{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,9]],"date-time":"2026-10-09T14:57:25Z","timestamp":1791557845606,"version":"4.3.4"},"reference-count":47,"publisher":"Springer Science and Business Media LLC","issue":"19","license":[{"start":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T00:00:00Z","timestamp":1560816000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T00:00:00Z","timestamp":1560816000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2019,10]]},"DOI":"10.1007\/s11042-019-07827-3","type":"journal-article","created":{"date-parts":[[2019,6,18]],"date-time":"2019-06-18T07:02:26Z","timestamp":1560841346000},"page":"27309-27331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["LSTM-based real-time action detection and prediction in human motion streams"],"prefix":"10.1007","volume":"78","author":[{"given":"Fabio","family":"Carrara","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Petr","family":"Elias","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7668-8521","authenticated-orcid":false,"given":"Jan","family":"Sedmidubsky","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pavel","family":"Zezula","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2019,6,18]]},"reference":[{"key":"7827_CR1","unstructured":"Aberman K, Wu R, Lischinski D, Chen B, Cohen-Or D (2019) Learning character-agnostic motion for motion retargeting in 2d. ACM Trans Graph 38(4). arXiv: 1905.01680"},{"key":"7827_CR2","doi-asserted-by":"crossref","unstructured":"Asadi-Aghbolaghi M, Clap\u00e9s A, Bellantonio M, Escalante HJ, Ponce-L\u00f3pez V, Bar\u00f3 X, Guyon I, Kasaei S, Escalera S (2017) A survey on deep learning based approaches for action and gesture recognition in image sequences. In: 2017 12th IEEE international conference on automatic face gesture recognition (FG 2017), pp 476\u2013483","DOI":"10.1109\/FG.2017.150"},{"issue":"2","key":"7827_CR3","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency L (2019) Multimodal machine learning: a survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"7827_CR4","unstructured":"Barbi\u010d J, Safonova A, Pan JY, Faloutsos C, Hodgins JK, Pollard NS (2004) Segmenting motion capture data into distinct behaviors. In: Proceedings of graphics interface 2004. Canadian Human-Computer Communications Society, pp 185\u2013194"},{"issue":"1","key":"7827_CR5","doi-asserted-by":"publisher","first-page":"238","DOI":"10.1016\/j.patcog.2013.06.020","volume":"47","author":"M Barnachon","year":"2014","unstructured":"Barnachon M, Bouakaz S, Boufama B, Guillou E (2014) Ongoing human action recognition with motion capture. Pattern Recogn 47(1):238\u2013247","journal-title":"Pattern Recogn"},{"key":"7827_CR6","doi-asserted-by":"crossref","unstructured":"Boulahia SY, Anquetil E, Multon F, Kulpa R (2018) Cudi3d: curvilinear displacement based approach for online 3d action detection. In: Computer vision and image understanding","DOI":"10.1016\/j.cviu.2018.07.003"},{"key":"7827_CR7","doi-asserted-by":"crossref","unstructured":"Butepage J, Black MJ, Kragic D, Kjellstrom H (2017) Deep representation learning for human motion prediction and classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6158\u20136166","DOI":"10.1109\/CVPR.2017.173"},{"key":"7827_CR8","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei S, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: 2017 IEEE conference on computer vision and pattern recognition (CVPR), pp 1302\u20131310","DOI":"10.1109\/CVPR.2017.143"},{"issue":"3","key":"7827_CR9","doi-asserted-by":"publisher","first-page":"4405","DOI":"10.1007\/s11042-015-3177-1","volume":"76","author":"C Chen","year":"2017","unstructured":"Chen C, Jafari R, Kehtarnavaz N (2017) A survey of depth and inertial sensor fusion for human action recognition. Multimed Tools Appl 76(3):4405\u20134425","journal-title":"Multimed Tools Appl"},{"key":"7827_CR10","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: 2015 IEEE conference on computer vision and pattern recognition, pp 1110\u20131118"},{"key":"7827_CR11","doi-asserted-by":"crossref","unstructured":"Elias P, Sedmidubsky J, Zezula P (2017) A real-time annotation of motion data streams. In: 19th International symposium on multimedia. IEEE Computer Society, pp 154\u2013161","DOI":"10.1109\/ISM.2017.29"},{"key":"7827_CR12","doi-asserted-by":"crossref","unstructured":"Evangelidis G, Singh G, Horaud R (2014) Skeletal quads: human action recognition using joint quadruples. In: 22nd International conference on pattern recognition (ICPR 2014), pp 4513\u20134518","DOI":"10.1109\/ICPR.2014.772"},{"issue":"8","key":"7827_CR13","doi-asserted-by":"publisher","first-page":"2394","DOI":"10.1016\/j.patcog.2015.03.004","volume":"48","author":"M Field","year":"2015","unstructured":"Field M, Stirling D, Pan Z, Ros M, Naghdy F (2015) Recognizing human motions through mixture modeling of inertial data. Pattern Recognit 48(8):2394\u20132406","journal-title":"Pattern Recognit"},{"key":"7827_CR14","doi-asserted-by":"crossref","unstructured":"Fothergill S, Mentis H, Kohli P, Nowozin S (2012) Instructing people for training gestural interactive systems. In: Proceedings of the SIGCHI conference on human factors in computing systems, CHI \u201912. ACM, New York, pp 1737\u20131746","DOI":"10.1145\/2207676.2208303"},{"issue":"8","key":"7827_CR15","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735\u20131780","journal-title":"Neural Comput"},{"key":"7827_CR16","unstructured":"Hussein ME, Torki M, Gowayyed MA, El-Saban M (2013) Human action recognition using a temporal hierarchy of covariance descriptors on 3D joint locations. In: Joint conference on artificial intelligence (IJCAI 2013), pp 2466\u20132472"},{"key":"7827_CR17","doi-asserted-by":"crossref","unstructured":"Jain A, Zamir AR, Savarese S, Saxena A (2016) Structural-rnn: deep learning on spatio-temporal graphs. In: IEEE conference on computer vision and pattern recognition (CVPR), pp 5308\u20135317","DOI":"10.1109\/CVPR.2016.573"},{"issue":"8","key":"7827_CR18","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1109\/TMM.2014.2360793","volume":"16","author":"H Kadu","year":"2014","unstructured":"Kadu H, Kuo CCJ (2014) Automatic human mocap data classification. IEEE Trans Multimedia 16(8):2191\u20132202","journal-title":"IEEE Trans Multimedia"},{"key":"7827_CR19","unstructured":"Kingma DP, Ba J (2014) Adam: a method for stochastic optimization. arXiv: 1412:6980"},{"key":"7827_CR20","doi-asserted-by":"crossref","unstructured":"Kratz L, Smith M, Lee F (2007) Wiizards: 3d gesture recognition for game play input. In: Proceedings of the 2007 conference on future play. Future play \u201907, pp 209\u2013212","DOI":"10.1145\/1328202.1328241"},{"issue":"4","key":"7827_CR21","doi-asserted-by":"publisher","first-page":"797","DOI":"10.1109\/TMM.2016.2635030","volume":"19","author":"B Kr\u00fcger","year":"2017","unstructured":"Kr\u00fcger B, V\u00f6gele A, Willig T, Yao A, Klein R, Weber A (2017) Efficient unsupervised temporal segmentation of motion data. IEEE Trans Multimedia 19(4):797\u2013812","journal-title":"IEEE Trans Multimedia"},{"issue":"5","key":"7827_CR22","doi-asserted-by":"publisher","first-page":"701","DOI":"10.1016\/j.jesp.2010.03.015","volume":"46","author":"D Lakens","year":"2010","unstructured":"Lakens D (2010) Movement synchrony and perceived entitativity. J Exp Soc Psychol 46(5):701\u2013708","journal-title":"J Exp Soc Psychol"},{"key":"7827_CR23","doi-asserted-by":"crossref","unstructured":"Laraba S, Brahimi M, Tilmanne J, Dutoit T (2017) 3d skeleton-based action recognition by representing motion capture sequences as 2d-rgb images. Comput Anim Virtual Worlds 28(3\u20134)","DOI":"10.1002\/cav.1782"},{"key":"7827_CR24","doi-asserted-by":"crossref","unstructured":"Li Y, Lan C, Xing J, Zeng W, Yuan C, Liu J (2016) Online human action detection using joint classification-regression recurrent neural networks. In: Leibe B, Matas J, Sebe N, Welling M (eds) Computer vision\u2014ECCV 2016. Springer International Publishing, Cham, pp 203\u2013220","DOI":"10.1007\/978-3-319-46478-7_13"},{"issue":"3","key":"7827_CR25","doi-asserted-by":"publisher","first-page":"294","DOI":"10.1007\/s11766-017-3466-8","volume":"32","author":"K Li","year":"2017","unstructured":"Li K, He FZ, Yu HP, Chen X (2017) A correlative classifiers approach based on particle filter and sample set for tracking occluded target. Appl Math\u2013A Journal of Chinese Universities 32(3):294\u2013312","journal-title":"Appl Math\u2013A Journal of Chinese Universities"},{"issue":"1","key":"7827_CR26","doi-asserted-by":"publisher","first-page":"223","DOI":"10.1007\/s11390-017-1764-5","volume":"33","author":"K Li","year":"2018","unstructured":"Li K, He FZ, Yu HP (2018) Robust visual tracking based on convolutional features with illumination and occlusion handing. J Comput Sci Technol 33(1):223\u2013236","journal-title":"J Comput Sci Technol"},{"issue":"1s","key":"7827_CR27","doi-asserted-by":"publisher","first-page":"20:1","DOI":"10.1145\/3131344","volume":"14","author":"S Li","year":"2018","unstructured":"Li S, Li K, Fu Y (2018) Early recognition of 3d human actions. ACM Trans Multimedia Comput Commun Appl 14(1s):20:1\u201320:21","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"issue":"4","key":"7827_CR28","doi-asserted-by":"publisher","first-page":"1586","DOI":"10.1109\/TIP.2017.2785279","volume":"27","author":"J Liu","year":"2018","unstructured":"Liu J, Wang G, Duan L, Hu P, Kot AC (2018) Skeleton based human action recognition with global context-aware attention LSTM networks. IEEE Trans Image Process 27(4):1586\u20131599","journal-title":"IEEE Trans Image Process"},{"key":"7827_CR29","doi-asserted-by":"crossref","unstructured":"Ma S, Sigal L, Sclaroff S (2016) Learning activity progression in lstms for activity detection and early detection. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR), pp 1942\u20131950","DOI":"10.1109\/CVPR.2016.214"},{"key":"7827_CR30","unstructured":"M\u00fcller M, R\u00f6der T, Clausen M, Eberhardt B, Kr\u00fcger B, Weber A (2007) Documentation Mocap Database HDM05. Tech. Rep. CG-2007-2, Universit\u00e4t Bonn"},{"key":"7827_CR31","doi-asserted-by":"crossref","unstructured":"M\u00fcller M, Baak A, Seidel HP (2009) Efficient and robust annotation of motion capture data. In: ACM SIGGRAPH\/Eurographics symposium on computer animation (SCA 2009). ACM Press, pp 17\u201326","DOI":"10.1145\/1599470.1599473"},{"key":"7827_CR32","doi-asserted-by":"publisher","first-page":"80","DOI":"10.1016\/j.patcog.2017.10.033","volume":"76","author":"JC Nunez","year":"2018","unstructured":"Nunez JC, Cabido R, Pantrigo JJ, Montemayor AS, Velez 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"},{"issue":"3","key":"7827_CR33","doi-asserted-by":"crossref","first-page":"625","DOI":"10.3758\/s13428-013-0398-y","volume":"46","author":"R Poppe","year":"2014","unstructured":"Poppe R, Van Der Zee S, Heylen DKJ, Taylor PJ (2014) Amab: automated measurement and analysis of body motion. Behav Res Methods 46(3):625\u2013633","journal-title":"Behav Res Methods"},{"key":"7827_CR34","doi-asserted-by":"crossref","unstructured":"Raptis M, Kirovski D, Hoppe H (2011) Real-time classification of dance gestures from skeleton animation. In: ACM SIGGRAPH Eurographics symposium on computer animation (SCA 2011), SCA 2011. ACM, pp 147\u2013156","DOI":"10.1145\/2019406.2019426"},{"issue":"10","key":"7827_CR35","doi-asserted-by":"publisher","first-page":"12,073","DOI":"10.1007\/s11042-017-4859-7","volume":"77","author":"J Sedmidubsky","year":"2018","unstructured":"Sedmidubsky J, Elias P, Zezula P (2018) Effective and efficient similarity searching in motion capture data. Multimed Tools Appl 77(10):12,073\u201312,094","journal-title":"Multimed Tools Appl"},{"key":"7827_CR36","doi-asserted-by":"crossref","unstructured":"Singh D, Merdivan E, Psychoula I, Kropf J, Hanke S, Geist M, Holzinger A (2017) Human activity recognition using recurrent neural networks. In: Holzinger A, Kieseberg P, Tjoa AM, Weippl E (eds) Machine learning and knowledge extraction. Springer International Publishing, Cham, pp 267\u2013274","DOI":"10.1007\/978-3-319-66808-6_18"},{"issue":"7","key":"7827_CR37","doi-asserted-by":"publisher","first-page":"3459","DOI":"10.1109\/TIP.2018.2818328","volume":"27","author":"S Song","year":"2018","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2018) Spatio-temporal attention-based lstm networks for 3d action recognition and detection. IEEE Trans Image Process 27(7):3459\u20133471","journal-title":"IEEE Trans Image Process"},{"key":"7827_CR38","unstructured":"Vieira A, Lewiner T, Schwartz W, Campos M (2012) Distance matrices as invariant features for classifying mocap data. In: 21st International conference on pattern recognition (ICPR 2012), pp 2934\u20132937"},{"key":"7827_CR39","doi-asserted-by":"crossref","unstructured":"Wang Y, Neff M (2015) Deep signatures for indexing and retrieval in large motion databases. In: 8th ACM SIGGRAPH conference on motion in games. ACM, pp 37\u201345","DOI":"10.1145\/2822013.2822024"},{"key":"7827_CR40","doi-asserted-by":"crossref","unstructured":"Wang C, Wang Y, Yuille AL (2013) An approach to pose-based action recognition. In: Proceedings of the 2013 IEEE conference on computer vision and pattern recognition, CVPR \u201913. IEEE Computer Society, pp 915\u2013922","DOI":"10.1109\/CVPR.2013.123"},{"key":"7827_CR41","doi-asserted-by":"crossref","unstructured":"Wu D, Shao L (2014) Leveraging hierarchical parametric networks for skeletal joints based action segmentation and recognition. In: 2014 IEEE conference on computer vision and pattern recognition, pp 724\u2013731","DOI":"10.1109\/CVPR.2014.98"},{"key":"7827_CR42","doi-asserted-by":"crossref","unstructured":"Xia L, Chen CC, Aggarwal JK (2012) View invariant human action recognition using histograms of 3D joints. In: CVPR workshops, pp 20\u201327","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"7827_CR43","doi-asserted-by":"publisher","first-page":"324","DOI":"10.1016\/j.pmcj.2017.07.001","volume":"40","author":"Y Xu","year":"2017","unstructured":"Xu Y, Shen Z, Zhang X, Gao Y, Deng S, Wang Y, Fan Y, Chang EC (2017) Learning multi-level features for sensor-based human action recognition. Pervasive Mob Comput 40:324\u2013338","journal-title":"Pervasive Mob Comput"},{"key":"7827_CR44","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.jvlc.2017.09.001","volume":"43","author":"X Yu","year":"2017","unstructured":"Yu X, Liu W, Xing W (2017) Behavioral segmentation for human motion capture data based on graph cut method. J Vis Lang Comput 43:50\u201359","journal-title":"J Vis Lang Comput"},{"key":"7827_CR45","doi-asserted-by":"crossref","unstructured":"Zanfir M, Leordeanu M, Sminchisescu C (2013) The moving pose: an efficient 3d kinematics descriptor for low-latency action recognition and detection. In: International conference on computer vision (ICCV 2013), pp 2752\u20132759","DOI":"10.1109\/ICCV.2013.342"},{"issue":"1s","key":"7827_CR46","doi-asserted-by":"publisher","first-page":"22:1","DOI":"10.1145\/2648583","volume":"11","author":"X Zhao","year":"2014","unstructured":"Zhao X, Li X, Pang C, Sheng QZ, Wang S, Ye M (2014) Structured streaming skeleton\u2014a new feature for online human gesture recognition. ACM Trans Multimedia Comput Commun Appl 11(1s):22:1\u201322:18","journal-title":"ACM Trans Multimedia Comput Commun Appl"},{"key":"7827_CR47","doi-asserted-by":"crossref","unstructured":"Zhu W, Lan C, Xing J, Zeng W, Li Y, Shen L, Xie X (2016) Co-occurrence feature learning for skeleton based action recognition using regularized deep LSTM networks. In: 30th AAAI conference on artificial intelligence, AAAI 2016. AAAI Press, pp 3697\u20133703","DOI":"10.1609\/aaai.v30i1.10451"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07827-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-07827-3\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-07827-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,21]],"date-time":"2022-09-21T00:25:57Z","timestamp":1663719957000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-07827-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,6,18]]},"references-count":47,"journal-issue":{"issue":"19","published-print":{"date-parts":[[2019,10]]}},"alternative-id":["7827"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-07827-3","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,6,18]]},"assertion":[{"value":"4 September 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"15 May 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 May 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 June 2019","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}