{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:55:06Z","timestamp":1761897306001,"version":"3.37.3"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T00:00:00Z","timestamp":1596067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T00:00:00Z","timestamp":1596067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/100014717","name":"National Outstanding Youth Science Fund Project of National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61906173"],"award-info":[{"award-number":["61906173"]}],"id":[{"id":"10.13039\/100014717","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Process Lett"],"published-print":{"date-parts":[[2020,10]]},"DOI":"10.1007\/s11063-020-10320-w","type":"journal-article","created":{"date-parts":[[2020,7,30]],"date-time":"2020-07-30T11:26:38Z","timestamp":1596108398000},"page":"1501-1515","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["A Review of Dynamic Maps for 3D Human Motion Recognition Using ConvNets and Its Improvement"],"prefix":"10.1007","volume":"52","author":[{"given":"Zhimin","family":"Gao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1430-0237","authenticated-orcid":false,"given":"Pichao","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Huogen","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Mingliang","family":"Xu","sequence":"additional","affiliation":[]},{"given":"Wanqing","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2020,7,30]]},"reference":[{"key":"10320_CR1","doi-asserted-by":"crossref","unstructured":"Bilen H, Fernando B, Gavves E, Vedaldi A, Gould S (2016) Dynamic image networks for action recognition. In: CVPR","DOI":"10.1109\/CVPR.2016.331"},{"key":"10320_CR2","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: ICIP, pp 168\u2013172","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"10320_CR3","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne\u00a0Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In: CVPR, pp 2625\u20132634","DOI":"10.21236\/ADA623249"},{"key":"10320_CR4","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: CVPR, pp 1110\u20131118"},{"key":"10320_CR5","unstructured":"Duan J, Wan J, Zhou S, Guo X, Li S (2017) A unified framework for multi-modal isolated gesture recognition. In: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM),(under review, round 2)"},{"key":"10320_CR6","doi-asserted-by":"crossref","unstructured":"Fothergill S, Mentis HM, Nowozin S, Kohli P (2012) Instructing people for training gestural interactive systems. In: ACM HCI","DOI":"10.1145\/2207676.2208303"},{"key":"10320_CR7","unstructured":"Hou Y, Li Z, Wang P, Li W (2016) Skeleton optical spectra based action recognition using convolutional neural networks. In: TCSVT, pp 1\u20135"},{"key":"10320_CR8","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T, Keuper M, Dosovitskiy A, Brox T (2017) Flownet 2.0: Evolution of optical flow estimation with deep networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2462\u20132470","DOI":"10.1109\/CVPR.2017.179"},{"key":"10320_CR9","doi-asserted-by":"crossref","unstructured":"Jayaraman D, Grauman K (2016) Slow and steady feature analysis: higher order temporal coherence in video. In: CVPR","DOI":"10.1109\/CVPR.2016.418"},{"issue":"1","key":"10320_CR10","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 (2013) 3D convolutional neural networks for human action recognition. TPAMI 35(1):221\u2013231","journal-title":"TPAMI"},{"key":"10320_CR11","doi-asserted-by":"publisher","first-page":"64","DOI":"10.1016\/j.knosys.2017.01.035","volume":"122","author":"X Ji","year":"2017","unstructured":"Ji X, Cheng J, Tao D, Wu X, Feng W (2017) The spatial laplacian and temporal energy pyramid representation for human action recognition using depth sequences. Knowl-Based Syst 122:64\u201374","journal-title":"Knowl-Based Syst"},{"issue":"5","key":"10320_CR12","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":"10320_CR13","doi-asserted-by":"crossref","unstructured":"Li W, Zhang Z, Liu Z (2010) Action recognition based on a bag of 3D points. In: CVPRW, pp 9\u201314","DOI":"10.1109\/CVPRW.2010.5543273"},{"key":"10320_CR14","doi-asserted-by":"crossref","unstructured":"Liu AA, Xu N, Nie WZ, Su YT, Wong Y, Kankanhalli M (2016a) Benchmarking a multimodal and multiview and interactive dataset for human action recognition. TCYB","DOI":"10.1109\/TCYB.2016.2582918"},{"key":"10320_CR15","doi-asserted-by":"crossref","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2016b) Spatio-temporal LSTM with trust gates for 3D human action recognition. In: ECCV, pp 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"issue":"8","key":"10320_CR16","doi-asserted-by":"publisher","first-page":"1824","DOI":"10.1109\/TCSVT.2017.2655521","volume":"28","author":"M Liu","year":"2017","unstructured":"Liu M, Liu H, Chen C (2017) 3d action recognition using multiscale energy-based global ternary image. IEEE Trans Circuits Syst Video Technol 28(8):1824\u20131838","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"10320_CR17","doi-asserted-by":"crossref","unstructured":"Lu C, Jia J, Tang CK (2014) Range-sample depth feature for action recognition. In: CVPR, pp 772\u2013779","DOI":"10.1109\/CVPR.2014.104"},{"key":"10320_CR18","doi-asserted-by":"crossref","unstructured":"Oreifej O, Liu Z (2013) HON4D: Histogram of oriented 4D normals for activity recognition from depth sequences. In: CVPR, pp 716\u2013723","DOI":"10.1109\/CVPR.2013.98"},{"key":"10320_CR19","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: CVPR","DOI":"10.1109\/CVPR.2016.115"},{"key":"10320_CR20","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. arXiv preprint arXiv:1511.04119"},{"key":"10320_CR21","doi-asserted-by":"crossref","unstructured":"Shotton J, Fitzgibbon A, Cook M, Sharp T, Finocchio M, Moore R, Kipman A, Blake A (2011) Real-time human pose recognition in parts from single depth images. In: CVPR, pp 1297\u20131304","DOI":"10.1109\/CVPR.2011.5995316"},{"key":"10320_CR22","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: NIPS, pp 568\u2013576"},{"key":"10320_CR23","unstructured":"Srivastava N, Mansimov E, Salakhudinov R (2015) Unsupervised learning of video representations using lstms. In: ICML, pp 843\u2013852"},{"key":"10320_CR24","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: ICCV, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"10320_CR25","doi-asserted-by":"crossref","unstructured":"Veeriah V, Zhuang N, Qi GJ (2015) Differential recurrent neural networks for action recognition. In: ICCV, pp 4041\u20134049","DOI":"10.1109\/ICCV.2015.460"},{"key":"10320_CR26","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: CVPR, pp 588\u2013595","DOI":"10.1109\/CVPR.2014.82"},{"issue":"8","key":"10320_CR27","doi-asserted-by":"publisher","first-page":"1626","DOI":"10.1109\/TPAMI.2015.2513479","volume":"38","author":"J Wan","year":"2016","unstructured":"Wan J, Guo G, Li SZ (2016a) Explore efficient local features from RGB-D data for one-shot learning gesture recognition. TPAMI 38(8):1626\u20131639","journal-title":"TPAMI"},{"key":"10320_CR28","doi-asserted-by":"crossref","unstructured":"Wan J, Li SZ, Zhao Y, Zhou S, Guyon I, Escalera S (2016b) Chalearn looking at people RGB-D isolated and continuous datasets for gesture recognition. In: CVPRW, pp 1\u20139","DOI":"10.1109\/CVPRW.2016.100"},{"key":"10320_CR29","doi-asserted-by":"crossref","unstructured":"Wang H, Wang P, Song Z, Li W (2017a) Large-scale multimodal gesture recognition using heterogeneous networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3129\u20133137","DOI":"10.1109\/ICCVW.2017.370"},{"key":"10320_CR30","doi-asserted-by":"crossref","unstructured":"Wang H, Wang P, Song Z, Li W (2017b) Large-scale multimodal gesture segmentation and recognition based on convolutional neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 3138\u20133146","DOI":"10.1109\/ICCVW.2017.371"},{"key":"10320_CR31","doi-asserted-by":"crossref","unstructured":"Wang J, Liu Z, Wu Y, Yuan J (2012) Mining actionlet ensemble for action recognition with depth cameras. In: CVPR, pp 1290\u20131297","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"10320_CR32","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Ogunbona P, Gao Z, Zhang H (2014) Mining mid-level features for action recognition based on effective skeleton representation. In: DICTA, pp 1\u20138","DOI":"10.1109\/DICTA.2014.7008115"},{"key":"10320_CR33","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Gao Z, Tang C, Zhang J, Ogunbona PO (2015) Convnets-based action recognition from depth maps through virtual cameras and pseudocoloring. In: ACM MM, pp 1119\u20131122","DOI":"10.1145\/2733373.2806296"},{"issue":"4","key":"10320_CR34","first-page":"498","volume":"46","author":"P Wang","year":"2016","unstructured":"Wang P, Li W, Gao Z, Zhang J, Tang C, Ogunbona P (2016a) Action recognition from depth maps using deep convolutional neural networks. THMS 46(4):498\u2013509","journal-title":"THMS"},{"key":"10320_CR35","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Liu S, Gao Z, Tang C, Ogunbona P (2016b) Large-scale isolated gesture recognition using convolutional neural networks. In: Pattern recognition (ICPR), 2016 23rd international conference on, IEEE, pp 7\u201312","DOI":"10.1109\/ICPR.2016.7899599"},{"key":"10320_CR36","doi-asserted-by":"crossref","unstructured":"Wang P, Li Z, Hou Y, Li W (2016c) Action recognition based on joint trajectory maps using convolutional neural networks. In: ACM MM, pp 102\u2013106","DOI":"10.1145\/2964284.2967191"},{"key":"10320_CR37","doi-asserted-by":"crossref","unstructured":"Wang P, Li W, Gao Z, Zhang Y, Tang C, Ogunbona P (2017c) Scene flow to action map: A new representation for rgb-d based action recognition with convolutional neural networks. In: The IEEE conference on computer vision and pattern recognition (CVPR)","DOI":"10.1109\/CVPR.2017.52"},{"issue":"5","key":"10320_CR38","doi-asserted-by":"publisher","first-page":"1051","DOI":"10.1109\/TMM.2018.2818329","volume":"20","author":"P Wang","year":"2018","unstructured":"Wang P, Li W, Gao Z, Tang C, Ogunbona PO (2018) Depth pooling based large-scale 3-d action recognition with convolutional neural networks. IEEE Trans Multimed 20(5):1051\u20131061","journal-title":"IEEE Trans Multimed"},{"key":"10320_CR39","doi-asserted-by":"crossref","unstructured":"Xia L, Chen CC, Aggarwal J (2012) View invariant human action recognition using histograms of 3D joints. In: CVPRW, pp 20\u201327","DOI":"10.1109\/CVPRW.2012.6239233"},{"key":"10320_CR40","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1016\/j.ins.2018.12.050","volume":"480","author":"Y Xiao","year":"2019","unstructured":"Xiao Y, Chen J, Wang Y, Cao Z, Zhou JT, Bai X (2019) Action recognition for depth video using multi-view dynamic images. Inform Sci 480:287\u2013304","journal-title":"Inform Sci"},{"key":"10320_CR41","doi-asserted-by":"crossref","unstructured":"Yang X, Tian Y (2012) Eigenjoints-based action recognition using Naive-Bayes-Nearest-Neighbor. In: CVPRW, pp 14\u201319","DOI":"10.1109\/CVPRW.2012.6239232"},{"key":"10320_CR42","doi-asserted-by":"crossref","unstructured":"Yang X, Tian Y (2014) Super normal vector for activity recognition using depth sequences. In: CVPR, pp 804\u2013811","DOI":"10.1109\/CVPR.2014.108"},{"key":"10320_CR43","doi-asserted-by":"crossref","unstructured":"Yang X, Zhang C, Tian Y (2012) Recognizing actions using depth motion maps-based histograms of oriented gradients. In: ACM MM, pp 1057\u20131060","DOI":"10.1145\/2393347.2396382"},{"key":"10320_CR44","doi-asserted-by":"crossref","unstructured":"Yue-Hei\u00a0Ng J, Hausknecht M, Vijayanarasimhan S, Vinyals O, Monga R, Toderici G (2015) Beyond short snippets: Deep networks for video classification. In: CVPR, pp 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"10320_CR45","doi-asserted-by":"crossref","unstructured":"Zhu G, Zhang L, Shen P, Song J (2017) Multimodal gesture recognition using 3d convolution and convolutional lstm. IEEE Access","DOI":"10.1109\/ACCESS.2017.2684186"}],"container-title":["Neural Processing Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-020-10320-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11063-020-10320-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11063-020-10320-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,5]],"date-time":"2022-11-05T04:40:35Z","timestamp":1667623235000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11063-020-10320-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,7,30]]},"references-count":45,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2020,10]]}},"alternative-id":["10320"],"URL":"https:\/\/doi.org\/10.1007\/s11063-020-10320-w","relation":{},"ISSN":["1370-4621","1573-773X"],"issn-type":[{"type":"print","value":"1370-4621"},{"type":"electronic","value":"1573-773X"}],"subject":[],"published":{"date-parts":[[2020,7,30]]},"assertion":[{"value":"30 July 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}