{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T16:31:24Z","timestamp":1775320284315,"version":"3.50.1"},"reference-count":66,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:00:00Z","timestamp":1545091200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundations of China","doi-asserted-by":"crossref","award":["61772396"],"award-info":[{"award-number":["61772396"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundations of China","doi-asserted-by":"crossref","award":["61472302"],"award-info":[{"award-number":["61472302"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundations of China","doi-asserted-by":"crossref","award":["61772392"],"award-info":[{"award-number":["61772392"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["JB170306"],"award-info":[{"award-number":["JB170306"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["JB170304"],"award-info":[{"award-number":["JB170304"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["JBF180301"],"award-info":[{"award-number":["JBF180301"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"name":"National Key R&D Program of China","award":["2018YFC0807500"],"award-info":[{"award-number":["2018YFC0807500"]}]},{"name":"Xi\u2019an Key Laboratory of Big Data and Intelligent Vision","award":["201805053ZD4CG37"],"award-info":[{"award-number":["201805053ZD4CG37"]}]},{"name":"Innovation Fund of Xidian University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Machine Vision and Applications"],"published-print":{"date-parts":[[2019,7]]},"DOI":"10.1007\/s00138-018-0996-x","type":"journal-article","created":{"date-parts":[[2018,12,18]],"date-time":"2018-12-18T00:02:54Z","timestamp":1545091374000},"page":"875-888","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["A spatiotemporal attention-based ResC3D model for large-scale gesture recognition"],"prefix":"10.1007","volume":"30","author":[{"given":"Yunan","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2872-388X","authenticated-orcid":false,"given":"Qiguang","family":"Miao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangda","family":"Qi","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenxin","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wanli","family":"Ouyang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,12,18]]},"reference":[{"issue":"1","key":"996_CR1","first-page":"74","volume":"7","author":"V Albu","year":"2016","unstructured":"Albu, V.: Measuring customer behavior with deep convolutional neural networks. BRAIN Broad Res. Artif. Intell. Neurosci. 7(1), 74\u201379 (2016)","journal-title":"BRAIN Broad Res. Artif. Intell. Neurosci."},{"key":"996_CR2","unstructured":"Andrade, E.L., Blunsden, S., Fisher, R.B.: Modelling crowd scenes for event detection. In: 18th International Conference on Pattern Recognition, 2006. ICPR 2006, vol. 1, pp. 175\u2013178. IEEE (2006)"},{"issue":"3","key":"996_CR3","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick, A.F., Davis, J.W.: The recognition of human movement using temporal templates. IEEE Trans. Pattern Anal. Mach. Intell. 23(3), 257\u2013267 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"996_CR4","doi-asserted-by":"crossref","unstructured":"Brox, T., Bruhn, A., Papenberg, N., Weickert, J.: High accuracy optical flow estimation based on a theory for warping. In: European Conference on Computer Vision, pp. 25\u201336. Springer (2004)","DOI":"10.1007\/978-3-540-24673-2_3"},{"issue":"8","key":"996_CR5","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1109\/TPAMI.2016.2519021","volume":"38","author":"JY Chang","year":"2016","unstructured":"Chang, J.Y.: Nonparametric feature matching based conditional random fields for gesture recognition from multi-modal video. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1612\u20131625 (2016)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"996_CR6","doi-asserted-by":"crossref","unstructured":"Choi, H., Park, H.: A hierarchical structure for gesture recognition using RGB-D sensor. In: Proceedings of the Second International Conference on Human\u2013Agent Interaction, pp. 265\u2013268. ACM (2014)","DOI":"10.1145\/2658861.2658938"},{"key":"996_CR7","doi-asserted-by":"crossref","unstructured":"Corradini, A.: Dynamic time warping for off-line recognition of a small gesture vocabulary. In: IEEE International Conference on Computer Vision Workshops, pp. 82\u201389. IEEE (2001)","DOI":"10.1109\/RATFG.2001.938914"},{"key":"996_CR8","doi-asserted-by":"crossref","unstructured":"Di\u00a0Benedetto, A., Palmieri, F.A., Cavallo, A., Falco, P.: A hidden markov model-based approach to grasping hand gestures classification. In: Advances in Neural Networks, pp. 415\u2013423. Springer (2016)","DOI":"10.1007\/978-3-319-33747-0_41"},{"issue":"23","key":"996_CR9","doi-asserted-by":"publisher","first-page":"15537","DOI":"10.1007\/s11042-015-2505-9","volume":"75","author":"J Ding","year":"2016","unstructured":"Ding, J., Chang, C.W.: An adaptive hidden markov model-based gesture recognition approach using kinect to simplify large-scale video data processing for humanoid robot imitation. Multimed. Tools Appl. 75(23), 15537\u201315551 (2016)","journal-title":"Multimed. Tools Appl."},{"key":"996_CR10","doi-asserted-by":"crossref","unstructured":"Donahue, J., Hendricks, L.A., Guadarrama, S., Rohrbach, M., Venugopalan, S., Saenko, K., Darrell, T.: Long-term recurrent convolutional networks for visual recognition and description. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 2625\u20132634 (2015)","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"996_CR11","first-page":"21:1","volume":"14","author":"J Duan","year":"2017","unstructured":"Duan, J., Wan, J., Zhou, S., Guo, X., Li, S.: A unified framework for multi-modal isolated gesture recognition. ACM Trans. Multimed. Comput. Commun. Appl. (TOMM) 14, 21:1\u201321:16 (2017)","journal-title":"ACM Trans. Multimed. Comput. Commun. Appl. (TOMM)"},{"issue":"8","key":"996_CR12","doi-asserted-by":"publisher","first-page":"1929","DOI":"10.1007\/s00138-014-0596-3","volume":"25","author":"I Guyon","year":"2014","unstructured":"Guyon, I., Athitsos, V., Jangyodsuk, P., Escalante, H.J.: The Chalearn gesture dataset (CGD 2011). Mach. Vis. Appl. 25(8), 1929\u20131951 (2014)","journal-title":"Mach. Vis. Appl."},{"issue":"9","key":"996_CR13","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.: Discriminant correlation analysis: real-time feature level fusion for multimodal biometric recognition. IEEE Trans. Inf. Forensics Secur. 11(9), 1984\u20131996 (2016)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"996_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"issue":"4","key":"996_CR15","doi-asserted-by":"publisher","first-page":"046109","DOI":"10.1103\/PhysRevE.75.046109","volume":"75","author":"D Helbing","year":"2007","unstructured":"Helbing, D., Johansson, A., Al-Abideen, H.Z.: Dynamics of crowd disasters: an empirical study. Phys. Rev. E 75(4), 046109 (2007)","journal-title":"Phys. Rev. E"},{"key":"996_CR16","unstructured":"Hong, P., Turk, M., Huang, T.S.: Gesture modeling and recognition using finite state machines. In: IEEE International Conference on Automatic Face and Gesture Recognition, pp. 410\u2013415. IEEE (2000)"},{"issue":"1","key":"996_CR17","doi-asserted-by":"publisher","first-page":"154","DOI":"10.1109\/JSEN.2014.2339843","volume":"15","author":"YL Hsu","year":"2015","unstructured":"Hsu, Y.L., Chu, C.L., Tsai, Y.J., Wang, J.S.: An inertial pen with dynamic time warping recognizer for handwriting and gesture recognition. IEEE Sens. J. 15(1), 154\u2013163 (2015)","journal-title":"IEEE Sens. J."},{"key":"996_CR18","doi-asserted-by":"crossref","unstructured":"Huang, S., Ramanan, D.: Expecting the unexpected: training detectors for unusual pedestrians with adversarial imposters. In: The IEEE Conference on Computer Vision and Pattern Recognition (CVPR), vol. 1 (2017)","DOI":"10.1109\/CVPR.2017.496"},{"issue":"1","key":"996_CR19","doi-asserted-by":"publisher","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","volume":"35","author":"S Ji","year":"2013","unstructured":"Ji, S., Xu, W., Yang, M., Yu, K.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"996_CR20","doi-asserted-by":"crossref","unstructured":"Jia, Y., Shelhamer, E., Donahue, J., Karayev, S., Long, J., Girshick, R., Guadarrama, S., Darrell, T.: Caffe: convolutional architecture for fast feature embedding. In: ACM International Conference on Multimedia, pp. 675\u2013678. ACM (2014)","DOI":"10.1145\/2647868.2654889"},{"key":"996_CR21","doi-asserted-by":"crossref","unstructured":"Jin, C.B., Li, S., Kim, H.: Real-time action detection in video surveillance using sub-action descriptor with multi-cnn. ArXiv preprint arXiv:1710.03383 (2017)","DOI":"10.5302\/J.ICROS.2018.17.0243"},{"issue":"11","key":"996_CR22","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.1109\/TPAMI.2012.19","volume":"34","author":"MB Ka\u00e2niche","year":"2012","unstructured":"Ka\u00e2niche, M.B., Bremond, F.: Recognizing gestures by learning local motion signatures of hog descriptors. IEEE Trans. Pattern Anal. Mach. Intell. 34(11), 2247\u20132258 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"996_CR23","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"996_CR24","doi-asserted-by":"crossref","unstructured":"Klaser, A., Marsza\u0142ek, M., Schmid, C.: A spatio-temporal descriptor based on 3D-gradients. In: British Machine Vision Conference, pp. 1\u201310. British Machine Vision Association (2008)","DOI":"10.5244\/C.22.99"},{"key":"996_CR25","doi-asserted-by":"publisher","first-page":"226","DOI":"10.1016\/j.engappai.2017.10.001","volume":"67","author":"KE Ko","year":"2018","unstructured":"Ko, K.E., Sim, K.B.: Deep convolutional framework for abnormal behavior detection in a smart surveillance system. Eng. Appl. Artif. Intell. 67, 226\u2013234 (2018)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"996_CR26","first-page":"2513","volume":"15","author":"J Konecn\u1ef3","year":"2014","unstructured":"Konecn\u1ef3, J., Hagara, M.: One-shot-learning gesture recognition using hog\u2013hof. J. Mach. Learn. Res. 15, 2513\u20132532 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"996_CR27","unstructured":"Kratz, L., Nishino, K.: Anomaly detection in extremely crowded scenes using spatio-temporal motion pattern models. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 1446\u20131453. IEEE (2009)"},{"issue":"5","key":"996_CR28","doi-asserted-by":"publisher","first-page":"339","DOI":"10.1177\/0037549705052772","volume":"81","author":"TI Lakoba","year":"2005","unstructured":"Lakoba, T.I., Kaup, D.J., Finkelstein, N.M.: Modifications of the Helbing\u2013Molnar\u2013Farkas\u2013Vicsek social force model for pedestrian evolution. Simulation 81(5), 339\u2013352 (2005)","journal-title":"Simulation"},{"issue":"1","key":"996_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1364\/JOSA.61.000001","volume":"61","author":"EH Land","year":"1971","unstructured":"Land, E.H., McCann, J.J.: Lightness and retinex theory. Josa 61(1), 1\u201311 (1971)","journal-title":"Josa"},{"key":"996_CR30","doi-asserted-by":"crossref","unstructured":"LeCun, Y., Huang, F.J., Bottou, L.: Learning methods for generic object recognition with invariance to pose and lighting. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, vol. 2, pp. 96\u2013104. IEEE (2004)","DOI":"10.1109\/CVPR.2004.1315150"},{"key":"996_CR31","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, X., Tao, J., Ding, L., Gao, H., Deng, Z.: Interact with robot: an efficient approach based on finite state machine and mouse gesture recognition. In: 2016 9th International Conference on Human System Interactions (HSI), pp. 203\u2013208. IEEE (2016)","DOI":"10.1109\/HSI.2016.7529632"},{"key":"996_CR32","unstructured":"Li, Y., Miao, Q., Tian, K., Fan, Y., Xu, X., Li, R., Song, J.: Large-scale gesture recognition with a fusion of RGB-D data based on the C3D model. In: IEEE International Conference on Pattern Recognition Workshops. IEEE (2016)"},{"issue":"10","key":"996_CR33","doi-asserted-by":"publisher","first-page":"2956","DOI":"10.1109\/TCSVT.2017.2749509","volume":"28","author":"Y Li","year":"2017","unstructured":"Li, Y., Miao, Q., Tian, K., Fan, Y., Xu, X., Li, R., Song, J.: Large-scale gesture recognition with a fusion of RGB-D data based on saliency theory and C3D model. IEEE Trans. Circuits Syst. Video Technol. 28(10), 2956\u20132964 (2017)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"996_CR34","doi-asserted-by":"publisher","unstructured":"Li, Y., Miao, Q., Tian, K., Fan, Y., Xu, X., Ma, Z., Song, J.: Large-scale gesture recognition with a fusion of RGB-D data based on optical flow and the C3D model. Pattern Recognit. Lett. (2017). https:\/\/doi.org\/10.1016\/j.patrec.2017.12.003","DOI":"10.1016\/j.patrec.2017.12.003"},{"issue":"4","key":"996_CR35","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1109\/83.913594","volume":"10","author":"C Liu","year":"2001","unstructured":"Liu, C., Wechsler, H.: A shape-and texture-based enhanced Fisher classifier for face recognition. IEEE Trans. Image Process. 10(4), 598\u2013608 (2001)","journal-title":"IEEE Trans. Image Process."},{"key":"996_CR36","first-page":"3","volume":"1","author":"L Liu","year":"2013","unstructured":"Liu, L., Shao, L.: Learning discriminative representations from RGB-D video data. IJCAI 1, 3 (2013)","journal-title":"IJCAI"},{"key":"996_CR37","doi-asserted-by":"publisher","first-page":"747","DOI":"10.1016\/j.neucom.2015.11.005","volume":"175","author":"M Liu","year":"2016","unstructured":"Liu, M., Liu, H.: Depth context: a new descriptor for human activity recognition by using sole depth sequences. Neurocomputing 175, 747\u2013758 (2016)","journal-title":"Neurocomputing"},{"key":"996_CR38","doi-asserted-by":"crossref","unstructured":"Liu, Z., Chai, X., Liu, Z., Chen, X.: Continuous gesture recognition with hand-oriented spatiotemporal feature. In: Workshops in Conjunction with IEEE International Conference on Computer Vision, pp. 3056\u20133064 (2017)","DOI":"10.1109\/ICCVW.2017.361"},{"key":"996_CR39","doi-asserted-by":"crossref","unstructured":"Malgireddy, M.R., Inwogu, I., Govindaraju, V.: A temporal bayesian model for classifying, detecting and localizing activities in video sequences. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 43\u201348. IEEE (2012)","DOI":"10.1109\/CVPRW.2012.6239185"},{"issue":"1","key":"996_CR40","first-page":"2189","volume":"14","author":"MR Malgireddy","year":"2013","unstructured":"Malgireddy, M.R., Nwogu, I., Govindaraju, V.: Language-motivated approaches to action recognition. J. Mach. Learn. Res. 14(1), 2189\u20132212 (2013)","journal-title":"J. Mach. Learn. Res."},{"key":"996_CR41","unstructured":"Mehran, R., Oyama, A., Shah, M.: Abnormal crowd behavior detection using social force model. In: IEEE Conference on Computer Vision and Pattern Recognition, 2009. CVPR 2009, pp. 935\u2013942. IEEE (2009)"},{"key":"996_CR42","doi-asserted-by":"crossref","unstructured":"Miao, Q., Li, Y., Ouyang, W., Ma, Z., Xu, X., Shi, W., Cao, X.: Multimodal gesture recognition based on the ResC3D network. In: Workshops in Conjunction with IEEE International Conference on Computer Vision, pp. 3047\u20133055 (2017)","DOI":"10.1109\/ICCVW.2017.360"},{"key":"996_CR43","doi-asserted-by":"crossref","unstructured":"Molchanov, P., Yang, X., Gupta, S., Kim, K., Tyree, S., Kautz, J.: Online detection and classification of dynamic hand gestures with recurrent 3D convolutional neural network. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 4207\u20134215. IEEE (2016)","DOI":"10.1109\/CVPR.2016.456"},{"key":"996_CR44","doi-asserted-by":"crossref","unstructured":"Nishida, N., Nakayama, H.: Multimodal gesture recognition using multi-stream recurrent neural network. In: Pacific-Rim Symposium on Image and Video Technology, pp. 682\u2013694. Springer (2015)","DOI":"10.1007\/978-3-319-29451-3_54"},{"issue":"1","key":"996_CR45","first-page":"255","volume":"16","author":"V Pitsikalis","year":"2015","unstructured":"Pitsikalis, V., Katsamanis, A., Theodorakis, S., Maragos, P.: Multimodal gesture recognition via multiple hypotheses rescoring. J. Mach. Learn. Res. 16(1), 255\u2013284 (2015)","journal-title":"J. Mach. Learn. Res."},{"issue":"2","key":"996_CR46","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1109\/TIM.2015.2498560","volume":"65","author":"G Plouffe","year":"2016","unstructured":"Plouffe, G., Cretu, A.M.: Static and dynamic hand gesture recognition in depth data using dynamic time warping. IEEE Trans. Instrum. Meas. 65(2), 305\u2013316 (2016)","journal-title":"IEEE Trans. Instrum. Meas."},{"issue":"1","key":"996_CR47","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-012-9356-9","volume":"43","author":"SS Rautaray","year":"2015","unstructured":"Rautaray, S.S., Agrawal, A.: Vision based hand gesture recognition for human computer interaction: a survey. Artif. Intell. Rev. 43(1), 1\u201354 (2015)","journal-title":"Artif. Intell. Rev."},{"key":"996_CR48","doi-asserted-by":"crossref","unstructured":"Sanin, A., Sanderson, C., Harandi, M.T., Lovell, B.C.: Spatio-temporal covariance descriptors for action and gesture recognition. In: IEEE Workshops on Applications of Computer Vision, pp. 103\u2013110. IEEE (2013)","DOI":"10.1109\/WACV.2013.6475006"},{"issue":"1","key":"996_CR49","doi-asserted-by":"publisher","first-page":"116","DOI":"10.1145\/2398356.2398381","volume":"56","author":"J Shotton","year":"2013","unstructured":"Shotton, J., Sharp, T., Kipman, A., Fitzgibbon, A., Finocchio, M., Blake, A., Cook, M., Moore, R.: Real-time human pose recognition in parts from single depth images. Commun. ACM 56(1), 116\u2013124 (2013)","journal-title":"Commun. ACM"},{"key":"996_CR50","unstructured":"Springenberg, J.T., Dosovitskiy, A., Brox, T., Riedmiller, M.: Striving for simplicity: the all convolutional net. ArXiv preprint arXiv:1412.6806 (2014)"},{"issue":"12","key":"996_CR51","doi-asserted-by":"publisher","first-page":"2437","DOI":"10.1016\/j.patcog.2004.12.013","volume":"38","author":"QS Sun","year":"2005","unstructured":"Sun, Q.S., Zeng, S.G., Liu, Y., Heng, P.A., Xia, D.S.: A new method of feature fusion and its application in image recognition. Pattern Recognit. 38(12), 2437\u20132448 (2005)","journal-title":"Pattern Recognit."},{"key":"996_CR52","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.patcog.2018.02.011","volume":"80","author":"J Tang","year":"2018","unstructured":"Tang, J., Cheng, H., Zhao, Y., Guo, H.: Structured dynamic time warping for continuous hand trajectory gesture recognition. Pattern Recognit. 80, 21\u201331 (2018)","journal-title":"Pattern Recognit."},{"key":"996_CR53","doi-asserted-by":"crossref","unstructured":"Tran, D., Bourdev, L., Fergus, R., Torresani, L., Paluri, M.: Learning spatiotemporal features with 3D convolutional networks. In: IEEE International Conference on Computer Vision, pp. 4489\u20134497. IEEE (2015)","DOI":"10.1109\/ICCV.2015.510"},{"key":"996_CR54","doi-asserted-by":"crossref","unstructured":"Wan, J., Escalera, S., Anbarjafari, G., Escalante, H.J., Bar\u00f3, X., Guyon, I., Madadi, M., Allik, J., Gorbova, J., Lin, C., et\u00a0al.: Results and analysis of Chalearn lap multi-modal isolated and continuous gesture recognition, and real versus fake expressed emotions challenges. In: ICCV Workshops, pp. 3189\u20133197 (2017)","DOI":"10.1109\/ICCVW.2017.377"},{"issue":"8","key":"996_CR55","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1109\/TPAMI.2015.2513479","volume":"38","author":"J Wan","year":"2015","unstructured":"Wan, J., Guo, G., Li, S.: Explore efficient local features from RGB-D data for one-shot learning gesture recognition. IEEE Trans. Pattern Anal. Mach. Intell. 38(8), 1626\u20131639 (2015)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"996_CR56","doi-asserted-by":"crossref","unstructured":"Wan, J., Li, S.Z., Zhao, Y., Zhou, S., Guyon, I., Escalera, S.: Chalearn looking at people RGB-D isolated and continuous datasets for gesture recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 56\u201364. IEEE (2016)","DOI":"10.1109\/CVPRW.2016.100"},{"issue":"2","key":"996_CR57","doi-asserted-by":"publisher","first-page":"3017","DOI":"10.1117\/1.JEI.23.2.023017","volume":"23","author":"J Wan","year":"2014","unstructured":"Wan, J., Ruan, Q., Li, W., An, G., Zhao, R.: 3D SMoSIFT: three-dimensional sparse motion scale invariant feature transform for activity recognition from RGB-D videos. J. Electron. Imaging 23(2), 3017\u20133017 (2014)","journal-title":"J. Electron. Imaging"},{"key":"996_CR58","doi-asserted-by":"crossref","unstructured":"Wang, H., Wang, P., Song, Z., Li, W.: Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3138\u20133146 (2017)","DOI":"10.1109\/ICCVW.2017.371"},{"key":"996_CR59","doi-asserted-by":"crossref","unstructured":"Wang, P., Li, W., Liu, S., Gao, Z., Tang, C., Ogunbona, P.: Large-scale isolated gesture recognition using convolutional neural networks. In: Proceedings of International Conference on PR, pp. 7\u201312. IEEE (2016)","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"996_CR60","doi-asserted-by":"crossref","unstructured":"Wang, S.B., Quattoni, A., Morency, L.P., Demirdjian, D., Darrell, T.: Hidden conditional random fields for gesture recognition. In: IEEE Conference on Computer Vision and Pattern Recognition Workshops, vol. 2, pp. 1521\u20131527. IEEE (2006)","DOI":"10.1109\/CVPR.2006.132"},{"issue":"2","key":"996_CR61","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1016\/j.cviu.2006.07.013","volume":"104","author":"D Weinland","year":"2006","unstructured":"Weinland, D., Ronfard, R., Boyer, E.: Free viewpoint action recognition using motion history volumes. Comput. Vis. Image Underst. 104(2), 249\u2013257 (2006)","journal-title":"Comput. Vis. Image Underst."},{"issue":"1","key":"996_CR62","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/S0031-3203(01)00152-2","volume":"35","author":"J Yang","year":"2002","unstructured":"Yang, J., Yang, J.: Generalized K\u2013L transform based combined feature extraction. Pattern Recognit. 35(1), 295\u2013297 (2002)","journal-title":"Pattern Recognit."},{"issue":"11","key":"996_CR63","doi-asserted-by":"publisher","first-page":"1805","DOI":"10.1016\/S0031-3203(99)00175-2","volume":"33","author":"M Yeasin","year":"2000","unstructured":"Yeasin, M., Chaudhuri, S.: Visual understanding of dynamic hand gestures. Pattern Recognit. 33(11), 1805\u20131817 (2000)","journal-title":"Pattern Recognit."},{"key":"996_CR64","doi-asserted-by":"crossref","unstructured":"Zhang, L., Zhu, G., Shen, P., Song, J., Shah, S.A., Bennamoun, M.: Learning spatiotemporal features using 3DCNN and convolutional LSTM for gesture recognition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 3120\u20133128 (2017)","DOI":"10.1109\/ICCVW.2017.369"},{"key":"996_CR65","doi-asserted-by":"crossref","unstructured":"Zhu, G., Zhang, L., Mei, L., Shao, J., Song, J., Shen, P.: Large-scale isolated gesture recognition using pyramidal 3D convolutional networks. In: IEEE International Conference on Pattern Recognition Workshops (2016)","DOI":"10.1109\/ICPR.2016.7899601"},{"key":"996_CR66","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.: Multimodal gesture recognition using 3D convolution and convolutional LSTM. IEEE Access 5, 4517\u20134524 (2017)","journal-title":"IEEE Access"}],"container-title":["Machine Vision and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0996-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00138-018-0996-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00138-018-0996-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T15:29:15Z","timestamp":1775316555000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00138-018-0996-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,12,18]]},"references-count":66,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2019,7]]}},"alternative-id":["996"],"URL":"https:\/\/doi.org\/10.1007\/s00138-018-0996-x","relation":{},"ISSN":["0932-8092","1432-1769"],"issn-type":[{"value":"0932-8092","type":"print"},{"value":"1432-1769","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,12,18]]},"assertion":[{"value":"5 April 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 November 2018","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 December 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 December 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}