{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T01:08:39Z","timestamp":1778634519078,"version":"3.51.4"},"reference-count":64,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T00:00:00Z","timestamp":1616457600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T00:00:00Z","timestamp":1616457600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1007\/s00530-021-00773-x","type":"journal-article","created":{"date-parts":[[2021,3,23]],"date-time":"2021-03-23T15:04:25Z","timestamp":1616511865000},"page":"969-984","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":14,"title":["Fusion of spatial and dynamic CNN streams for action recognition"],"prefix":"10.1007","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0835-5848","authenticated-orcid":false,"given":"Newlin Shebiah","family":"Russel","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Arivazhagan","family":"Selvaraj","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,3,23]]},"reference":[{"key":"773_CR1","doi-asserted-by":"crossref","unstructured":"Bobick, A., Davis, J.: An appearance-based representation of action. In: Proceedings of 13th International Conference on Pattern Recognition, Vienna, Austria, vol.1, pp. 307\u2013312 (1996)","DOI":"10.1109\/ICPR.1996.546039"},{"key":"773_CR2","doi-asserted-by":"publisher","first-page":"255","DOI":"10.1007\/s00138-010-0298-4","volume":"23","author":"MAR Ahad","year":"2012","unstructured":"Ahad, M.A.R., Tan, J.K., Kim, H., et al.: Motion history image: its variants and applications. Mach. Vis. Appl. 23, 255\u2013281 (2012)","journal-title":"Mach. Vis. Appl."},{"issue":"2","key":"773_CR3","doi-asserted-by":"publisher","first-page":"316","DOI":"10.1109\/TPAMI.2006.38","volume":"28","author":"J Han","year":"2006","unstructured":"Han, J., Bhanu, B.: Individual recognition using gait energy image. IEEE Trans. Pattern Anal. Mach. Intell. 28(2), 316\u2013322 (2006)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"773_CR4","unstructured":"Chandrashekhar, V., Venkatesh, K.S.: Action energy images for reliable human action recognition. In: Proceedings of 9th Asian Symposium on Information, pp. 484\u2013487 (2006)"},{"issue":"1","key":"773_CR5","first-page":"12","volume":"5","author":"M Ahmad","year":"2010","unstructured":"Ahmad, M., Parvin, I., Lee, S.: Silhouette history and energy image information for human movement recognition. J Multimed 5(1), 12\u201321 (2010)","journal-title":"J Multimed"},{"key":"773_CR6","doi-asserted-by":"crossref","unstructured":"Ahmad, M., Lee, S.: Recognizing human actions based on silhouette energy image and global motion description. In: Proceedings of 8th IEEE International Conference on Automatic Face & Gesture Recognition, Amsterdam, pp. 1\u20136 (2008)","DOI":"10.1109\/AFGR.2008.4813435"},{"key":"773_CR7","doi-asserted-by":"crossref","unstructured":"Ahmad, M., Hossain, M.Z.: SEI and SHI representations for human movement recognition. In: Proceedings of 11th International Conference on Computer and Information Technology, Khulna, Bangladesh, pp. 521\u2013526 (2008)","DOI":"10.1109\/ICCITECHN.2008.4803053"},{"key":"773_CR8","doi-asserted-by":"crossref","unstructured":"Laptev, I., Lindeberg, T.: Space-time interest points. In: Proceedings of Ninth IEEE International Conference on Computer Vision, Nice, France, vol. 1, pp. 432\u2013439 (2003)","DOI":"10.1109\/ICCV.2003.1238378"},{"issue":"3","key":"773_CR9","doi-asserted-by":"publisher","first-page":"710","DOI":"10.1109\/TSMCB.2005.861864","volume":"36","author":"A Oikonomopoulos","year":"2006","unstructured":"Oikonomopoulos, A., Patras, I., Pantic, M.: Spatiotemporal salient points for visual recognition of human actions. IEEE Trans Syst Man Cybern Part B Cybern 36(3), 710\u2013719 (2006)","journal-title":"IEEE Trans Syst Man Cybern Part B Cybern"},{"key":"773_CR10","doi-asserted-by":"crossref","unstructured":"Kadir, T., Brady, M.: Scale Saliency: a novel approach to salient feature and scale selection. In: Proceedings of International Conference on Visual Information Engineering VIE 2003, Guildford, UK, pp. 25\u201328 (2003)","DOI":"10.1049\/cp:20030478"},{"key":"773_CR11","unstructured":"Dollar, P., Rabaud, V., Cottrell, G., Belongie, S.: Behavior recognition via sparse spatio-temporal features. In: Proceedings of IEEE International Workshop on Visual Surveillance and Performance Evaluation of Tracking and Surveillance, Beijing, China, pp. 65\u201372 (2005)"},{"key":"773_CR12","doi-asserted-by":"crossref","unstructured":"Rapantzikos, K., Avrithis, Y., Kollias S.: Spatiotemporal saliency for event detection and representation in the 3D wavelet domain: potential in human action recognition. In: Proceedings of ACM International Conference on Image and Video Retrieval, Amsterdam, The Netherlands, pp. 294\u2013301 (2007)","DOI":"10.1145\/1282280.1282326"},{"key":"773_CR13","doi-asserted-by":"crossref","unstructured":"Wang, H., MuneebUllah, M., Kl\u00e4ser, A., Laptev, I., Schmid, C.: Evaluation of local spatio-temporal features for action recognition. In: Proceedings of British Machine Vision Conference, London, United Kingdom, BMVA Press, pp. 124.1\u2013124.11 (2009)","DOI":"10.5244\/C.23.124"},{"key":"773_CR14","doi-asserted-by":"crossref","unstructured":"Wong, S., Cipolla, R.: Extracting spatiotemporal interest points using global information. In: Proceedings of IEEE 11th International Conference on Computer Vision, Rio de Janeiro, Brazil, pp. 1\u20138 (2007)","DOI":"10.1109\/ICCV.2007.4408923"},{"key":"773_CR15","doi-asserted-by":"crossref","unstructured":"Schuldt, C., Laptev, I., Caputo, B.: Recognizing human actions: a local SVM approach. In: Proceedings of 17th International Conference on Pattern Recognition, Cambridge, UK, vol. 3, pp. 32\u201336 (2004)","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"773_CR16","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial-temporal words. Int. J. Comput. Vis. 79, 299\u2013318 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"773_CR17","doi-asserted-by":"crossref","unstructured":"Laptev, I., Marszalek, M., Schmid, C., Rozenfeld, B.: Learning realistic human actions from movies. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Anchorage, AK, USA, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587756"},{"issue":"1","key":"773_CR18","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.: 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221\u2013231 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"773_CR19","doi-asserted-by":"crossref","unstructured":"Karpathy, A., Toderici, G., Shetty, S., Leung, T., Sukthankar, R., Fei-Fei, L.: Large-scale video classification with convolutional neural networks. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, USA, pp. 1725\u20131732 (2014)","DOI":"10.1109\/CVPR.2014.223"},{"key":"773_CR20","unstructured":"Simonyan, K., Zisserman, A.: Two-stream convolutional networks for action recognition in videos. In: Proceedings of 27th International Conference on Neural Information Processing Systems, vol. 1, pp. 568\u2013576 (2014)"},{"key":"773_CR21","doi-asserted-by":"crossref","unstructured":"Feichtenhofer, C., Pinz, A., Zisserman, A.: Convolutional two-stream network fusion for video action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Las Vegas, NV, USA, pp. 1933\u20131941 (2016)","DOI":"10.1109\/CVPR.2016.213"},{"key":"773_CR22","doi-asserted-by":"crossref","unstructured":"Wang, L., Qiao, Y., Tang, X.: Action recognition with trajectory-pooled deep-convolutional descriptors. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, Boston, MA, USA, pp. 4305\u20134314 (2015)","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"773_CR23","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y.: Towards good practices for very deep two-stream ConvNets. arXiv preprint (2015). arXiv:1507.02159"},{"key":"773_CR24","doi-asserted-by":"crossref","unstructured":"Wang, L., Xiong, Y., Wang, Z., Qiao, Y., Lin, D., Tang, X., Van Gool, L.: Temporal segment networks: towards good practices for deep action recognition. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds) Computer Vision\u2014ECCV 2016. Lecture Notes in Computer Science, vol. 9912, pp. 20\u201336. Springer, Cham (2016)","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"773_CR25","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1007\/s00530-019-00645-5","volume":"26","author":"R Singh","year":"2020","unstructured":"Singh, R., Khurana, R., Kushwaha, A.K.S., Srivastava, R.: Combining CNN streams of dynamic image and depth data for action recognition. Multimed. Syst. 26, 313\u2013322 (2020)","journal-title":"Multimed. Syst."},{"key":"773_CR26","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-020-00667-4","author":"SK Tripathy","year":"2020","unstructured":"Tripathy, S.K., Srivastava, R.: A real-time two-input stream multi-column multi-stage convolution neural network (TIS-MCMS-CNN) for efficient crowd congestion-level analysis. Multimed. Syst. (2020). https:\/\/doi.org\/10.1007\/s00530-020-00667-4","journal-title":"Multimed. Syst."},{"key":"773_CR27","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patcog.2018.01.020","volume":"79","author":"Z Tu","year":"2018","unstructured":"Tu, Z., Xie, W., Qin, Q., Poppe, R., Veltkamp, R.C., Li, B., Yuan, J.: Multi-stream CNN: learning representations based on human-related regions for action recognition. Pattern Recogn. 79, 32\u201343 (2018)","journal-title":"Pattern Recogn."},{"key":"773_CR28","doi-asserted-by":"publisher","unstructured":"Yu D., Wang H., Chen P., Wei Z. (2014) Mixed pooling for convolutional neural networks. In: Miao, D., Pedrycz, W., \u015al\u0229zak, D., Peters, G., Hu, Q., Wang, R. (eds) Rough sets and knowledge technology. RSKT 2014. Lecture notes in computer science, vol. 8818. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-319-11740-9_34","DOI":"10.1007\/978-3-319-11740-9_34"},{"key":"773_CR29","doi-asserted-by":"publisher","unstructured":"Berthold K.P. Horn, Brian G. Schunck, Determining optical flow, artificial intelligence, vol. 17, Issues 1\u20133, pp 185-203, ISSN 0004-3702 (1981). https:\/\/doi.org\/10.1016\/0004-3702(81)90024-2","DOI":"10.1016\/0004-3702(81)90024-2"},{"issue":"4","key":"773_CR30","doi-asserted-by":"publisher","first-page":"773","DOI":"10.1109\/TPAMI.2016.2558148","volume":"39","author":"B Fernando","year":"2017","unstructured":"Fernando, B., Gavves, E., Oramas, M.J., Ghodrati, A., Tuytelaars, T.: Rank pooling for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 39(4), 773\u2013787 (2017)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"773_CR31","doi-asserted-by":"crossref","unstructured":"Blank, M., Gorelick, L., Shechtman, E., Irani, M., Basri, R.: \u2018Actions as space-time shapes\u2019. In: Proceedings of the Tenth IEEE International Conference on Computer Vision, Beijing, China, pp. 1395\u20131402 (2005)","DOI":"10.1109\/ICCV.2005.28"},{"key":"773_CR32","doi-asserted-by":"crossref","unstructured":"Rodriguez, M.D., Ahmed, J., Shah, M.: \u2018Action MACH a spatio-temporal maximum average correlation height filter for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, Anchorage, AK, USA, pp. 1\u20138 (2008)","DOI":"10.1109\/CVPR.2008.4587727"},{"key":"773_CR33","unstructured":"Soomro, K., Zamir, A.R., Shah, M.: UCF101: a dataset of 101 human action classes from videos in the wild, CRCV-TR-12-01, November (2012)"},{"issue":"3","key":"773_CR34","doi-asserted-by":"publisher","first-page":"1220","DOI":"10.1016\/j.patcog.2011.08.014","volume":"45","author":"M Bregonzio","year":"2012","unstructured":"Bregonzio, M., Xiang, T., Gong, S.: Fusing appearance and distribution information of interest points for action recognition. Pattern Recogn. 45(3), 1220\u20131234 (2012)","journal-title":"Pattern Recogn."},{"key":"773_CR35","doi-asserted-by":"publisher","first-page":"88","DOI":"10.1016\/j.neucom.2013.01.022","volume":"113","author":"D Zhao","year":"2013","unstructured":"Zhao, D., Shao, L., Zhen, X., Liu, Y.: Combining appearance and structural features for human action recognition. Neurocomputing 113, 88\u201396 (2013)","journal-title":"Neurocomputing"},{"issue":"6","key":"773_CR36","doi-asserted-by":"publisher","first-page":"579","DOI":"10.1049\/iet-cvi.2013.0306","volume":"8","author":"W Zhou","year":"2014","unstructured":"Zhou, W., Wang, C., Xiao, B., Zhang, Z.: Human action recognition using weighted pooling. IET Comput. Vis. 8(6), 579\u2013587 (2014)","journal-title":"IET Comput. Vis."},{"key":"773_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cviu.2014.01.002","volume":"123","author":"G Somasundaram","year":"2014","unstructured":"Somasundaram, G., Cherian, A., Morellas, V., Papanikolopoulos, N.: Action recognition using global spatio-temporal features derived from sparse representations. Comput. Vis. Image Underst. 123, 1\u201313 (2014)","journal-title":"Comput. Vis. Image Underst."},{"issue":"2","key":"773_CR38","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1016\/j.jare.2013.11.007","volume":"6","author":"MM Moussa","year":"2015","unstructured":"Moussa, M.M., Hamayed, E., Fayek, M.B., El Nemr, H.A.: An enhanced method for human action recognition. J. Adv. Res. 6(2), 163\u2013169 (2015)","journal-title":"J. Adv. Res."},{"key":"773_CR39","doi-asserted-by":"crossref","unstructured":"Xu, K., Jiang, X., Sun, T.: Human activity recognition based on pose points selection. In: Proceedings of IEEE International Conference on Image Processing, Quebec City, QC, Canada, pp. 2930\u20132834 (2015)","DOI":"10.1109\/ICIP.2015.7351339"},{"issue":"1","key":"773_CR40","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s41095-016-0033-9","volume":"2","author":"A Abdulmunem","year":"2016","unstructured":"Abdulmunem, A., Lai, Y., Sun, X.: Saliency guided local and global descriptors for effective action recognition. Comput. Vis. Media 2(1), 97\u2013106 (2016)","journal-title":"Comput. Vis. Media"},{"issue":"4","key":"773_CR41","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1049\/iet-cvi.2015.0235","volume":"10","author":"M Selmi","year":"2016","unstructured":"Selmi, M., El-Yacoubi, M.A., Dorizzi, B.: Two-layer discriminative model for human activity recognition. IET Comput. Vis. 10(4), 273\u2013278 (2016)","journal-title":"IET Comput. Vis."},{"key":"773_CR42","first-page":"1","volume":"134","author":"N Zhang","year":"2018","unstructured":"Zhang, N., Hu, Z., Lee, S., Lee, E.: Human action recognition based on global silhouette and local optical flow. Adv. Eng. Res. 134, 1\u20135 (2018)","journal-title":"Adv. Eng. Res."},{"issue":"7","key":"773_CR43","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1049\/iet-cvi.2016.0055","volume":"11","author":"F Mart\u00ednez","year":"2017","unstructured":"Mart\u00ednez, F., Manzanera, A., Romero, E.: Spatio-temporal multi-scale motion descriptor from a spatially-constrained decomposition for online action recognition. IET Comput. Vis. 11(7), 541\u2013549 (2017)","journal-title":"IET Comput. Vis."},{"key":"773_CR44","doi-asserted-by":"publisher","first-page":"471","DOI":"10.1016\/j.procs.2018.07.059","volume":"133","author":"J Arunnehru","year":"2018","unstructured":"Arunnehru, J., Chamundeeswari, G., Bharathi, S.P.: Human action recognition using 3D convolutional neural networks with 3D motion cuboids in surveillance videos. Procedia Comput. Sci. 133, 471\u2013477 (2018)","journal-title":"Procedia Comput. Sci."},{"key":"773_CR45","doi-asserted-by":"publisher","first-page":"39","DOI":"10.1016\/j.patrec.2017.12.024","volume":"103","author":"S Nazir","year":"2018","unstructured":"Nazir, S., Yousaf, M.H., Nebel, J., Velastin, S.A.: A Bag of Expression framework for improved human action recognition. Pattern Recogn. Lett. 103, 39\u201345 (2018)","journal-title":"Pattern Recogn. Lett."},{"issue":"4","key":"773_CR46","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1134\/S1054661819040084","volume":"29","author":"A Khelalef","year":"2019","unstructured":"Khelalef, A., Ababsa, F., Benoudjit, N.: An efficient human activity recognition technique based on deep learning. Pattern Recognit. Image Anal. 29(4), 702\u2013715 (2019)","journal-title":"Pattern Recognit. Image Anal."},{"issue":"4","key":"773_CR47","first-page":"447","volume":"32","author":"N Jaouedi","year":"2020","unstructured":"Jaouedi, N., Boujnah, N., Bouhlel, M.S.: A new hybrid deep learning model for human action recognition. J. King Saud Univ. Comput. Inf. Sci. 32(4), 447\u2013453 (2020)","journal-title":"J. King Saud Univ. Comput. Inf. Sci."},{"key":"773_CR48","unstructured":"Basha, S.H.S., Pulabaigari, V., Mukherjee, S.: An information-rich sampling technique over spatio-temporal CNN for classification of human actions in videos. arXiv preprint (2020). arXiv:2002.02100"},{"key":"773_CR49","doi-asserted-by":"publisher","unstructured":"Parisi, G.I.: Human action recognition and assessment via deep neural network self-organization. In: Noceti, N., Sciutti, A., Rea, F. (eds) Modelling human motion. Springer, Cham, pp. 187\u2013211 (2020). https:\/\/doi.org\/10.1007\/978-3-030-46732-6_10","DOI":"10.1007\/978-3-030-46732-6_10"},{"key":"773_CR50","doi-asserted-by":"crossref","unstructured":"Baccouche, M., Mamalet, F., Wolf, C., Garcia, C., Baskurt, A.: Sequential deep learning for human action recognition. In: Salah A.A., Lepri B. (eds) Human behavior understanding. HBU 2011. Lecture notes in computer science, vol. 7065. Springer, Berlin, pp. 29\u201339 (2011)","DOI":"10.1007\/978-3-642-25446-8_4"},{"key":"773_CR51","doi-asserted-by":"crossref","unstructured":"De Oliveira Silva, V., De Barros Vidal, F., Soares Romariz, A.R.: Human action recognition based on a two-stream convolutional network classifier. In: Proceedings of 16th IEEE International Conference on Machine Learning and Applications, Cancun, Mexico, pp. 774\u2013778 (2017)","DOI":"10.1109\/ICMLA.2017.00-64"},{"key":"773_CR52","doi-asserted-by":"crossref","unstructured":"Peng, X., Schmid, C.: Multi-region two-stream R-CNN for action detection. In: Proceedings of European Conference on Computer Vision, Amsterdam, Netherlands, pp. 744\u2013759 (2016)","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"773_CR53","unstructured":"Shamsipour, G., Shanbehzadeh, J., Sarrafzadeh, H.: Human action recognition by conceptual features. In: Proceedings of the International MultiConference of Engineers and Computer Scientists, Hong Kong, vol. 1 (2017)"},{"key":"773_CR54","doi-asserted-by":"publisher","first-page":"17913","DOI":"10.1109\/ACCESS.2018.2817253","volume":"6","author":"L Wang","year":"2018","unstructured":"Wang, L., Xu, Y., Cheng, J., Xia, H., Yin, J., Wu, J.: Human action recognition by learning spatio-temporal features with deep neural networks. IEEE Access 6, 17913\u201317922 (2018)","journal-title":"IEEE Access"},{"key":"773_CR55","doi-asserted-by":"publisher","unstructured":"Shamsipour, G., Pirasteh, S.: Artificial intelligence and Convolutional neural network for recognition of human interaction by video from drone. Preprints 2019 (2019). https:\/\/doi.org\/10.20944\/preprints201908.0289.v1","DOI":"10.20944\/preprints201908.0289.v1"},{"key":"773_CR56","doi-asserted-by":"crossref","unstructured":"Carreira, J., Zisserman, A.: Quo vadis, action recognition? A new model and the kinetics dataset. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 4724\u20134733 (2017)","DOI":"10.1109\/CVPR.2017.502"},{"key":"773_CR57","doi-asserted-by":"crossref","unstructured":"Kar, A., Rai, N., Sikka, K., Sharma, G.: AdaScan: adaptive scan pooling in deep convolutional neural networks for human action recognition in videos. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA, pp. 5699\u20135708 (2017)","DOI":"10.1109\/CVPR.2017.604"},{"key":"773_CR58","doi-asserted-by":"crossref","unstructured":"Bilen, H., Fernando, B., Gavves, E., Vedaldi, A., Gould, S.: Dynamic image networks for action recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Las Vegas, NV, USA, pp. 3034\u20133042 (2016)","DOI":"10.1109\/CVPR.2016.331"},{"issue":"12","key":"773_CR59","doi-asserted-by":"publisher","first-page":"115","DOI":"10.3390\/fi10120115","volume":"10","author":"W Yang","year":"2018","unstructured":"Yang, W., Chen, Y., Huang, C., Gao, M.: Video-based human action recognition using spatial pyramid pooling and 3D densely convolutional networks. Future Internet 10(12), 115 (2018)","journal-title":"Future Internet"},{"issue":"6","key":"773_CR60","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.: Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510\u20131517 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"773_CR61","doi-asserted-by":"publisher","first-page":"1155","DOI":"10.1109\/ACCESS.2017.2778011","volume":"6","author":"A Ullah","year":"2018","unstructured":"Ullah, A., Ahmad, J., Muhammad, K., Sajjad, M., Baik, S.W.: Action recognition in video sequences using deep bi-directional LSTM with CNN features. IEEE Access 6, 1155\u20131166 (2018)","journal-title":"IEEE Access"},{"issue":"3","key":"773_CR62","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.: Two-stream 3-D convNet fusion for action recognition in videos with arbitrary size and length. IEEE Trans. Multimed. 20(3), 634\u2013644 (2018)","journal-title":"IEEE Trans. Multimed."},{"key":"773_CR63","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-020-04982-9","author":"YL Chang","year":"2020","unstructured":"Chang, Y.L., Chan, C.S., Remagnino, P.: Action recognition on continuous video. Neural Comput. Appl. (2020). https:\/\/doi.org\/10.1007\/s00521-020-04982-9","journal-title":"Neural Comput. Appl."},{"key":"773_CR64","doi-asserted-by":"publisher","unstructured":"Zhao, Y., Man, K.L., Smith, J., Siddique, K., Guan, S.: Improved two-stream model for human action recognition. EURASIP J. Image Video Process. 24:5 (2020). https:\/\/doi.org\/10.1186\/s13640-020-00501-x","DOI":"10.1186\/s13640-020-00501-x"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00773-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-021-00773-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-021-00773-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,9,13]],"date-time":"2021-09-13T09:41:26Z","timestamp":1631526086000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-021-00773-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,3,23]]},"references-count":64,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2021,10]]}},"alternative-id":["773"],"URL":"https:\/\/doi.org\/10.1007\/s00530-021-00773-x","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,3,23]]},"assertion":[{"value":"20 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 March 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}