{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T05:05:44Z","timestamp":1769576744492,"version":"3.49.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"29","license":[{"start":{"date-parts":[[2021,8,26]],"date-time":"2021-08-26T00:00:00Z","timestamp":1629936000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,8,26]],"date-time":"2021-08-26T00:00:00Z","timestamp":1629936000000},"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":[[2022,12]]},"DOI":"10.1007\/s11042-021-11220-4","type":"journal-article","created":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:25:58Z","timestamp":1630023958000},"page":"42117-42129","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":19,"title":["Deep convolutional neural model for human activities recognition in a sequence of video by combining multiple CNN streams"],"prefix":"10.1007","volume":"81","author":[{"given":"Neeraj","family":"Varshney","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Brijesh","family":"Bakariya","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2021,8,26]]},"reference":[{"key":"11220_CR1","doi-asserted-by":"publisher","unstructured":"Bhagat C, Kushwaha AKR (2019) Delving Deeper with Dual-Stream CNN for Activity Recognition: Select Proceedings of IC3E 2018. https:\/\/doi.org\/10.1007\/978-981-13-2685-1_32","DOI":"10.1007\/978-981-13-2685-1_32"},{"key":"11220_CR2","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 the IEEE Conference on Computer Vision and Pattern Recognition, pp 3034\u20133042","DOI":"10.1109\/CVPR.2016.331"},{"key":"11220_CR3","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L, Li K, Li F (2009) ImageNet: a large-scale hierarchical image database. In: CVPR, pp 248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"11220_CR4","doi-asserted-by":"crossref","unstructured":"Donahue J, Anne Hendricks L, Guadarrama S, Rohrbach M, Venugopalan S, Saenko K, Darrell T (2015) Long-term recurrent convolutional networks for visual recognition and description. In\u00a0Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2625\u20132634","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"11220_CR5","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, pp 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"key":"11220_CR6","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Wildes R (2016) Spatiotemporal residual networks for video action recognition. In: Proceedings of the Advances in Neural Information pro- cessing systems, pp 3468\u20133476","DOI":"10.1109\/CVPR.2017.787"},{"key":"11220_CR7","doi-asserted-by":"crossref","unstructured":"Girdhar R, Deva R, Abhinav G, Josef S, Bryan R (2017) Actionvlad: Learning spatio-temporal aggregation for action classification. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 971\u2013980","DOI":"10.1109\/CVPR.2017.337"},{"key":"11220_CR8","doi-asserted-by":"crossref","unstructured":"Karpathy A, George T, Sanketh S, Thomas L, Rahul S, Fei-Fei L (2014) Large-scale video classification with convolutional neural networks. In\u00a0Proceedings of the IEEE conference on Computer Vision and Pattern Recognition, pp 1725\u20131732","DOI":"10.1109\/CVPR.2014.223"},{"key":"11220_CR9","doi-asserted-by":"crossref","unstructured":"Khurana R, Kushwaha AKS (2019) Delving Deeper with Dual-Stream CNN for Activity Recognition. In\u00a0Recent Trends in Communication, Computing, and Electronics, pp 333\u2013342. Springer, Singapore","DOI":"10.1007\/978-981-13-2685-1_32"},{"key":"11220_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.04.035","author":"P Khaire","year":"2018","unstructured":"Khaire P, Kumar P, Imran J (2018) Combining CNN streams of RGB-D and skeletal data for human activity recognition. Pattern Recogn Lett. https:\/\/doi.org\/10.1016\/j.patrec.2018.04.035","journal-title":"Pattern Recogn Lett"},{"key":"11220_CR11","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. ICCV","DOI":"10.1109\/ICCV.2011.6126543"},{"issue":"4","key":"11220_CR12","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/s00530-016-0505-x","volume":"23","author":"AKS Kushwaha","year":"2017","unstructured":"Kushwaha AKS, Srivastava S, Srivastava R (2017) Multi-view human activity recognition based on silhouette and uniform rotation invariant local binary patterns. Multimedia Syst 23(4):451\u2013467","journal-title":"Multimedia Syst"},{"key":"11220_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2016.03.011","author":"D Roy","year":"2016","unstructured":"Roy D, Srinivas M, Chalavadi KM (2016) Sparsity-inducing dictionaries for effective action classification. Pattern Recogn. https:\/\/doi.org\/10.1016\/j.patcog.2016.03.011","journal-title":"Pattern Recogn"},{"key":"11220_CR14","unstructured":"Simonyan K, Andrew Z (2014) Two-stream convolutional networks for action recognition in videos. In Advances in neural information processing systems, pp 568\u2013576"},{"issue":"12","key":"11220_CR15","doi-asserted-by":"publisher","first-page":"17165","DOI":"10.1007\/s11042-018-7108-9","volume":"78","author":"R Singh","year":"2019","unstructured":"Singh R, Kushwaha AKS, Srivastava R (2019) Multi-view recognition system for human activity based on multiple features for video surveillance system. Multimedia Tools Appl 78(12):17165\u201317196","journal-title":"Multimedia Tools Appl"},{"key":"11220_CR16","unstructured":"Soomro K, Zamir AR, Shah M (2012) UCF101: A dataset of 101 human actions classes from videos in the wild. arXiv preprint https:\/\/arXiv:1212.0402"},{"key":"11220_CR17","doi-asserted-by":"crossref","unstructured":"Sun L, Kui J, Dit-Yan Y, Bertram ES (2015) Human action recognition using factorized spatio-temporal convolutional networks. In\u00a0Proceedings of the IEEE international conference on computer vision, pp 4597\u20134605","DOI":"10.1109\/ICCV.2015.522"},{"issue":"8","key":"11220_CR18","doi-asserted-by":"publisher","first-page":"1897","DOI":"10.1007\/s11760-014-0677-9","volume":"9","author":"D-M Tsai","year":"2015","unstructured":"Tsai D-M, Chiu W-Y, Lee M-H (2015) Optical flow-motion history image (OF-MHI) for action recognition. SIViP 9(8):1897\u20131906.\u00a0https:\/\/github.com\/tomar840\/two-stream-fusion-for-action-recognition-in-videos","journal-title":"SIViP"},{"key":"11220_CR19","doi-asserted-by":"crossref","unstructured":"Tran D, Lubomir B, Rob F, Lorenzo T, Manohar P (2015) Learning spatiotemporal features with 3d convolutional networks. In\u00a0Proceedings of the IEEE international conference on computer vision, pp 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"key":"11220_CR20","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, Li B, Yuan J (2018) Multi-stream CNN: learning representations based on human related regions for action recognition. Pattern Recogn 79:32\u201343","journal-title":"Pattern Recogn"},{"key":"11220_CR21","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, pp 3551\u20133558","DOI":"10.1109\/ICCV.2013.441"},{"key":"11220_CR22","doi-asserted-by":"crossref","unstructured":"Wang J, Cherian A, Porikli F, Gould S (2018) Video representation learning using discriminative pooling. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Salt Lake City, UT, USA, 18\u201322 pp 1149\u20131158","DOI":"10.1109\/CVPR.2018.00126"},{"key":"11220_CR23","doi-asserted-by":"publisher","first-page":"33","DOI":"10.1016\/j.patrec.2017.04.004","volume":"92","author":"L Wang","year":"2017","unstructured":"Wang L, Ge L, Li R, Fang Y (2017) Three-stream CNNs for action recognition. Pattern Recogn Lett 92:33\u201340","journal-title":"Pattern Recogn Lett"},{"key":"11220_CR24","doi-asserted-by":"crossref","unstructured":"Wang L, Qiao Y, Tang X (2015) Action recognition with trajectory-pooled deep-con- volutional descriptors. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 4305\u20134314","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"11220_CR25","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: Towards good practices for deep action recognition. In\u00a0European conference on computer vision, pp 20\u201336. Springer, Cham.\u00a0https:\/\/towardsdatascience.com\/gentle-dive-into-math-behind-convolutional-neural-networks-9a07dd44cf9","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"11220_CR26","doi-asserted-by":"crossref","unstructured":"Wang L, Xiong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L (2016) Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision, Springer, pp 20\u201336","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"11220_CR27","first-page":"363","volume-title":"Asian Conference on Computer Vision","author":"Y Zhu","year":"2018","unstructured":"Zhu Y, Zhenzhong L, Shawn N, Alexander H (2018) Hidden two-stream convolutional networks for action recognition. Asian Conference on Computer Vision. Springer, Cham, pp 363\u2013378"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11220-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-021-11220-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-021-11220-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,26]],"date-time":"2022-11-26T22:40:31Z","timestamp":1669502431000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-021-11220-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,26]]},"references-count":27,"journal-issue":{"issue":"29","published-print":{"date-parts":[[2022,12]]}},"alternative-id":["11220"],"URL":"https:\/\/doi.org\/10.1007\/s11042-021-11220-4","relation":{},"ISSN":["1380-7501","1573-7721"],"issn-type":[{"value":"1380-7501","type":"print"},{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,26]]},"assertion":[{"value":"9 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 June 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 July 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 August 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}