{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,29]],"date-time":"2025-10-29T03:48:15Z","timestamp":1761709695910},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"17-18","license":[{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,7]],"date-time":"2020-01-07T00:00:00Z","timestamp":1578355200000},"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":[[2020,5]]},"DOI":"10.1007\/s11042-019-08588-9","type":"journal-article","created":{"date-parts":[[2020,2,3]],"date-time":"2020-02-03T15:10:32Z","timestamp":1580742632000},"page":"11723-11746","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["A four-stream ConvNet based on spatial and depth flow for human action classification using RGB-D data"],"prefix":"10.1007","volume":"79","author":[{"given":"D.","family":"Srihari","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"P. V. V.","family":"Kishore","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"E. Kiran","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"D. Anil","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. Teja Kiran","family":"Kumar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"M. V. D.","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ch. Raghava","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,1,7]]},"reference":[{"key":"8588_CR1","doi-asserted-by":"publisher","first-page":"70","DOI":"10.1016\/j.patrec.2014.04.011","volume":"48","author":"J Aggarwal","year":"2014","unstructured":"Aggarwal J, Xia L (2014) Human activity recognition from 3d data: a review. Pattern Recogn Lett 48:70\u201380","journal-title":"Pattern Recogn Lett"},{"key":"8588_CR2","doi-asserted-by":"crossref","unstructured":"Bloom V, Makris D, Argyriou V (2012) G3d: a gaming action dataset and real time action recognition evaluation framework. In: 2012 IEEE computer society conference on computer vision and pattern recognition workshops. IEEE","DOI":"10.1109\/CVPRW.2012.6239175"},{"key":"8588_CR3","doi-asserted-by":"crossref","unstructured":"Boulahia SY, Anquetil E, Kulpa R, Multon F (2016) HIF3D: Handwriting-inspired features for 3d skeleton-based action recognition. In: 2016 23rd International Conference on Pattern Recognition (ICPR), IEEE","DOI":"10.1109\/ICPR.2016.7899764"},{"issue":"15","key":"8588_CR4","doi-asserted-by":"publisher","first-page":"1861","DOI":"10.1016\/j.patrec.2013.01.024","volume":"34","author":"G Burghouts","year":"2013","unstructured":"Burghouts G, Schutte K (2013) Spatio-temporal layout of human actions for improved bag-of-words action detection. Pattern Recogn Lett 34(15):1861\u20131869","journal-title":"Pattern Recogn Lett"},{"key":"8588_CR5","doi-asserted-by":"crossref","unstructured":"Chatfield K, Simonyan K, Vedaldi A, Zisserman A (2014) Return of the devil in the details: Delving deep into convolutional nets. In: Proceedings of the British machine vision conference 2014. British Machine Vision Association","DOI":"10.5244\/C.28.6"},{"key":"8588_CR6","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.patrec.2013.09.004","volume":"50","author":"L Chen","year":"2014","unstructured":"Chen L, Wei H, Ferryman J (2014) Readingact RGB-d action dataset and human action recognition from local features. Pattern Recogn Lett 50:159\u2013169","journal-title":"Pattern Recogn Lett"},{"key":"8588_CR7","doi-asserted-by":"crossref","unstructured":"Cheron G, Laptev I, Schmid C (2015) P-CNN: Pose-based CNN features for action recognition. In: 2015 IEEE International Conference on Computer Vision (ICCV). IEEE","DOI":"10.1109\/ICCV.2015.368"},{"key":"8588_CR8","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: 2016 IEEE conference on computer vision and pattern recognition (CVPR) . IEEE","DOI":"10.1109\/CVPR.2016.213"},{"key":"8588_CR9","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. IEEE","DOI":"10.1109\/CVPR.2017.787"},{"key":"8588_CR10","doi-asserted-by":"crossref","unstructured":"Gammulle H, Denman S, Sridharan S, Fookes C (2017) Two stream lstm: a deep fusion framework for human action recognition. In: 2017 IEEE winter conference on applications of computer vision (WACV). IEEE, pp 177\u2013186","DOI":"10.1109\/WACV.2017.27"},{"issue":"4","key":"8588_CR11","doi-asserted-by":"publisher","first-page":"1612","DOI":"10.1109\/JSEN.2017.2784425","volume":"18","author":"B Ghojogh","year":"2018","unstructured":"Ghojogh B, Mohammadzade H, Mokari M (2018) Fisherposes for human action recognition using kinect sensor data. IEEE Sensors J 18(4):1612\u20131627","journal-title":"IEEE Sensors J"},{"key":"8588_CR12","doi-asserted-by":"crossref","unstructured":"Grest D, Kr\u00fcijger V (2007) Gradient-enhanced p filter for visionbased motion capture. In: Human motion \u2013 understanding, modeling, capture and animation. Springer, Berlin, pp 28\u201341","DOI":"10.1007\/978-3-540-75703-0_3"},{"key":"8588_CR13","doi-asserted-by":"crossref","unstructured":"Herbst E, Ren X, Fox D (2013) Rgb-d flow: Dense 3-d motion estimation using color and depth. In: 2013 IEEE international conference on robotics and automation, pp 2276\u20132282","DOI":"10.1109\/ICRA.2013.6630885"},{"issue":"12","key":"8588_CR14","doi-asserted-by":"publisher","first-page":"2512","DOI":"10.3724\/SP.J.1016.2013.02512","volume":"36","author":"Q Hu","year":"2014","unstructured":"Hu Q, Qin L, Huang Q-M (2014) A survey on visual human action recognition. Chinese J Comput 36(12):2512\u20132524","journal-title":"Chinese J Comput"},{"key":"8588_CR15","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1016\/j.patcog.2016.01.012","volume":"59","author":"EP Ijjina","year":"2016","unstructured":"Ijjina EP, Chalavadi KM (2016) Human action recognition using genetic algorithms and convolutional neural networks. Pattern Recogn 59:199\u2013212","journal-title":"Pattern Recogn"},{"key":"8588_CR16","doi-asserted-by":"crossref","unstructured":"Kakadiaris I, Barr\u00f3n C. (2006) Model-based human motion capture. In: Hand of mathematical models in computer vision. Springer, pp 325\u2013340","DOI":"10.1007\/0-387-28831-7_20"},{"key":"8588_CR17","doi-asserted-by":"crossref","unstructured":"Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Fei- Fei L (2014) Large-scale video classification with convolutional neural networks. In: 2014 IEEE conference on computer vision and pattern recognition. IEEE","DOI":"10.1109\/CVPR.2014.223"},{"key":"8588_CR18","unstructured":"Kishore P, Kumar D, Sastry A, Kumar E (2018) Motionlets matching with adaptive kernels for 3d indian sign language recognition. IEEE Sensors J:1\u20131"},{"key":"8588_CR19","doi-asserted-by":"crossref","unstructured":"Koller O, Zargaran S, Ney H, Bowden R (2016) Deep sign: Hybrid CNN-HMM for continuous sign language recognition. In: Procedings of the British machine vision conference 2016. British Machine Vision Association","DOI":"10.5244\/C.30.136"},{"key":"8588_CR20","doi-asserted-by":"crossref","unstructured":"Lavinia Y, Vo HH, Verma A (2016) Fusion based deep CNN for improved large-scale image action recognition. In: 2016 IEEE international symposium on multimedia (ISM). IEEE","DOI":"10.1109\/ISM.2016.0131"},{"key":"8588_CR21","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1016\/j.patrec.2016.07.021","volume":"87","author":"M Li","year":"2017","unstructured":"Li M, Leung H (2017) Graph-based approach for 3d human skeletal action recognition. Pattern Recogn Lett 87:195\u2013202","journal-title":"Pattern Recogn Lett"},{"key":"8588_CR22","doi-asserted-by":"crossref","unstructured":"Li W, Li X, Qiu J (2015) Human action recognition based on dense of spatio-temporal interest points and HOG-3d descriptor. In: Proceedings of the 7th international conference on internet multimedia computing and service - ICIMCS \u201915. ACM Press","DOI":"10.1145\/2808492.2808536"},{"key":"8588_CR23","doi-asserted-by":"crossref","unstructured":"Liu L, Hu F, Zhao J (2016) Action recognition based on features fusion and 3d convolutional neural networks. In: 2016 9th international symposium on computational intelligence and design (ISCID). IEEE","DOI":"10.1109\/ISCID.2016.1048"},{"key":"8588_CR24","unstructured":"Liu M, Liu H, Chen C (2017) 3d action recognition using multi-scale energy-based global ternary image. IEEE Trans Circuits Sys Vid Technol:1\u20131"},{"key":"8588_CR25","doi-asserted-by":"publisher","first-page":"506","DOI":"10.1016\/j.patcog.2017.11.026","volume":"76","author":"M Ma","year":"2018","unstructured":"Ma M, Marturi N, Li Y, Leonardis A, Stolkin R (2018) Region-sequence based six-stream CNN features for general and fine-grained human action recognition in videos. Pattern Recogn 76:506\u2013521","journal-title":"Pattern Recogn"},{"issue":"3","key":"8588_CR26","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1006\/cviu.2000.0897","volume":"81","author":"TB Moeslund","year":"2001","unstructured":"Moeslund TB, Granum E (2001) A survey of computer vision-based human motion capture. Comput Vis Image Underst 81(3):231\u2013268","journal-title":"Comput Vis Image Underst"},{"key":"8588_CR27","unstructured":"Ng J. Y. -H., Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: Deep networks for video classification. In: 2015 IEEE conference on computer vision and pattern recognition (cvpr). IEEE"},{"key":"8588_CR28","unstructured":"Pichao W, Wanqing L, Jun W, Philip O, Xinwang L (2017) Cooperative training of deep aggregation networks for rgb-d action recognition. Computer Vision and Pattern Recognition"},{"key":"8588_CR29","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1016\/j.patcog.2015.11.019","volume":"53","author":"LL Presti","year":"2016","unstructured":"Presti LL, Cascia ML (2016) 3D skeleton-based human action classification: a survey. Pattern Recogn 53:130\u2013147","journal-title":"Pattern Recogn"},{"key":"8588_CR30","unstructured":"Qiu Z, Li Q, Yao T, Mei T, Rui Y (2015) Msr asia msm at thumos challenge 2015. In: CVPR workshop, vol 8"},{"key":"8588_CR31","doi-asserted-by":"crossref","unstructured":"Rahmani H, Mahmood A, Huynh DQ, Mian A (2014) HOPC: Histogram Of oriented principal components of 3d pointclouds for action recognition. In: Computer Vision \u2013 ECCV 2014. Springer International Publishing, pp 742\u2013757","DOI":"10.1007\/978-3-319-10605-2_48"},{"key":"8588_CR32","unstructured":"Shahroudy A, Ng T. -T., Gong Y, Wang G (2017) Deep multimodal feature analysis for action recognition in RGB+d videos. In: IEEE Trans Pattern Anal Mach Intell: 1\u20131"},{"key":"8588_CR33","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. arXiv:\/1406.2199"},{"key":"8588_CR34","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv:1409.1556"},{"key":"8588_CR35","doi-asserted-by":"crossref","unstructured":"Singh B, Marks TK, Jones M, Tuzel O, Shao M (2016) A multi-stream bi-directional recurrent neural network for fine-grained action detection. Proceedings of the IEEE conference on computer vision and pattern recognition, 1961?1970","DOI":"10.1109\/CVPR.2016.216"},{"key":"8588_CR36","doi-asserted-by":"crossref","unstructured":"Song Y, Gu Y, Wang P, Liu Y, Li A (2013) A kinect based gesture recognition algorithm using GMM and HMM. In: 2013 6th international conference on biomedical engineering and informatics. IEEE","DOI":"10.1109\/BMEI.2013.6747040"},{"key":"8588_CR37","doi-asserted-by":"crossref","unstructured":"Sun Y, Bray M, Thayananthan A, Yuan B, Torr P (2006) Regressionbased human motion capture from voxel data. In: Procedings of the British Machine Vision Conference 2006. British Machine Vision Association","DOI":"10.5244\/C.20.29"},{"issue":"10","key":"8588_CR38","doi-asserted-by":"publisher","first-page":"3611","DOI":"10.1016\/j.patcog.2012.04.002","volume":"45","author":"C-C Tseng","year":"2012","unstructured":"Tseng C-C, Chen J-C, Fang C-H, Lien J-JJ (2012) Human action recognition based on graph-embedded spatio-temporal subspace. Pattern Recogn 45(10):3611\u20133624","journal-title":"Pattern Recogn"},{"key":"8588_CR39","doi-asserted-by":"crossref","unstructured":"Tu Z, Cao J, Li Y, Li B (2016) MSR-CNN: Applying motion salient region based descriptors for action recognition. In: 2016 23rd international conference on pattern recognition (ICPR). IEEE","DOI":"10.1109\/ICPR.2016.7900180"},{"key":"8588_CR40","unstructured":"Varol G, Laptev I, Schmid C (2017) Long-term temporal convolutions for action recognition. IEEE Trans Pattern Anal Mach Intell:1\u20131"},{"key":"8588_CR41","doi-asserted-by":"publisher","first-page":"241","DOI":"10.1016\/j.gaitpost.2017.06.394","volume":"57","author":"EK Vonstad","year":"2017","unstructured":"Vonstad EK, Lervik E, Holt T, Ljosland M, Sandstrak G, Vereijken B, Nilsen JH (2017) P30: an open database of synchronized, high precision 3d motion capture data for human gait analysis research and development. Gait & Posture 57:241\u2013242","journal-title":"Gait & Posture"},{"key":"8588_CR42","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. IEEE"},{"key":"8588_CR43","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2017.04.004","volume":"92","author":"L Wang","year":"2017","unstructured":"Wang L, Ge L, Li R, Fang Y (2017) Three-stream CNNs for action recognition. Pattern Recogn Lett 92:33\u201340","journal-title":"Pattern Recogn Lett"},{"issue":"3","key":"8588_CR44","doi-asserted-by":"publisher","first-page":"634","DOI":"10.1109\/TMM.2017.2749159","volume":"20","author":"X Wang","year":"2018","unstructured":"Wang X, Gao L, Wang P, Sun X, Liu X (2018) Two-stream 3-d ConvNet fusion for action recognition in videos with arbitrary size and length. IEEE Trans Multimedia 20(3):634\u2013644","journal-title":"IEEE Trans Multimedia"},{"key":"8588_CR45","doi-asserted-by":"crossref","unstructured":"Wang Y, Song J, Wang L, Gool L, Hilliges O (2016) Two-stream SRCNNs for action recognition in videos, British Machine Vision Association","DOI":"10.5244\/C.30.108"},{"key":"8588_CR46","doi-asserted-by":"crossref","unstructured":"Xia L, Chen C-C, 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. IEEE","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"8588_CR47","unstructured":"Xiao T, Xia T, Yang Y, Huang C, Wang X (2015) Learning from massive noisy labeled data for image classification. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2691\u20132699"},{"key":"8588_CR48","doi-asserted-by":"crossref","unstructured":"Yu G, Li T (2017) Recognition of human continuous action with 3d CNN. In: Lecture Notes in Computer Science. Springer International Publishing, pp 314\u2013322","DOI":"10.1007\/978-3-319-68345-4_28"},{"key":"8588_CR49","doi-asserted-by":"publisher","first-page":"86","DOI":"10.1016\/j.patcog.2016.05.019","volume":"60","author":"J Zhang","year":"2016","unstructured":"Zhang J, Li W, Ogunbona PO, Wang P, Tang C (2016) RGB-D-based action recognition datasets: a survey. Pattern Recogn 60:86\u2013105","journal-title":"Pattern Recogn"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08588-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11042-019-08588-9\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-019-08588-9.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,1,6]],"date-time":"2021-01-06T01:07:44Z","timestamp":1609895264000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-019-08588-9"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,1,7]]},"references-count":49,"journal-issue":{"issue":"17-18","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["8588"],"URL":"https:\/\/doi.org\/10.1007\/s11042-019-08588-9","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,1,7]]},"assertion":[{"value":"22 May 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 October 2019","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 December 2019","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 January 2020","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}