{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2022,7,19]],"date-time":"2022-07-19T09:29:49Z","timestamp":1658222989602},"reference-count":71,"publisher":"Springer Science and Business Media LLC","issue":"9","license":[{"start":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T00:00:00Z","timestamp":1549584000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"name":"Shaanxi Province key project of Research and Development Plan research project","award":["S2018-YF-ZDGY-0187"],"award-info":[{"award-number":["S2018-YF-ZDGY-0187"]}]},{"name":"International Cooperation Project of Shaanxi Province research project","award":["S2018-YF-GHMS-0061"],"award-info":[{"award-number":["S2018-YF-GHMS-0061"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Neural Comput & Applic"],"published-print":{"date-parts":[[2020,5]]},"DOI":"10.1007\/s00521-019-04030-1","type":"journal-article","created":{"date-parts":[[2019,2,8]],"date-time":"2019-02-08T07:08:58Z","timestamp":1549609738000},"page":"5285-5302","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["DKD\u2013DAD: a novel framework with discriminative kinematic descriptor and deep attention-pooled descriptor for action recognition"],"prefix":"10.1007","volume":"32","author":[{"given":"Ming","family":"Tong","sequence":"first","affiliation":[]},{"given":"Mingyang","family":"Li","sequence":"additional","affiliation":[]},{"given":"He","family":"Bai","sequence":"additional","affiliation":[]},{"given":"Lei","family":"Ma","sequence":"additional","affiliation":[]},{"given":"Mengao","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,2,8]]},"reference":[{"key":"4030_CR1","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: a dataset of 101 human actions classes from videos in the wild. \narXiv:1212.0402"},{"key":"4030_CR2","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) HMDB: a large video database for human motion recognition. In: Proceedings of IEEE international conference on computer vision (ICCV), pp 2556\u20132563","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"4030_CR3","doi-asserted-by":"crossref","unstructured":"Laptev I, Marszalek M, Schmid C, Rozenfeld B (2008) Learning realistic human actions from movies. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 1\u20138","DOI":"10.1109\/CVPR.2008.4587756"},{"issue":"2\u20133","key":"4030_CR4","doi-asserted-by":"publisher","first-page":"107","DOI":"10.1007\/s11263-005-1838-7","volume":"64","author":"I Laptev","year":"2005","unstructured":"Laptev I (2005) On space-time interest points. Int J Comput Vis 64(2\u20133):107\u2013123","journal-title":"Int J Comput Vis"},{"key":"4030_CR5","doi-asserted-by":"crossref","unstructured":"Dollar P, Rabaud V, Cottrell G, Belongie S (2005) Behavior recognition via sparse spatio-temporal features. In: Proceedings of the 14th international conference on computer communications and networks (ICCCN), pp 65\u201372","DOI":"10.1109\/VSPETS.2005.1570899"},{"issue":"2","key":"4030_CR6","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1109\/TIP.2013.2291319","volume":"23","author":"C Yuan","year":"2014","unstructured":"Yuan C, Li X, Hu W, Ling H, Maybank SJ (2014) Modeling geometric-temporal context with directional pyramid co-occurrence for action recognition. IEEE Trans Image Process 23(2):658\u2013672","journal-title":"IEEE Trans Image Process"},{"issue":"10","key":"4030_CR7","doi-asserted-by":"publisher","first-page":"4709","DOI":"10.1109\/TIP.2018.2836323","volume":"27","author":"J Zhang","year":"2018","unstructured":"Zhang J, Shum HP, Han J, Shao L (2018) Action recognition from arbitrary views using transferable dictionary learning. IEEE Trans Image Process 27(10):4709\u20134723","journal-title":"IEEE Trans Image Process"},{"issue":"3","key":"4030_CR8","doi-asserted-by":"publisher","first-page":"219","DOI":"10.1007\/s11263-015-0846-5","volume":"119","author":"H Wang","year":"2016","unstructured":"Wang H, Oneata D, Verbeek J, Schmid C (2016) A robust and efficient video representation for action recognition. Int J Comput Vis 119(3):219\u2013238","journal-title":"Int J Comput Vis"},{"issue":"1","key":"4030_CR9","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Kl\u00e4ser A, Schmid C, Liu CL (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vis 103(1):60\u201379","journal-title":"Int J Comput Vis"},{"key":"4030_CR10","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. In: Advances in neural information processing systems (NIPS), pp 568\u2013576"},{"key":"4030_CR11","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3D convolutional networks. In: Proceedings of IEEE international conference on computer vision (ICCV), pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"4030_CR12","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.patcog.2015.11.022","volume":"53","author":"Y Yi","year":"2016","unstructured":"Yi Y, Lin M (2016) Human action recognition with graph-based multiple-instance learning. Pattern Recognit 53:148\u2013162","journal-title":"Pattern Recognit"},{"key":"4030_CR13","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.patcog.2016.07.031","volume":"62","author":"S Singh","year":"2017","unstructured":"Singh S, Arora C, Jawahar CV (2017) Trajectory aligned features for first person action recognition. Pattern Recognit 62:45\u201355","journal-title":"Pattern Recognit"},{"key":"4030_CR14","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3691-y","author":"H Zhang","year":"2018","unstructured":"Zhang H, Sun Y, Liu L, Wang X, Li L, Liu W (2018) ClothingOut: a category-supervised GAN model for clothing segmentation and retrieval. Neural Comput Appl. \nhttps:\/\/doi.org\/10.1007\/s00521-018-3691-y","journal-title":"Neural Comput Appl"},{"key":"4030_CR15","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1016\/j.neucom.2018.08.013","volume":"316","author":"Y Ji","year":"2018","unstructured":"Ji Y, Zhang H, Wu QMJ (2018) Saliency detection via conditional adversarial image-to-image network. Neurocomputing 316:357\u2013368","journal-title":"Neurocomputing"},{"key":"4030_CR16","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-018-3579-x","author":"H Zhang","year":"2018","unstructured":"Zhang H, Ji Y, Huang W, Liu L (2018) Sitcom-star-based clothing retrieval for video advertising: a deep learning framework. Neural Comput Appl. \nhttps:\/\/doi.org\/10.1007\/s00521-018-3579-x","journal-title":"Neural Comput Appl"},{"issue":"1","key":"4030_CR17","doi-asserted-by":"publisher","first-page":"90","DOI":"10.1109\/TCSVT.2016.2586853","volume":"28","author":"J Wang","year":"2018","unstructured":"Wang J, Wang G (2018) Hierarchical spatial sum-product networks for action recognition in still images. IEEE Trans Circuits Syst Video Technol 28(1):90\u2013100","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4030_CR18","doi-asserted-by":"crossref","unstructured":"Kwak S, Cho M, Laptev I (2016) Thin-slicing for pose: Learning to understand pose without explicit pose estimation. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 4938\u20134947","DOI":"10.1109\/CVPR.2016.534"},{"key":"4030_CR19","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1016\/j.neucom.2017.06.041","volume":"267","author":"T Qi","year":"2017","unstructured":"Qi T, Xu Y, Quan Y, Ling L (2017) Image-based action recognition using hint-enhanced deep neural networks. Neurocomputing 267:475\u2013488","journal-title":"Neurocomputing"},{"key":"4030_CR20","doi-asserted-by":"crossref","unstructured":"Peng X, Schmid C (2016) Multi-region two-stream R-CNN for action detection. In: Proceedings of European conference on computer vision (ECCV), pp 744\u2013759","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"4030_CR21","unstructured":"Ren S, He K, Girshick R, Sun J (2015) Faster R-CNN: towards real-time object detection with region proposal networks. In: Advances in neural information processing systems (NIPS), pp 91\u201399"},{"issue":"8","key":"4030_CR22","doi-asserted-by":"publisher","first-page":"3715","DOI":"10.1109\/TNNLS.2017.2731775","volume":"29","author":"B Ni","year":"2018","unstructured":"Ni B, Li T, Yang X (2018) Learning semantic-aligned action representation. IEEE Trans Neural Netw Learn Syst 29(8):3715\u20133725","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"key":"4030_CR23","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR), pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"4030_CR24","doi-asserted-by":"crossref","unstructured":"Farneb\u00e4ck G (2003) Two-frame motion estimation based on polynomial expansion. In: Proceedings of the Scandinavian conference on image analysis (SCIA), pp 363\u2013370","DOI":"10.1007\/3-540-45103-X_50"},{"issue":"1","key":"4030_CR25","doi-asserted-by":"publisher","first-page":"131","DOI":"10.1109\/TPAMI.2004.1261097","volume":"26","author":"J Yang","year":"2004","unstructured":"Yang J, Zhang D, Frangi AF, Yang J (2004) Two-dimensional PCA: a new approach to appearance-based face representation and recognition. IEEE Trans Pattern Anal Mach Int 26(1):131\u2013137","journal-title":"IEEE Trans Pattern Anal Mach Int"},{"issue":"3","key":"4030_CR26","doi-asserted-by":"publisher","first-page":"222","DOI":"10.1007\/s11263-013-0636-x","volume":"105","author":"J S\u00e1nchez","year":"2013","unstructured":"S\u00e1nchez J, Perronnin F, Mensink T, Verbeek J (2013) Image classification with the fisher vector: theory and practice. Int J Comput Vis 105(3):222\u2013245","journal-title":"Int J Comput Vis"},{"key":"4030_CR27","unstructured":"Krizhevsky A, Sutskever I, Hinton GE (2012) ImageNet classification with deep convolutional neural networks. In: Advances in neural information processing systems (NIPS), pp 1097\u20131105"},{"key":"4030_CR28","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. \narXiv:1502.03167"},{"key":"4030_CR29","unstructured":"Girdhar R, Ramanan D (2017) Attentional pooling for action recognition. In: Advances in neural information processing systems (NIPS), pp 34\u201345"},{"key":"4030_CR30","unstructured":"Zhou Q, Fan H, Su H, Yang H, Zheng S, Ling H (2018) Weighted bilinear coding over salient body parts for person re-identification. \narXiv:1803.08580"},{"key":"4030_CR31","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. \narXiv:1511.04119"},{"key":"4030_CR32","doi-asserted-by":"crossref","unstructured":"Zhuang B, Liu L, Shen C, Reid I (2017) Towards context\u2013aware interaction recognition for visual relationship detection. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 589\u2013598","DOI":"10.1109\/ICCV.2017.71"},{"key":"4030_CR33","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2017.2783944","author":"S Yan","year":"2017","unstructured":"Yan S, Smith JS, Lu W, Zhang B (2017) Multi-branch attention networks for action recognition in still images. IEEE Trans Cognit Develop Syst. \nhttps:\/\/doi.org\/10.1109\/TCDS.2017.2783944","journal-title":"IEEE Trans Cognit Develop Syst"},{"key":"4030_CR34","unstructured":"Jiang YG, Liu J, Zamir AR, Toderici G, Laptev I, Shah M, Sukthankar R (2013) THUMOS challenge: action recognition with a large number of classes. \nhttp:\/\/crcv.ucf.edu\/THUMOS14\n\n. Accessed 30 June 2018"},{"issue":"3","key":"4030_CR35","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1007\/s11263-015-0816-y","volume":"115","author":"O Russakovsky","year":"2015","unstructured":"Russakovsky O, Deng J, Su H, Krause J, Satheesh S, Ma S, Huang Z, Karpathy A, Khosla A, Bernstein M, Berg AC, Fei-Fei L (2015) Imagenet large scale visual recognition challenge. Int J Comput Vis 115(3):211\u2013252","journal-title":"Int J Comput Vis"},{"key":"4030_CR36","unstructured":"Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, Goodfellow I, Harp A, Irving G, Isard M, Jia Y, Jozefowicz R, Kaiser L, Kudlur M, Levenberg J, Man\u00e9 D, Monga R, Moore S, Murray D, Olah C, Schuster M, Shlens J, Steiner B, Sutskever I, Talwar K, Tucker P, Vanhoucke V, Vasudevan V, Vi\u00e9gas F, Vinyals O, Warden P, Wattenberg M, Wicke M, Yu Y, Zheng X (2015) TensorFlow: large-scale machine learning on heterogeneous systems. \nhttp:\/\/tensorflow.org\/\n\n. Accessed 30 June 2018. Software available from tensorflow.org"},{"issue":"12","key":"4030_CR37","doi-asserted-by":"publisher","first-page":"5904","DOI":"10.1109\/TIP.2015.2490551","volume":"24","author":"J Miao","year":"2015","unstructured":"Miao J, Xu X, Qiu S, Qinf C, Tao D (2015) Temporal variance analysis for action recognition. IEEE Trans Image Process 24(12):5904\u20135915","journal-title":"IEEE Trans Image Process"},{"issue":"11","key":"4030_CR38","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1016\/j.imavis.2015.11.010","volume":"46","author":"F Shi","year":"2016","unstructured":"Shi F, Lagani\u00e8re R, Petriu E (2016) Local part model for action recognition. Image Vis Comput 46(11):18\u201328","journal-title":"Image Vis Comput"},{"key":"4030_CR39","doi-asserted-by":"publisher","first-page":"109","DOI":"10.1016\/j.cviu.2016.03.013","volume":"150","author":"X Peng","year":"2016","unstructured":"Peng X, Wang L, Wang X, Qiao Y (2016) Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. Comput Vis Image Underst 150:109\u2013125","journal-title":"Comput Vis Image Underst"},{"key":"4030_CR40","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1016\/j.neucom.2017.04.007","volume":"260","author":"TV Nguyen","year":"2017","unstructured":"Nguyen TV, Mirza B (2017) Dual-layer kernel extreme learning machine for action recognition. Neurocomputing 260:123\u2013130","journal-title":"Neurocomputing"},{"key":"4030_CR41","doi-asserted-by":"crossref","unstructured":"Kobayashi T (2017) Flip-invariant motion representation. In: Proceedings of the IEEE international conference on computer vision (ICCV), pp 5628\u20135637","DOI":"10.1109\/ICCV.2017.600"},{"key":"4030_CR42","doi-asserted-by":"crossref","unstructured":"Jain M, Jegou H, Bouthemy P (2013) Better exploiting motion for better action recognition. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR), pp 2555\u20132562","DOI":"10.1109\/CVPR.2013.330"},{"issue":"8","key":"4030_CR43","doi-asserted-by":"publisher","first-page":"1651","DOI":"10.1109\/TPAMI.2015.2491925","volume":"38","author":"M Yu","year":"2016","unstructured":"Yu M, Liu L, Shao L (2016) Structure-preserving binary representations for RGB-D action recognition. IEEE Trans Pattern Anal Mach Int 38(8):1651\u20131664","journal-title":"IEEE Trans Pattern Anal Mach Int"},{"key":"4030_CR44","doi-asserted-by":"crossref","unstructured":"Caetano C, dos Santos JA, Schwartz WR (2016) Optical flow co-occurrence matrices: a novel spatiotemporal feature descriptor. In: Proceedings of international conference pattern recognition (ICPR), pp 1947\u20131952","DOI":"10.1109\/ICPR.2016.7899921"},{"key":"4030_CR45","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1016\/j.neucom.2016.09.106","volume":"236","author":"Z Xu","year":"2017","unstructured":"Xu Z, Hu R, Chen J, Chen C, Chen H, Li H, Sun Q (2017) Action recognition by saliency-based dense sampling. Neurocomputing 236:82\u201392","journal-title":"Neurocomputing"},{"key":"4030_CR46","doi-asserted-by":"crossref","unstructured":"Miao J, Xu X, Mathew R, Huang H (2015) Residue boundary histograms for action recognition in the compressed domain. In: Proceedings of IEEE international conference on image processing (ICIP), pp 2825\u20132829","DOI":"10.1109\/ICIP.2015.7351318"},{"issue":"4","key":"4030_CR47","doi-asserted-by":"publisher","first-page":"1174","DOI":"10.1016\/j.patcog.2014.11.013","volume":"48","author":"O Kihl","year":"2015","unstructured":"Kihl O, Picard D, Gosselin PH (2015) A unified framework for local visual descriptors evaluation. Pattern Recognit 48(4):1174\u20131184","journal-title":"Pattern Recognit"},{"key":"4030_CR48","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2015) Dynamically encoded actions based on spacetime saliency. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR), pp 2755\u20132764","DOI":"10.1109\/CVPR.2015.7298892"},{"key":"4030_CR49","doi-asserted-by":"crossref","unstructured":"Fernando B, Anderson P, Hutter M, Gould S (2016) Discriminative hierarchical rank pooling for activity recognition. In: Proceedings of the IEEE international conference on computer vision and pattern recognition (CVPR), pp 1924\u20131932","DOI":"10.1109\/CVPR.2016.212"},{"issue":"3","key":"4030_CR50","doi-asserted-by":"publisher","first-page":"254","DOI":"10.1007\/s11263-015-0859-0","volume":"119","author":"L Wang","year":"2016","unstructured":"Wang L, Qiao Y, Tang X (2016) MoFAP: a multi-level representation for action recognition. Int J Comput Vis 119(3):254\u2013271","journal-title":"Int J Comput Vis"},{"key":"4030_CR51","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2816960","author":"NA Tu","year":"2018","unstructured":"Tu NA, Huynh-The T, Khan KU, Lee YK (2018) ML-HDP: a hierarchical bayesian nonparametric model for recognizing human actions in video. IEEE Trans Circuits Syst Video Technol. \nhttps:\/\/doi.org\/10.1109\/TCSVT.2018.2816960","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4030_CR52","doi-asserted-by":"publisher","first-page":"323","DOI":"10.1016\/j.sigpro.2017.10.022","volume":"144","author":"Y Zheng","year":"2018","unstructured":"Zheng Y, Yao H, Sun X, Zhao S, Porikli F (2018) Distinctive action sketch for human action recognition. Signal Process 144:323\u2013332","journal-title":"Signal Process"},{"issue":"11","key":"4030_CR53","doi-asserted-by":"publisher","first-page":"3781","DOI":"10.1109\/TIP.2015.2456412","volume":"24","author":"YG Jiang","year":"2015","unstructured":"Jiang YG, Dai Q, Liu W, Xue X, Ngo CH (2015) Human action recognition in unconstrained videos by explicit motion modeling. IEEE Trans Image Process 24(11):3781\u20133795","journal-title":"IEEE Trans Image Process"},{"key":"4030_CR54","unstructured":"Bilinski PT, Bremond F (2015) Video covariance matrix logarithm for human action recognition in videos. In: Proceedings of the 24th international conference on artificial intelligence (IJCAI), pp 2140\u20132147"},{"issue":"2","key":"4030_CR55","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1007\/s11263-015-0861-6","volume":"118","author":"L Shao","year":"2016","unstructured":"Shao L, Liu L, Yu M (2016) Kernelized multiview projection for robust action recognition. Int J Comput Vis 118(2):115\u2013129","journal-title":"Int J Comput Vis"},{"key":"4030_CR56","doi-asserted-by":"publisher","first-page":"36","DOI":"10.1016\/j.sigpro.2015.10.035","volume":"124","author":"Y Yang","year":"2016","unstructured":"Yang Y, Liu R, Deng C, Gao X (2016) Multi-task human action recognition via exploring super-category. Signal Process 124:36\u201344","journal-title":"Signal Process"},{"key":"4030_CR57","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1016\/j.patcog.2016.11.012","volume":"64","author":"T Yao","year":"2017","unstructured":"Yao T, Wang Z, Xie Z, Gao J, Feng DD (2017) Learning universal multiview dictionary for human action recognition. Pattern Recognit 64:236\u2013244","journal-title":"Pattern Recognit"},{"key":"4030_CR58","doi-asserted-by":"crossref","unstructured":"Zhu Y, Newsam S (2016) Depth2action: exploring embedded depth for large-scale action recognition. In: Proceedings of European conference on computer vision (ECCV), pp 668\u2013684","DOI":"10.1007\/978-3-319-46604-0_47"},{"key":"4030_CR59","doi-asserted-by":"crossref","unstructured":"Bilen H, Fernando B, Gavves E, Vedaldi A, Gould S (2016) Dynamic image networks for action recognition. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 3034\u20133042","DOI":"10.1109\/CVPR.2016.331"},{"key":"4030_CR60","unstructured":"Lan Z, Yu SI, Yao D, Lin M, Raj B, Hauptmann A (2016) The best of both worlds: Combining data-independent and data-driven approaches for action recognition. In: Proceedings of IEEE international conference on computer vision and pattern recognition workshops (CVPR Workshops), pp 123\u2013132"},{"key":"4030_CR61","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. In: Advances in neural information processing systems (NIPS), pp 3468\u20133476"},{"key":"4030_CR62","doi-asserted-by":"crossref","unstructured":"Wang X, Farhadi A, Gupta A (2016) Actions\u2009~\u2009transformations. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 2658\u20132667","DOI":"10.1109\/CVPR.2016.291"},{"issue":"12","key":"4030_CR63","doi-asserted-by":"publisher","first-page":"2613","DOI":"10.1109\/TCSVT.2016.2576761","volume":"27","author":"P Wang","year":"2017","unstructured":"Wang P, Cao Y, Shen C, Liu L, Shen HT (2017) Temporal pyramid pooling-based convolutional neural network for action recognition. IEEE Trans Circuits Syst Video Technol 27(12):2613\u20132622","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4030_CR64","doi-asserted-by":"crossref","unstructured":"Kar A, Rai N, Sikka K, Sharma G (2017) Adascan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 3376\u20133385","DOI":"10.1109\/CVPR.2017.604"},{"key":"4030_CR65","doi-asserted-by":"crossref","unstructured":"Ye Y, Tian Y (2016) Embedding sequential information into spatiotemporal features for action recognition. In: Proceedings of the IEEE international conference on computer vision workshops (ICCV Workshops), pp 37\u201345","DOI":"10.1109\/CVPRW.2016.142"},{"key":"4030_CR66","doi-asserted-by":"crossref","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2016) Real-time action recognition with enhanced motion vector CNNs. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 2718\u20132726","DOI":"10.1109\/CVPR.2016.297"},{"key":"4030_CR67","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1016\/j.patcog.2017.01.027","volume":"68","author":"S Ma","year":"2017","unstructured":"Ma S, Bargal SA, Zhang J, Sigal L, Sclaroff S (2017) Do less and achieve more: training CNNs for action recognition utilizing action images from the web. Pattern Recognit 68:334\u2013345","journal-title":"Pattern Recognit"},{"key":"4030_CR68","doi-asserted-by":"crossref","unstructured":"Yang H, Yuan C, Xing J, Hu W (2017) SCNN: Sequential convolutional neural network for human action recognition in videos. In: Proceedings of the IEEE international conference on image processing (ICIP), pp 355\u2013359","DOI":"10.1109\/ICIP.2017.8296302"},{"key":"4030_CR69","doi-asserted-by":"crossref","unstructured":"Cherian A, Fernando B, Harandi M, Gould S (2017) Generalized rank pooling for activity recognition. In: Proceedings of IEEE international conference on computer vision and pattern recognition (CVPR), pp 1581\u20131590","DOI":"10.1109\/CVPR.2017.172"},{"issue":"5","key":"4030_CR70","doi-asserted-by":"publisher","first-page":"2326","DOI":"10.1109\/TIP.2018.2791180","volume":"27","author":"B Zhang","year":"2018","unstructured":"Zhang B, Wang L, Wang Z, Qiao Y, Wang H (2018) Real-time action recognition with deeply transferred motion vector CNNs. IEEE Trans Image Process 27(5):2326\u20132339","journal-title":"IEEE Trans Image Process"},{"issue":"6","key":"4030_CR71","doi-asserted-by":"publisher","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","volume":"40","author":"G Varol","year":"2018","unstructured":"Varol G, Laptev I, Schmid C (2018) Long-term temporal convolutions for action recognition. IEEE Trans Pattern Anal Mach Int 40(6):1510\u20131517","journal-title":"IEEE Trans Pattern Anal Mach Int"}],"container-title":["Neural Computing and Applications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00521-019-04030-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04030-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00521-019-04030-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,4,19]],"date-time":"2020-04-19T18:22:21Z","timestamp":1587320541000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00521-019-04030-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,2,8]]},"references-count":71,"journal-issue":{"issue":"9","published-print":{"date-parts":[[2020,5]]}},"alternative-id":["4030"],"URL":"https:\/\/doi.org\/10.1007\/s00521-019-04030-1","relation":{},"ISSN":["0941-0643","1433-3058"],"issn-type":[{"value":"0941-0643","type":"print"},{"value":"1433-3058","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,2,8]]},"assertion":[{"value":"8 October 2018","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 January 2019","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2019","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Compliance with ethical standards"}},{"value":"All the authors of the manuscript declared that there are no potential conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"All the authors of the manuscript declared that there is no research involving human participants and\/or animal.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Human and animal rights"}},{"value":"All the authors of the manuscript declared that there is no material that required informed consent.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}