year":"2017","unstructured":"Zhu G, Zhang L, Shen P, Song J (2017) Multimodal gesture recognition using 3-D convolution and convolutional LSTM. IEEE Access 5:4517\u20134524","journal-title":"IEEE Access"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16130-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-023-16130-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-023-16130-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,31]],"date-time":"2024-01-31T08:33:47Z","timestamp":1706690027000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-023-16130-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,14]]},"references-count":54,"journal-issue":{"issue":"6","published-online":{"date-parts":[[2024,2]]}},"alternative-id":["16130"],"URL":"https:\/\/doi.org\/10.1007\/s11042-023-16130-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,7,14]]},"assertion":[{"value":"24 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"31 May 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 June 2023","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"14 July 2023","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}