{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T15:53:08Z","timestamp":1784130788457,"version":"3.55.0"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T00:00:00Z","timestamp":1668124800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Fundamental Research Funds of China for the Central Universities","award":["No.B200202188"],"award-info":[{"award-number":["No.B200202188"]}]},{"DOI":"10.13039\/501100018581","name":"Jiangsu Water Conservancy Science and Technology Project","doi-asserted-by":"crossref","award":["No. 2018057"],"award-info":[{"award-number":["No. 2018057"]}],"id":[{"id":"10.13039\/501100018581","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2023,5]]},"DOI":"10.1007\/s11042-022-14193-0","type":"journal-article","created":{"date-parts":[[2022,11,11]],"date-time":"2022-11-11T08:03:04Z","timestamp":1668153784000},"page":"16409-16430","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Multimodal human action recognition based on spatio-temporal action representation recognition model"],"prefix":"10.1007","volume":"82","author":[{"given":"Qianhan","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5625-0402","authenticated-orcid":false,"given":"Qian","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xing","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,11]]},"reference":[{"issue":"1","key":"14193_CR1","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TPAMI.2015.2439257","volume":"38","author":"BB Amor","year":"2015","unstructured":"Amor BB, Su J, Srivastava A (2015) Action recognition using rate-invariant analysis of skeletal shape trajectories. IEEE Trans Pattern Anal Machine Intell 38(1):1\u201313","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"issue":"3","key":"14193_CR2","doi-asserted-by":"publisher","first-page":"257","DOI":"10.1109\/34.910878","volume":"23","author":"AF Bobick","year":"2001","unstructured":"Bobick AF, Davis JW (2001) The recognition of human movement using temporal templates. IEEE Trans Pattern Anal Machine Intell 23(3):257\u2013267","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"14193_CR3","doi-asserted-by":"crossref","unstructured":"Bregonzio M, Gong S, Xiang T (2009) Recognising action as clouds of space-time interest points. In: 2009 IEEE conference on computer vision and pattern recognition, pp 1948\u20131955","DOI":"10.1109\/CVPR.2009.5206779"},{"issue":"15","key":"14193_CR4","doi-asserted-by":"publisher","first-page":"21085","DOI":"10.1007\/s11042-019-7365-2","volume":"78","author":"MF Bulbul","year":"2019","unstructured":"Bulbul MF, Islam S, Ali H (2019) 3D human action analysis and recognition through GLAC descriptor on 2D motion and static posture images. Multimed Tools Appl 78(15):21085\u201321111","journal-title":"Multimed Tools Appl"},{"key":"14193_CR5","first-page":"168","volume":"2015","author":"C Chen","year":"2015","unstructured":"Chen C, Jafari R, Kehtarnavaz N (2015) UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. IEEE Int Conf Image Process (ICIP) 2015:168\u2013172","journal-title":"IEEE Int Conf Image Process (ICIP)"},{"issue":"18","key":"14193_CR6","doi-asserted-by":"publisher","first-page":"5180","DOI":"10.3390\/s20185180","volume":"20","author":"X Chao","year":"2020","unstructured":"Chao X, Hou Z, Liang J, Yang T (2020) Integrally cooperative spatio-temporal feature representation of motion joints for action recognition. Sensors 20 (18):5180","journal-title":"Sensors"},{"key":"14193_CR7","doi-asserted-by":"crossref","unstructured":"Chen C, Jafari R, Kehtarnavaz N (2015) UTD-MHAD: a multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: 2015 IEEE international conference on image processing (ICIP), pp 168\u2013172","DOI":"10.1109\/ICIP.2015.7350781"},{"issue":"1","key":"14193_CR8","doi-asserted-by":"publisher","first-page":"113","DOI":"10.1016\/S0893-6080(03)00169-2","volume":"17","author":"V Cherkassky","year":"2004","unstructured":"Cherkassky V, Ma Y (2004) Practical selection of SVM parameters and noise estimation for SVM regression. Neur Netw 17(1):113\u2013126","journal-title":"Neur Netw"},{"key":"14193_CR9","doi-asserted-by":"crossref","unstructured":"Cutler A, Cutler DR, Stevens JR (2012) Random forests. In: Ensemble machine learning, pp 157\u2013175","DOI":"10.1007\/978-1-4419-9326-7_5"},{"key":"14193_CR10","doi-asserted-by":"crossref","unstructured":"Das S, Sharma S, Dai R, Bremond F, Thonnat M (2020) Vpn: learning video-pose embedding for activities of daily living. In: European conference on computer vision, pp 72\u201390","DOI":"10.1007\/978-3-030-58545-7_5"},{"key":"14193_CR11","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.engappai.2018.08.014","volume":"77","author":"C Dhiman","year":"2019","unstructured":"Dhiman C, Vishwakarma DK (2019) A review of state-of-the-art techniques for abnormal human activity recognition. Eng Appl Artif Intell 77:21\u201345","journal-title":"Eng Appl Artif Intell"},{"key":"14193_CR12","doi-asserted-by":"publisher","first-page":"3835","DOI":"10.1109\/TIP.2020.2965299","volume":"29","author":"C Dhiman","year":"2020","unstructured":"Dhiman C, Vishwakarma DK (2020) View-invariant deep architecture for human action recognition using two-stream motion and shape temporal dynamics. IEEE Trans Image Process 29:3835\u20133844","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"14193_CR13","doi-asserted-by":"publisher","first-page":"5275","DOI":"10.1109\/TIP.2018.2855438","volume":"27","author":"NED Elmadany","year":"2018","unstructured":"Elmadany NED, He Y, Guan L (2018) Information fusion for human action recognition via biset\/multiset globality locality preserving canonical correlation analysis. IEEE Trans Image Process 27(11):5275\u20135287","journal-title":"IEEE Trans Image Process"},{"issue":"5","key":"14193_CR14","doi-asserted-by":"publisher","first-page":"1317","DOI":"10.1109\/TMM.2018.2875510","volume":"21","author":"NED Elmadany","year":"2018","unstructured":"Elmadany NED, He Y, Guan L (2018) Multimodal learning for human action recognition via bimodal\/multimodal hybrid centroid canonical correlation analysis. IEEE Trans Multimed 21(5):1317\u20131331","journal-title":"IEEE Trans Multimed"},{"key":"14193_CR15","unstructured":"Gowayyed MA, Torki M, Hussein ME, El-Saban M (2013) Histogram of oriented displacements (HOD): describing trajectories of human joints for action recognition. In: IJCAI, vol 1, pp 1351\u20131357"},{"key":"14193_CR16","doi-asserted-by":"crossref","unstructured":"Guo G, Wang H, Bell D, Bi Y, Greer K (2003) KNN Model-based approach in classification. In: OTM confederated international conferences on the move to meaningful internet systems, pp 986\u2013996","DOI":"10.1007\/978-3-540-39964-3_62"},{"issue":"12","key":"14193_CR17","doi-asserted-by":"publisher","first-page":"2639","DOI":"10.1162\/0899766042321814","volume":"16","author":"DR Hardoon","year":"2004","unstructured":"Hardoon DR, Szedmak S, Shawe-Taylor J (2004) Canonical correlation analysis: an overview with application to learning methods. Neural Comput 16 (12):2639\u20132664","journal-title":"Neural Comput"},{"issue":"3","key":"14193_CR18","doi-asserted-by":"publisher","first-page":"807","DOI":"10.1109\/TCSVT.2016.2628339","volume":"28","author":"Y Hou","year":"2016","unstructured":"Hou Y, Li Z, Wang P, Li W (2016) Skeleton optical spectra-based action recognition using convolutional neural networks. IEEE Trans Circuits Syst Video Technol 28(3):807\u2013811","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"14193_CR19","doi-asserted-by":"crossref","unstructured":"Hu JF, Zheng WS, Pan J, Lai J, Zhang J (2018) Deep bilinear learning for rgb-d action recognition. In: Proceedings of the European conference on computer vision (ECCV), pp 335\u2013351","DOI":"10.1007\/978-3-030-01234-2_21"},{"issue":"1-3","key":"14193_CR20","doi-asserted-by":"publisher","first-page":"489","DOI":"10.1016\/j.neucom.2005.12.126","volume":"70","author":"GB Huang","year":"2006","unstructured":"Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1-3):489\u2013501","journal-title":"Neurocomputing"},{"issue":"9","key":"14193_CR21","doi-asserted-by":"publisher","first-page":"1806","DOI":"10.1109\/TSMC.2018.2850149","volume":"49","author":"A Kamel","year":"2018","unstructured":"Kamel A, Sheng B, Yang P, Li P, Shen R, Feng DD (2018) Deep convolutional neural networks for human action recognition using depth maps and postures. IEEE Trans Syst Man Cybern Syst 49(9):1806\u20131819","journal-title":"IEEE Trans Syst Man Cybern Syst"},{"issue":"1","key":"14193_CR22","doi-asserted-by":"publisher","first-page":"188","DOI":"10.1109\/TPAMI.2015.2435740","volume":"38","author":"M Kan","year":"2015","unstructured":"Kan M, Shan S, Zhang H, Lao S, Chen X (2015) Multi-view discriminant analysis. IEEE Trans Pattern Anal Machine Intell 38(1):188\u2013194","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"14193_CR23","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.isprsjprs.2020.12.010","volume":"173","author":"T Kattenborn","year":"2021","unstructured":"Kattenborn T, Leitloff J, Schiefer F, Hinz S (2021) Review on Convolutional Neural Networks (CNN) in vegetation remote sensing. ISPRS J Photogramm Remote Sens 173:24\u201349","journal-title":"ISPRS J Photogramm Remote Sens"},{"issue":"6","key":"14193_CR24","doi-asserted-by":"publisher","first-page":"731","DOI":"10.1109\/LSP.2017.2690339","volume":"24","author":"Q Ke","year":"2017","unstructured":"Ke Q, An S, Bennamoun M, Sohel F, Boussaid F (2017) Skeletonnet: mining deep part features for 3-d action recognition. IEEE Signal Process Lett 24(6):731\u2013735","journal-title":"IEEE Signal Process Lett"},{"key":"14193_CR25","doi-asserted-by":"crossref","unstructured":"Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2017) A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3288\u20133297","DOI":"10.1109\/CVPR.2017.486"},{"key":"14193_CR26","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1016\/j.patrec.2018.04.035","volume":"115","author":"P Khaire","year":"2018","unstructured":"Khaire P, Kumar P, Imran J (2018) Combining CNN streams of RGB-d and skeletal data for human activity recognition. Pattern Recogn Lett 115:107\u2013116","journal-title":"Pattern Recogn Lett"},{"key":"14193_CR27","doi-asserted-by":"crossref","unstructured":"Khaire P, Imran J, Kumar P (2018) Human activity recognition by fusion of rgb, depth, and skeletal data. In: Proceedings of 2nd international conference on computer vision & image processing, pp 409\u2013421","DOI":"10.1007\/978-981-10-7895-8_32"},{"issue":"3","key":"14193_CR28","doi-asserted-by":"publisher","first-page":"349","DOI":"10.1109\/TCE.2019.2924177","volume":"65","author":"HG Kim","year":"2019","unstructured":"Kim HG, Kim GY, Kim JY (2019) Music recommendation system using human activity recognition from accelerometer data. IEEE Trans Consum Electron 65(3):349\u2013358","journal-title":"IEEE Trans Consum Electron"},{"key":"14193_CR29","doi-asserted-by":"crossref","unstructured":"Koniusz P, Cherian A, Porikli F (2016) Tensor representations via kernel linearization for action recognition from 3d skeletons. In: European conference on computer vision, pp 37\u201353","DOI":"10.1007\/978-3-319-46493-0_3"},{"issue":"5","key":"14193_CR30","doi-asserted-by":"publisher","first-page":"624","DOI":"10.1109\/LSP.2017.2678539","volume":"24","author":"C Li","year":"2017","unstructured":"Li C, Hou Y, Wang P, Li W (2017) Joint distance maps based action recognition with convolutional neural networks. IEEE Signal Process Lett 24(5):624\u2013628","journal-title":"IEEE Signal Process Lett"},{"key":"14193_CR31","doi-asserted-by":"crossref","unstructured":"Li M, Chen S, Chen X, Zhang Y, Wang Y, Tian Q (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, p 2019","DOI":"10.1109\/CVPR.2019.00371"},{"key":"14193_CR32","doi-asserted-by":"publisher","first-page":"107356","DOI":"10.1016\/j.patcog.2020.107356","volume":"104","author":"J Li","year":"2020","unstructured":"Li J, Xie X, Pan Q, Cao Y, Zhao Z, Shi G (2020) SGM-Net: skeleton-guided multimodal network for action recognition. Pattern Recogn 104:107356","journal-title":"Pattern Recogn"},{"key":"14193_CR33","doi-asserted-by":"crossref","unstructured":"Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos \u201cin the wild\u201d. In: 2009 IEEE conference on computer vision and pattern recognition. IEEE, pp 1996\u20132003","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"14193_CR34","first-page":"9","volume":"2010","author":"W Li","year":"2010","unstructured":"Li W, Zhang Z, Liu Z (2010) Action recognition based on a bag of 3D points. IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) 2010:9\u201314","journal-title":"IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)"},{"issue":"16","key":"14193_CR35","doi-asserted-by":"publisher","first-page":"21617","DOI":"10.1007\/s11042-017-5593-x","volume":"77","author":"XS Nguyen","year":"2018","unstructured":"Nguyen XS, Mouaddib AI, Nguyen TP, Jeanpierre L (2018) Action recognition in depth videos using hierarchical gaussian descriptor. Multimed Tools Appl 77(16):21617\u201321652","journal-title":"Multimed Tools Appl"},{"key":"14193_CR36","doi-asserted-by":"crossref","unstructured":"Ohn-Bar E, Trivedi M (2013) Joint angles similarities and HOG2 for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 465\u2013470","DOI":"10.1109\/CVPRW.2013.76"},{"key":"14193_CR37","doi-asserted-by":"crossref","unstructured":"Oreifej O, Liu Z (2013) Hon4d: histogram of oriented 4d normals for activity recognition from depth sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 716\u2013723","DOI":"10.1109\/CVPR.2013.98"},{"key":"14193_CR38","doi-asserted-by":"publisher","first-page":"127","DOI":"10.1016\/j.neucom.2020.04.034","volume":"406","author":"X Qin","year":"2020","unstructured":"Qin X, Ge Y, Feng J, Yang D, Chen F, Huang S, Xu L (2020) DTMMN: Deep Transfer multi-metric network for RGB-d action recognition. Neurocomputing 406:127\u2013134","journal-title":"Neurocomputing"},{"key":"14193_CR39","doi-asserted-by":"crossref","unstructured":"Rahmani H, Bennamoun M (2017) Learning action recognition model from depth and skeleton videos. In: Proceedings of the IEEE international conference on computer vision, pp 5832\u20135841","DOI":"10.1109\/ICCV.2017.621"},{"key":"14193_CR40","first-page":"3164","volume":"37","author":"SS Rani","year":"2021","unstructured":"Rani SS, Naidu GA, Shree VU (2021) Kinematic joint descriptor and depth motion descriptor with convolutional neural networks for human action recognition. Materials Today: Proceedings 37:3164\u20133173","journal-title":"Materials Today: Proceedings"},{"key":"14193_CR41","unstructured":"Rasiwasia N, Mahajan D, Mahadevan V, Aggarwal G (2014) Cluster canonical correlation analysis. In: Artificial intelligence and statistics. PMLR, pp 823\u2013831"},{"issue":"5","key":"14193_CR42","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1109\/TPAMI.2017.2691321","volume":"40","author":"A Shahroudy","year":"2017","unstructured":"Shahroudy A, Ng TT, Gong Y, Wang G (2017) Deep multimodal feature analysis for action recognition in rgb+ d videos. IEEE Trans Pattern Anal Machine Intell 40(5):1045\u20131058","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"14193_CR43","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G (2016) Ntu rgb+ d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"14193_CR44","doi-asserted-by":"crossref","unstructured":"Sharma A, Kumar A, Daume H, Jacobs DW (2012) Generalized multiview analysis: a discriminative latent space. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE, pp 2160\u20132167","DOI":"10.1109\/CVPR.2012.6247923"},{"key":"14193_CR45","doi-asserted-by":"publisher","first-page":"107511","DOI":"10.1016\/j.patcog.2020.107511","volume":"107","author":"C Si","year":"2020","unstructured":"Si C, Jing Y, Wang W, Wang L, Tan T (2020) Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network. Pattern Recogn 107:107511","journal-title":"Pattern Recogn"},{"key":"14193_CR46","doi-asserted-by":"crossref","unstructured":"Si C, Chen W, Wang W, Wang L, Tan T (2019) An attention enhanced graph convolutional lstm network for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 1227\u20131236","DOI":"10.1109\/CVPR.2019.00132"},{"key":"14193_CR47","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2018) Skeleton-indexed deep multi-modal feature learning for high performance human action recognition. In: 2018 IEEE international conference on multimedia and expo (ICME). IEEE, pp 1\u20136","DOI":"10.1109\/ICME.2018.8486486"},{"key":"14193_CR48","doi-asserted-by":"crossref","unstructured":"Sun L, Jia K, Chen K, Yeung DY, Shi BE, Savarese S (2017) Lattice long short-term memory for human action recognition. In: Proceedings of the IEEE international conference on computer vision, pp 2147\u20132156","DOI":"10.1109\/ICCV.2017.236"},{"key":"14193_CR49","doi-asserted-by":"crossref","unstructured":"Tran QD, Ly NQ (2013) Sparse spatio-temporal representation of joint shape-motion cues for human action recognition in depth sequences. In: The 2013 RIVF international conference on computing & communication technologies-research innovation, and vision for future (RIVF), pp 253\u2013258","DOI":"10.1109\/RIVF.2013.6719903"},{"key":"14193_CR50","doi-asserted-by":"crossref","unstructured":"Vishwakarma DK, Kapoor R (2012) Simple and intelligent system to recognize the expression of speech-disabled person. In: 2012 4th international conference on intelligent human computer interaction (IHCI), pp 1\u20136","DOI":"10.1109\/IHCI.2012.6481804"},{"key":"14193_CR51","doi-asserted-by":"crossref","unstructured":"Vemulapalli R, Arrate F, Chellappa R (2014) Human action recognition by representing 3d skeletons as points in a lie group. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 588\u2013595","DOI":"10.1109\/CVPR.2014.82"},{"key":"14193_CR52","unstructured":"Vishwakarma DK, Kapoor R, Maheshwari R, Kapoor V, Raman S (2015) Recognition of abnormal human activity using the changes in orientation of silhouette in key frames. In: 2015 2nd international conference on computing for sustainable global development (INDIACom), pp 336\u2013341"},{"issue":"4","key":"14193_CR53","doi-asserted-by":"publisher","first-page":"454","DOI":"10.1504\/IJCVR.2017.084991","volume":"7","author":"DK Vishwakarma","year":"2017","unstructured":"Vishwakarma DK, Kapoor R (2017) An efficient interpretation of hand gestures to control smart interactive television. International Journal of Computational Vision and Robotics 7(4):454\u2013 471","journal-title":"International Journal of Computational Vision and Robotics"},{"issue":"11","key":"14193_CR54","doi-asserted-by":"publisher","first-page":"3305","DOI":"10.3390\/s20113305","volume":"20","author":"H Wang","year":"2020","unstructured":"Wang H, Song Z, Li W, Wang P (2020) A hybrid network for large-scale action recognition from rgb and depth modalities. Sensors 20(11):3305","journal-title":"Sensors"},{"key":"14193_CR55","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Z, Chorowski J, Chen Z, Wu Y (2012) Robust 3d action recognition with random occupancy patterns. In: European conference on computer vision, pp 872\u2013885","DOI":"10.1007\/978-3-642-33709-3_62"},{"key":"14193_CR56","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2012) Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE conference on computer vision and pattern recognition, pp 1290\u2013 1297","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"14193_CR57","doi-asserted-by":"crossref","unstructured":"Wang L, Ding Z, Tao Z, Liu Y, Fu Y (2019) Generative multi-view human action recognition. In: Inproceedings of the IEEE\/CVF international conference on computer vision, pp 6212\u20136221","DOI":"10.1109\/ICCV.2019.00631"},{"issue":"10","key":"14193_CR58","doi-asserted-by":"publisher","first-page":"2010","DOI":"10.1109\/TPAMI.2015.2505311","volume":"38","author":"K Wang","year":"2015","unstructured":"Wang K, He R, Wang L, Wang W, Tan T (2015) Joint feature selection and subspace learning for cross-modal retrieval. IEEE Trans Pattern Anal Machine Intell 38(10):2010\u20132023","journal-title":"IEEE Trans Pattern Anal Machine Intell"},{"key":"14193_CR59","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Gao Z, Zhang Y, Tang C, Ogunbona P (2017) Scene flow to action map: a new representation for rgb-d based action recognition with convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 595\u2013604","DOI":"10.1109\/CVPR.2017.52"},{"issue":"9","key":"14193_CR60","doi-asserted-by":"publisher","first-page":"2195","DOI":"10.1109\/TMM.2019.2897902","volume":"21","author":"P Wei","year":"2019","unstructured":"Wei P, Sun H, Zheng N (2019) Learning composite latent structures for 3D human action representation and recognition. IEEE Trans Multimedia 21 (9):2195\u20132208","journal-title":"IEEE Trans Multimedia"},{"key":"14193_CR61","doi-asserted-by":"crossref","unstructured":"Xia L, Aggarwal JK (2013) Spatio-temporal depth cuboid similarity feature for activity recognition using depth camera. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2834\u20132841","DOI":"10.1109\/CVPR.2013.365"},{"key":"14193_CR62","doi-asserted-by":"crossref","unstructured":"Xia L, Chen CC, Aggarwal JK (2012) View invariant human action recognition using histograms of 3d joints. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops, pp 20\u201327","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"14193_CR63","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"14193_CR64","doi-asserted-by":"crossref","unstructured":"Yang X, Tian YL (2012) Eigenjoints-based action recognition using naive-bayes-nearest-neighbor. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops, pp 14\u201319","DOI":"10.1109\/CVPRW.2012.6239232"},{"key":"14193_CR65","doi-asserted-by":"crossref","unstructured":"Yang X, Tian Y (2014) Super normal vector for activity recognition using depth sequences. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 804\u2013811","DOI":"10.1109\/CVPR.2014.108"},{"key":"14193_CR66","doi-asserted-by":"crossref","unstructured":"Yang X, Zhang C, Tian Y (2012) Recognizing actions using depth motion maps-based histograms of oriented gradients. In: Proceedings of the 20th ACM international conference on Multimedia, pp 1057\u20131060","DOI":"10.1145\/2393347.2396382"},{"issue":"4","key":"14193_CR67","doi-asserted-by":"publisher","first-page":"716","DOI":"10.3390\/app9040716","volume":"9","author":"C Zhao","year":"2019","unstructured":"Zhao C, Chen M, Zhao J, Wang Q, Shen Y (2019) 3d behavior recognition based on multi-modal deep space-time learning. Appl Sci 9(4):716","journal-title":"Appl Sci"},{"key":"14193_CR68","doi-asserted-by":"crossref","unstructured":"Zolfaghari M, Oliveira GL, Brox Sedaghat N T (2017) Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. In: 2017 Ieee international conference on computer vision, IEEE international conference on computer vision, pp 2923\u20132932","DOI":"10.1109\/ICCV.2017.316"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14193-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-022-14193-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-022-14193-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,4,15]],"date-time":"2023-04-15T09:33:59Z","timestamp":1681551239000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-022-14193-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,11,11]]},"references-count":68,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2023,5]]}},"alternative-id":["14193"],"URL":"https:\/\/doi.org\/10.1007\/s11042-022-14193-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,11,11]]},"assertion":[{"value":"2 October 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 August 2022","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 October 2022","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 November 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":"The authors declare that they have no conflicts of interest to report regarding the present study.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"<!--Emphasis Type='Bold' removed-->Conflict of Interests"}}]}}