{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T16:21:40Z","timestamp":1768407700103,"version":"3.49.0"},"reference-count":73,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T00:00:00Z","timestamp":1621209600000},"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":["Multimed Tools Appl"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1007\/s11042-021-11022-8","type":"journal-article","created":{"date-parts":[[2021,5,17]],"date-time":"2021-05-17T03:12:40Z","timestamp":1621221160000},"page":"3145-3163","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Learning representative temporal features for action recognition"],"prefix":"10.1007","volume":"81","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1502-5548","authenticated-orcid":false,"given":"Ali","family":"Javidani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ahmad","family":"Mahmoudi-Aznaveh","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,5,17]]},"reference":[{"key":"11022_CR1","doi-asserted-by":"crossref","unstructured":"Ali A, Taylor GW (2018) Real-time end-to-end action detection with two-stream networks. in 2018 15th Conference on Computer and Robot Vision (CRV). IEEE p. 31\u201338","DOI":"10.1109\/CRV.2018.00015"},{"issue":"3","key":"11022_CR2","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1023\/B:VISI.0000045324.43199.43","volume":"61","author":"A Bruhn","year":"2005","unstructured":"Bruhn A, Weickert J, Schn\u00f6rr C (2005) Lucas\/Kanade meets Horn\/Schunck: combining local and global optic flow methods. Int J Comput Vis 61(3):211\u2013231","journal-title":"Int J Comput Vis"},{"key":"11022_CR3","doi-asserted-by":"crossref","unstructured":"Buch S, Escorcia V, Ghanem B et al. (2017) End-to-end, Single-Stream Temporal Action Detection in Untrimmed Videos in BMVC 2 p. 7","DOI":"10.5244\/C.31.93"},{"key":"11022_CR4","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. in proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"11022_CR5","unstructured":"Cheng Y, Li G, Chen H-B, et al. (2018) DEEPEYE: A Compact and Accurate Video Comprehension at Terminal Devices Compressed with Quantization and Tensorization. arXiv preprint arXiv:1805.07935"},{"key":"11022_CR6","doi-asserted-by":"crossref","unstructured":"Cherian A, Fernando B, Harandi M et al. (2017) Generalized rank pooling for activity recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 3222\u20133231","DOI":"10.1109\/CVPR.2017.172"},{"key":"11022_CR7","doi-asserted-by":"crossref","unstructured":"Ch\u00e9ron G, Laptev I, Schmid C (2015) P-cnn: Pose-based cnn features for action recognition. in Proceedings of the IEEE international conference on computer vision. p. 3218\u20133226","DOI":"10.1109\/ICCV.2015.368"},{"issue":"5","key":"11022_CR8","doi-asserted-by":"publisher","first-page":"1813","DOI":"10.1016\/j.patcog.2013.12.004","volume":"47","author":"J Cho","year":"2014","unstructured":"Cho J, Lee M, Chang HJ, Oh S (2014) Robust action recognition using local motion and group sparsity. Pattern Recogn 47(5):1813\u20131825","journal-title":"Pattern Recogn"},{"key":"11022_CR9","doi-asserted-by":"crossref","unstructured":"Choutas V, Weinzaepfel P, Revaud J et al. (2018) Potion: Pose motion representation for action recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 7024\u20137033","DOI":"10.1109\/CVPR.2018.00734"},{"key":"11022_CR10","doi-asserted-by":"crossref","unstructured":"Csurka G, Perronnin F (2010) Fisher vectors: Beyond bag-of-visual-words image representations. in International Conference on Computer Vision, Imaging and Computer Graphics. Springer p. 28\u201342","DOI":"10.1007\/978-3-642-25382-9_2"},{"key":"11022_CR11","unstructured":"Csurka G, Dance C, Fan L et al. (2004) Visual categorization with bags of keypoints. in Workshop on statistical learning in computer vision, ECCV. Prague.1 p. 1\u20132"},{"key":"11022_CR12","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection. in 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05). IEEE.1 p. 886\u2013893","DOI":"10.1109\/CVPR.2005.177"},{"key":"11022_CR13","doi-asserted-by":"crossref","unstructured":"Dalal N, Triggs B, Schmid C (2006) Human detection using oriented histograms of flow and appearance. in European conference on computer vision. Springer p. 428\u2013441","DOI":"10.1007\/11744047_33"},{"key":"11022_CR14","unstructured":"Diba A, Fayyaz M, Sharma V et al. (2017) Temporal 3d convnets: new architecture and transfer learning for video classification"},{"key":"11022_CR15","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S et al. (2015) Long-term recurrent convolutional networks for visual recognition and description. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"11022_CR16","doi-asserted-by":"crossref","unstructured":"Fan L, Huang W, Gan C et al. (2018) End-to-end learning of motion representation for video understanding. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 6016\u20136025","DOI":"10.1109\/CVPR.2018.00630"},{"key":"11022_CR17","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 1933-1941","DOI":"10.1109\/CVPR.2016.213"},{"key":"11022_CR18","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. in Advances in neural information processing systems. p. 3468\u20133476","DOI":"10.1109\/CVPR.2017.787"},{"key":"11022_CR19","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes RP (2017) Spatiotemporal multiplier networks for video action recognition. in 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). IEEE p. 7445\u20137454","DOI":"10.1109\/CVPR.2017.787"},{"key":"11022_CR20","doi-asserted-by":"crossref","unstructured":"Gammulle H, Denman S, Sridharan S et al. (2017) Two Stream LSTM: A Deep Fusion Framework for Human Action Recognition. in Applications of Computer Vision (WACV), 2017 IEEE Winter Conference on. IEEE p. 177\u2013186","DOI":"10.1109\/WACV.2017.27"},{"key":"11022_CR21","doi-asserted-by":"crossref","unstructured":"Gkioxari G, Malik J (2015) Finding action tubes. in Computer Vision and Pattern Recognition (CVPR), 2015 IEEE Conference on. IEEE p. 759\u2013768","DOI":"10.1109\/CVPR.2015.7298676"},{"key":"11022_CR22","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S et al. (2014) Spatial pyramid pooling in deep convolutional networks for visual recognition. in European conference on computer vision. Springer p. 346\u2013361","DOI":"10.1007\/978-3-319-10578-9_23"},{"issue":"1\u20133","key":"11022_CR23","doi-asserted-by":"publisher","first-page":"185","DOI":"10.1016\/0004-3702(81)90024-2","volume":"17","author":"BK Horn","year":"1981","unstructured":"Horn BK, Schunck BG (1981) Determining optical flow. Artif Intell 17(1\u20133):185\u2013203","journal-title":"Artif Intell"},{"key":"11022_CR24","doi-asserted-by":"crossref","unstructured":"Ilg E, Mayer N, Saikia T et al. (2017) Flownet 2.0: Evolution of optical flow estimation with deep networks. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 2462\u20132470","DOI":"10.1109\/CVPR.2017.179"},{"key":"11022_CR25","doi-asserted-by":"crossref","unstructured":"Iqbal A, Richard A, Kuehne H et al. (2017) Recurrent Residual Learning for Action Recognition. in German Conference on Pattern Recognition. Springer p. 126\u2013137","DOI":"10.1007\/978-3-319-66709-6_11"},{"key":"11022_CR26","doi-asserted-by":"crossref","unstructured":"Javidani A, Mahmoudi-Aznaveh A (2018) A unified method for first and third person action recognition. in Electrical Engineering (ICEE), Iranian Conference on. IEEE p. 1629-1633","DOI":"10.1109\/ICEE.2018.8472580"},{"key":"11022_CR27","doi-asserted-by":"crossref","unstructured":"J\u00e9gou H, Douze M, Schmid C et al. (2010) Aggregating local descriptors into a compact image representation. in 2010 IEEE computer society conference on computer vision and pattern recognition. IEEE p. 3304\u20133311","DOI":"10.1109\/CVPR.2010.5540039"},{"issue":"1","key":"11022_CR28","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. IEEE Trans Pattern Anal Mach Intell 35(1):221\u2013231","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"11022_CR29","doi-asserted-by":"crossref","unstructured":"Karpathy, A., G. Toderici, S. Shetty, et al. (2014) Large-scale video classification with convolutional neural networks. in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. p. 1725-1732","DOI":"10.1109\/CVPR.2014.223"},{"key":"11022_CR30","doi-asserted-by":"crossref","unstructured":"Klaser A, Marsza\u0142ek M, Schmid C (2008) A spatio-temporal descriptor based on 3d-gradients. in BMVC 2008-19th British Machine Vision Conference. British Machine Vision Association p. 275: 1\u201310","DOI":"10.5244\/C.22.99"},{"issue":"2\u20133","key":"11022_CR31","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":"11022_CR32","unstructured":"LeCun Y, Bengio Y (1995) Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks. Vol. 3361(10): p. 1995"},{"key":"11022_CR33","doi-asserted-by":"publisher","first-page":"41","DOI":"10.1016\/j.cviu.2017.10.011","volume":"166","author":"Z Li","year":"2018","unstructured":"Li Z, Gavrilyuk K, Gavves E, Jain M, Snoek CGM (2018) VideoLSTM convolves, attends and flows for action recognition. Comput Vis Image Underst 166:41\u201350","journal-title":"Comput Vis Image Underst"},{"key":"11022_CR34","doi-asserted-by":"crossref","unstructured":"Li Z, Gavrilyuk K, Gavves E et al. (2018) Videolstm convolves, attends and flows for action recognition. Vol. 166: p. 41\u201350","DOI":"10.1016\/j.cviu.2017.10.011"},{"key":"11022_CR35","doi-asserted-by":"crossref","unstructured":"Liu J, Luo J, Shah M (2009) Recognizing realistic actions from videos \u201cin the wild\u201d. in Computer vision and pattern recognition, 2009. CVPR 2009. IEEE conference on. IEEE p. 1996-2003","DOI":"10.1109\/CVPR.2009.5206744"},{"key":"11022_CR36","doi-asserted-by":"crossref","unstructured":"Liu J, Wang G, Hu P et al. (2017) Global context-aware attention LSTM networks for 3D action recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 1647-1656","DOI":"10.1109\/CVPR.2017.391"},{"key":"11022_CR37","doi-asserted-by":"crossref","unstructured":"Liu Z, Tian Y, Wang Z (2017) Improving human action recognitionby temporal attention. in 2017 IEEE International Conference on Image Processing (ICIP). IEEE p. 870\u2013874","DOI":"10.1109\/ICIP.2017.8296405"},{"key":"11022_CR38","doi-asserted-by":"crossref","unstructured":"Liu K, Liu W, Gan C et al. (2018) T-C3D: temporal convolutional 3d network for real-time action recognition. in Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12333"},{"issue":"2","key":"11022_CR39","doi-asserted-by":"publisher","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","volume":"60","author":"DG Lowe","year":"2004","unstructured":"Lowe DG (2004) Distinctive image features from scale-invariant keypoints. Int J Comput Vis 60(2):91\u2013110","journal-title":"Int J Comput Vis"},{"key":"11022_CR40","doi-asserted-by":"crossref","unstructured":"Nazir S, Yousaf MH, Velastin SA (2017) Feature Similarity and Frequency-Based Weighted Visual Words Codebook Learning Scheme for Human Action Recognition. in Pacific-Rim Symposium on Image and Video Technology. Springer p. 326\u2013336","DOI":"10.1007\/978-3-319-75786-5_27"},{"key":"11022_CR41","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 MH, Nebel J-C, Velastin SA (2018) A bag of expression framework for improved human action recognition. Pattern Recogn Lett 103:39\u201345","journal-title":"Pattern Recogn Lett"},{"key":"11022_CR42","doi-asserted-by":"publisher","first-page":"284","DOI":"10.1016\/j.compeleceng.2016.06.004","volume":"70","author":"CI Patel","year":"2018","unstructured":"Patel CI, Garg S, Zaveri T, Banerjee A, Patel R (2018) Human action recognition using fusion of features for unconstrained video sequences. Comput Electric Eng 70:284\u2013301","journal-title":"Comput Electric Eng"},{"key":"11022_CR43","doi-asserted-by":"crossref","unstructured":"Peng X, Schmid C (2016) Multi-region two-stream R-CNN for action detection. in European conference on computer vision. Springer p. 744\u2013759","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"11022_CR44","doi-asserted-by":"crossref","unstructured":"Peng X, Zou C, Qiao Y et al. (2014) Action recognition with stacked fisher vectors. in European Conference on Computer Vision. Springer p. 581\u2013595","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"11022_CR45","doi-asserted-by":"crossref","unstructured":"Piergiovanni A, Ryoo MS (2019) Representation flow for action recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 9945\u20139953","DOI":"10.1109\/CVPR.2019.01018"},{"key":"11022_CR46","doi-asserted-by":"crossref","unstructured":"Piergiovanni A, Fan C, Ryoo MS (2017) Learning latent sub-events in activity videos using temporal attention filters. in Proceedings of the 31st AAAI conference on artificial intelligence. in press","DOI":"10.1609\/aaai.v31i1.11240"},{"key":"11022_CR47","unstructured":"Ravanbakhsh M, Mousavi H, Rastegari M et al. (2015) Action Recognition with Image Based CNN Features. arXiv preprint arXiv:1512.03980"},{"key":"11022_CR48","doi-asserted-by":"crossref","unstructured":"Ryoo M, Matthies L (2016) Video-based convolutional neural networks for activity recognition from robot-centric videos. in SPIE Defense+ Security. International Society for Optics and Photonics p. 98370R-98370R-6","DOI":"10.1117\/12.2229531"},{"key":"11022_CR49","doi-asserted-by":"crossref","unstructured":"Ryoo MS, Rothrock B, Matthies L (2015) Pooled motion features for first-person videos. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 896\u2013904","DOI":"10.1109\/CVPR.2015.7298691"},{"key":"11022_CR50","doi-asserted-by":"crossref","unstructured":"Schuldt C, Laptev I, Caputo B (2004) Recognizing human actions: a local SVM approach. in Pattern Recognition, 2004. ICPR 2004. Proceedings of the 17th International Conference on. IEEE.3 p. 32\u201336","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"11022_CR51","doi-asserted-by":"crossref","unstructured":"Scovanner P, Ali S, Shah M (2007) A 3-dimensional sift descriptor and its application to action recognition. in Proceedings of the 15th ACM international conference on Multimedia. ACM p. 357\u2013360","DOI":"10.1145\/1291233.1291311"},{"key":"11022_CR52","unstructured":"Sharma S, Kiros R, Salakhutdinov R (2015) Action recognition using visual attention. arXiv preprint arXiv:1511.04119"},{"key":"11022_CR53","unstructured":"Simonyan K, Zisserman A (2014) Two-stream convolutional networks for action recognition in videos. in Advances in Neural Information Processing Systems. p. 568\u2013576"},{"key":"11022_CR54","doi-asserted-by":"crossref","unstructured":"Song S, Lan C, Xing J et al. (2017) An end-to-end spatio-temporal attention model for human action recognition from skeleton data. in Thirty-first AAAI conference on artificial intelligence.","DOI":"10.1609\/aaai.v31i1.11212"},{"key":"11022_CR55","doi-asserted-by":"crossref","unstructured":"Sun S, Kuang Z, Sheng L et al. (2018) Optical flow guided feature: A fast and robust motion representation for video action recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 1390\u20131399","DOI":"10.1109\/CVPR.2018.00151"},{"key":"11022_CR56","doi-asserted-by":"crossref","unstructured":"Sun C, Shrivastava A, Vondrick C et al. (2019) Relational action forecasting. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 273\u2013283","DOI":"10.1109\/CVPR.2019.00036"},{"key":"11022_CR57","unstructured":"Tran D, Bourdev L, Fergus R et al. (2014) C3D: generic features for video analysis. CoRR, abs\/1412.0767, Vol. 2: p. 7"},{"key":"11022_CR58","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R et al. (2015) Learning spatiotemporal features with 3d convolutional networks. in 2015 IEEE International Conference on Computer Vision (ICCV). IEEE p. 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"11022_CR59","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L et al. (2018) A closer look at spatiotemporal convolutions for action recognition. in Proceedings of the IEEE conference on Computer Vision and Pattern Recognition. p. 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"key":"11022_CR60","doi-asserted-by":"crossref","unstructured":"Wang H, Schmid C (2013) Action recognition with improved trajectories. in Proceedings of the IEEE International Conference on Computer Vision. p. 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"11022_CR61","doi-asserted-by":"crossref","unstructured":"Wang H, Kl\u00e4ser A, Schmid C et al. (2011) Action recognition by dense trajectories. in Computer Vision and Pattern Recognition (CVPR), 2011 IEEE Conference on. IEEE p. 3169\u20133176","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"11022_CR62","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-convolutional descriptors. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"11022_CR63","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z et al. (2016) Temporal segment networks: Towards good practices for deep action recognition. in European conference on computer vision. Springer p. 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"11022_CR64","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1016\/j.neucom.2017.08.063","volume":"275","author":"X Wang","year":"2018","unstructured":"Wang X, Gao L, Song J, Zhen X, Sebe N, Shen HT (2018) Deep appearance and motion learning for egocentric activity recognition. Neurocomputing 275:438\u2013447","journal-title":"Neurocomputing"},{"key":"11022_CR65","doi-asserted-by":"crossref","unstructured":"Wang L, Li W, Li W et al. (2018) Appearance-and-relation networks for video classification. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 1430\u20131439","DOI":"10.1109\/CVPR.2018.00155"},{"key":"11022_CR66","unstructured":"Xie S, Sun C, Huang J et al. (2017) Rethinking spatiotemporal feature learning for video understanding. Vol. 1(2): p. 5"},{"key":"11022_CR67","doi-asserted-by":"crossref","unstructured":"Yan A, Wang Y, Li Z et al. (2019) PA3D: Pose-action 3D machine for video recognition. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 7922\u20137931","DOI":"10.1109\/CVPR.2019.00811"},{"key":"11022_CR68","doi-asserted-by":"crossref","unstructured":"Yang K, Qiao P, Li D et al. (2019) If-ttn: Information fused temporal transformation network for video action recognition. arXiv preprint arXiv:1902.09928","DOI":"10.1109\/ICASSP40776.2020.9053394"},{"key":"11022_CR69","doi-asserted-by":"crossref","unstructured":"Yue-Hei Ng J, Hausknecht M, Vijayanarasimhan S et al. (2015) Beyond short snippets: Deep networks for video classification. in Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. p. 4694\u20134702","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"11022_CR70","doi-asserted-by":"crossref","unstructured":"Zhang P, Xue J, Lan C et al. (2018) Adding attentiveness to the neurons in recurrent neural networks. in Proceedings of the European Conference on Computer Vision (ECCV). p. 135\u2013151","DOI":"10.1007\/978-3-030-01240-3_9"},{"key":"11022_CR71","doi-asserted-by":"crossref","unstructured":"Zhou Y, Sun X, Zha Z-J et al. (2018) Mict: Mixed 3d\/2d convolutional tube for human action recognition. in Proceedings of the IEEE conference on computer vision and pattern recognition. p. 449\u2013458","DOI":"10.1109\/CVPR.2018.00054"},{"key":"11022_CR72","doi-asserted-by":"crossref","unstructured":"Zhu Y, Lan Z, Newsam S et al. (2018) Hidden two-stream convolutional networks for action recognition. in Asian Conference on Computer Vision. Springer p. 363\u2013378","DOI":"10.1007\/978-3-030-20893-6_23"},{"key":"11022_CR73","doi-asserted-by":"crossref","unstructured":"Zolfaghari M, Oliveira GL, Sedaghat N et al. (2017) Chained multi-stream networks exploiting pose, motion, and appearance for action classification and detection. in Proceedings of the IEEE International Conference on Computer Vision. p. 2904\u20132913","DOI":"10.1109\/ICCV.2017.316"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11022-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11022-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,27]],"date-time":"2022-12-27T14:23:15Z","timestamp":1672150995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11022-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,17]]},"references-count":73,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,1]]}},"alternative-id":["11022"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11022-8","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,17]]},"assertion":[{"value":"1 June 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 February 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 May 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"17 May 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}