{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,14]],"date-time":"2026-02-14T05:23:07Z","timestamp":1771046587984,"version":"3.50.1"},"reference-count":50,"publisher":"Springer Science and Business Media LLC","issue":"17","license":[{"start":{"date-parts":[[2018,2,6]],"date-time":"2018-02-06T00:00:00Z","timestamp":1517875200000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61420106007"],"award-info":[{"award-number":["61420106007"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61671387"],"award-info":[{"award-number":["61671387"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Australian Research Council grants","award":["DE140100180"],"award-info":[{"award-number":["DE140100180"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"published-print":{"date-parts":[[2018,9]]},"DOI":"10.1007\/s11042-018-5642-0","type":"journal-article","created":{"date-parts":[[2018,2,6]],"date-time":"2018-02-06T11:42:26Z","timestamp":1517917346000},"page":"22901-22921","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":36,"title":["3D skeleton based action recognition by video-domain translation-scale invariant mapping and multi-scale dilated CNN"],"prefix":"10.1007","volume":"77","author":[{"given":"Bo","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2051-6955","authenticated-orcid":false,"given":"Mingyi","family":"He","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchao","family":"Dai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xuelian","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yucheng","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2018,2,6]]},"reference":[{"issue":"1","key":"5642_CR1","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":"5642_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: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 7\u201312","DOI":"10.1109\/CVPRW.2012.6239175"},{"key":"5642_CR3","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: Proceedings of the IEEE international conference on image processing, pp 168\u2013172","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"5642_CR4","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110\u20131118"},{"issue":"7","key":"5642_CR5","doi-asserted-by":"publisher","first-page":"3010","DOI":"10.1109\/TIP.2016.2552404","volume":"25","author":"Y Du","year":"2016","unstructured":"Du Y, Fu Y, Wang L (2016) Representation learning of temporal dynamics for skeleton-based action recognition. IEEE Trans Image Proc 25(7):3010\u20133022","journal-title":"IEEE Trans Image Proc"},{"key":"5642_CR6","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. ACM, pp 1737\u20131746","DOI":"10.1145\/2207676.2208303"},{"issue":"4","key":"5642_CR7","doi-asserted-by":"publisher","first-page":"2088","DOI":"10.1109\/TIE.2013.2262760","volume":"61","author":"Y Gao","year":"2013","unstructured":"Gao Y, Wang M, Ji R, Wu X, Dai Q (2013) 3-D object retrieval with hausdorff distance learning. IEEE Trans Ind Electron 61(4):2088\u20132098","journal-title":"IEEE Trans Ind Electron"},{"key":"5642_CR8","doi-asserted-by":"crossref","unstructured":"Girshick R, Donahue J, Darrell T, Malik J (2014) Rich feature hierarchies for accurate object detection and semantic segmentation. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 580\u2013587","DOI":"10.1109\/CVPR.2014.81"},{"key":"5642_CR9","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: AAAI, pp 1351\u20131357"},{"key":"5642_CR10","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"issue":"99","key":"5642_CR11","first-page":"1","volume":"PP","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 PP(99):1\u20131","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"5642_CR12","doi-asserted-by":"crossref","unstructured":"Huang Z, Wan C, Probst T, Van Gool L (2017) Deep learning on lie groups for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6099\u20136108","DOI":"10.1109\/CVPR.2017.137"},{"key":"5642_CR13","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: AAAI, pp 2466\u20132472"},{"key":"5642_CR14","doi-asserted-by":"crossref","unstructured":"Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T (2014) Caffe: convolutional architecture for fast feature embedding. In: Proceedings of the 22nd ACM international conference on multimedia, pp 675\u2013678","DOI":"10.1145\/2647868.2654889"},{"issue":"6","key":"5642_CR15","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":"5642_CR16","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":"5642_CR17","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) Imagenet classification with deep convolutional neural networks. In: Proceedings of the advance neural information processing systems, pp 1097\u20131105"},{"key":"5642_CR18","unstructured":"Li B, Dai Y, Cheng X, Chen H, Lin Y, He M (2017) Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn. In: Proceedings of the IEEE international conference on multimedia and expo workshops, pp 1\u20131"},{"key":"5642_CR19","unstructured":"Liu C, Hu Y, Li Y, Song S, Liu J Pku-mmd: a large scale benchmark for continuous multi-modal human action understanding. arXiv: 1703.07475"},{"key":"5642_CR20","doi-asserted-by":"crossref","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: Proceedings of the european conference on computer vision. Springer, pp 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"issue":"6","key":"5642_CR21","doi-asserted-by":"publisher","first-page":"3479","DOI":"10.1007\/s11042-015-2448-1","volume":"75","author":"G Lu","year":"2016","unstructured":"Lu G, Zhou Y, Li X, Kudo M (2016) Efficient action recognition via local position offset of 3d skeletal body joints. Multimedia Tools and Applications 75 (6):3479\u20133494","journal-title":"Multimedia Tools and Applications"},{"key":"5642_CR22","doi-asserted-by":"crossref","unstructured":"Luo J, Wang W, Qi H (2013) Group sparsity and geometry constrained dictionary learning for action recognition from depth maps. In: Proceedings of the IEEE international conference on computer vision, pp 1809\u20131816","DOI":"10.1109\/ICCV.2013.227"},{"key":"5642_CR23","doi-asserted-by":"publisher","first-page":"14","DOI":"10.1016\/j.cviu.2014.12.005","volume":"136","author":"S Nie","year":"2015","unstructured":"Nie S, Wang Z, Ji Q (2015) A generative restricted boltzmann machine based method for high-dimensional motion data modeling. Comp Vis Image Understanding 136:14\u201322","journal-title":"Comp Vis Image Understanding"},{"key":"5642_CR24","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":"5642_CR25","doi-asserted-by":"crossref","unstructured":"Oquab M, Bottou L, Laptev I, Sivic J (2014) Learning and transferring mid-level image representations using convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1717\u20131724","DOI":"10.1109\/CVPR.2014.222"},{"key":"5642_CR26","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, La Cascia M (2016) 3d skeleton-based human action classification: a survey. Pattern Recogn 53:130\u2013147","journal-title":"Pattern Recogn"},{"key":"5642_CR27","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng T-T, 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"},{"issue":"12","key":"5642_CR28","doi-asserted-by":"publisher","first-page":"2821","DOI":"10.1109\/TPAMI.2012.241","volume":"35","author":"J Shotton","year":"2013","unstructured":"Shotton J, Girshick R, Fitzgibbon A, Sharp T, Cook M, Finocchio M, Moore R, Kohli P, Criminisi A, Kipman A, et al (2013) Efficient human pose estimation from single depth images. IEEE Trans Pattern Anal Mach Intell 35 (12):2821\u20132840","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5642_CR29","unstructured":"Simonyan K, Zisserman A Very deep convolutional networks for large-scale image recognition. arXiv: 1409.1556"},{"issue":"4","key":"5642_CR30","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1109\/LSP.2014.2361901","volume":"22","author":"Y Song","year":"2015","unstructured":"Song Y, Liu S, Tang J (2015) Describing trajectory of surface patch for human action recognition on rgb and depth videos. IEEE Signal Process Lett 22(4):426\u2013429","journal-title":"IEEE Signal Process Lett"},{"key":"5642_CR31","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J, Zeng W, Liu J (2017) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. In: AAAI, pp 4263\u20134270","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"5642_CR32","doi-asserted-by":"crossref","unstructured":"Veeriah V, Zhuang N, Qi G-J (2015) Differential recurrent neural networks for action recognition. In: Proceedings of the IEEE international conference on computer vision, pp 4041\u20134049","DOI":"10.1109\/ICCV.2015.460"},{"key":"5642_CR33","doi-asserted-by":"crossref","unstructured":"Vemulapalli R, Chellapa R (2016) Rolling rotations for recognizing human actions from 3d skeletal data. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4471\u20134479","DOI":"10.1109\/CVPR.2016.484"},{"key":"5642_CR34","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":"5642_CR35","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.cviu.2016.04.005","volume":"152","author":"R Vemulapalli","year":"2016","unstructured":"Vemulapalli R, Arrate F, Chellappa R (2016) R3dg features: relative 3d geometry-based skeletal representations for human action recognition. Comp Vis Image Understanding 152:155\u2013166","journal-title":"Comp Vis Image Understanding"},{"key":"5642_CR36","doi-asserted-by":"crossref","unstructured":"Wang P, Li Z, Hou Y, Li W (2016) Action recognition based on joint trajectory maps using convolutional neural networks. In: Proceedings of the 2016 ACM on multimedia conference, pp 102\u2013106","DOI":"10.1145\/2964284.2967191"},{"issue":"C","key":"5642_CR37","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1016\/j.neucom.2016.06.095","volume":"252","author":"D Wang","year":"2017","unstructured":"Wang D, Wang B, Zhao S, Yao H, Liu H (2017) View-based 3d object retrieval with discriminative views. Neurocomputing 252(C):58\u201366","journal-title":"Neurocomputing"},{"issue":"4","key":"5642_CR38","doi-asserted-by":"publisher","first-page":"510","DOI":"10.1109\/LSP.2016.2611485","volume":"24","author":"X Wang","year":"2017","unstructured":"Wang X, Gao L, Song J, Shen H (2017) Beyond frame-level cnn: saliency-aware 3-d cnn with lstm for video action recognition. IEEE Signal Process Lett 24(4):510\u2013514","journal-title":"IEEE Signal Process Lett"},{"key":"5642_CR39","doi-asserted-by":"crossref","unstructured":"Wu D, Shao L (2014) Leveraging hierarchical parametric networks for skeletal joints based action segmentation and recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 724\u2013731","DOI":"10.1109\/CVPR.2014.98"},{"key":"5642_CR40","doi-asserted-by":"crossref","unstructured":"Yang S, Yuan C, Hu W, Ding X (2014) A hierarchical model based on latent dirichlet allocation for action recognition. In: Proceedings of the IEEE international conference on pattern recognition, pp 2613\u20132618","DOI":"10.1109\/ICPR.2014.451"},{"key":"5642_CR41","unstructured":"Yong D, Yun F, Liang W (2015) Skeleton based action recognition with convolutional neural network. In: Iapr asian conference on pattern recognition, pp 579\u2013583"},{"key":"5642_CR42","unstructured":"Yu F, Koltun V (2016) Multi-scale context aggregation by dilated convolutions. In: Proceedings of the international conference on learning representations, pp 1\u201310"},{"key":"5642_CR43","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: Proceedings of the IEEE international conference on computer vision, pp 2752\u20132759","DOI":"10.1109\/ICCV.2013.342"},{"key":"5642_CR44","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1016\/j.neucom.2014.03.092","volume":"151","author":"S Zhao","year":"2015","unstructured":"Zhao S, Chen L, Yao H, Zhang Y, Sun X (2015) Strategy for dynamic 3d depth data matching towards robust action retrieval. Neurocomputing 151:533\u2013543","journal-title":"Neurocomputing"},{"issue":"C","key":"5642_CR45","doi-asserted-by":"publisher","first-page":"110","DOI":"10.1016\/j.sigpro.2014.09.038","volume":"112","author":"S Zhao","year":"2015","unstructured":"Zhao S, Yao H, Zhang Y, Wang Y, Liu S (2015) View-based 3d object retrieval via multi-modal graph learning. Signal Process 112(C):110\u2013118","journal-title":"Signal Process"},{"issue":"3","key":"5642_CR46","doi-asserted-by":"publisher","first-page":"632","DOI":"10.1109\/TMM.2016.2617741","volume":"19","author":"S Zhao","year":"2017","unstructured":"Zhao S, Yao H, Gao Y, Ji R, Ding G (2017) Continuous probability distribution prediction of image emotions via multitask shared sparse regression. IEEE Trans Multimedia 19(3):632\u2013645","journal-title":"IEEE Trans Multimedia"},{"key":"5642_CR47","doi-asserted-by":"crossref","unstructured":"Zheng Y, Yao H, Sun X, Zhao S (2015) Distinctive action sketch. In: IEEE international conference on image processing, pp 576\u2013580","DOI":"10.1109\/ICIP.2015.7350864"},{"key":"5642_CR48","doi-asserted-by":"crossref","unstructured":"Zhou L, Li W, Zhang Y, Ogunbona P, Nguyen DT, Zhang H (2014) Discriminative key pose extraction using extended lc-ksvd for action recognition. In: Proceedings of the IEEE international conference on digital lmage computing: techniques and applications, pp 1\u20138","DOI":"10.1109\/DICTA.2014.7008101"},{"key":"5642_CR49","doi-asserted-by":"crossref","unstructured":"Zhou L, Li W, Ogunbona P (2016) Learning a pose lexicon for semantic action recognition. In: Proceedings of the IEEE international conference on multimedia and expo, pp 1\u20136","DOI":"10.1109\/ICME.2016.7552882"},{"key":"5642_CR50","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: AAAI, 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\/article\/10.1007\/s11042-018-5642-0\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5642-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-018-5642-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,13]],"date-time":"2022-08-13T23:42:57Z","timestamp":1660434177000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11042-018-5642-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,2,6]]},"references-count":50,"journal-issue":{"issue":"17","published-print":{"date-parts":[[2018,9]]}},"alternative-id":["5642"],"URL":"https:\/\/doi.org\/10.1007\/s11042-018-5642-0","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,2,6]]},"assertion":[{"value":"31 July 2017","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2017","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2018","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 February 2018","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}