A Dual Stream Model for Activity Recognition: Exploiting Residual- CNN with Transfer Learning

References

• Andrew Z, Joao C, Karen S, Will K, Brian Z, Chloe H, Sudheendra V, Fabio V, Tim G, Trevor B. 2017. The kinetics human action video dataset. arXiv:1705 06950 [Cs CV]
   Google Scholar
• Baccouche M, Mamalet F, Wolf C, Garcia C, Baskurt A. 2011. sequential deep learning for human action recognition. In: Human behavior understanding. p. 29–39.
   Google Scholar
• Bobick AF, Davis JW. 2001. The recognition of human movement using temporal templates BT - Pattern analysis and machine intelligence, IEEE transactions on. IEEE Trans Pattern Anal Mach Intell. 23(3):257–267.
   Google Scholar
• Chaudhary S, Murala S. 2018. “TSNet: deep network for human action recognition in Hazy videos.” 2018 IEEE International Conference on Systems, Man, and Cybernetics (SMC), Miyazaki, Japan, 2018, 3981–3986.
   Google Scholar
• Feichtenhofer C, Pinz A, Zisserman A, “convolutional two-stream network fusion for video action recognition,” 2016.
   Google Scholar
• 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):221–231.
   Google Scholar
• Karpathy A, Toderici G, Shetty S, Leung T, Sukthankar R, Li FF. 2014. “Large-Scale Video Classification with Convolutional Neural Networks,” 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 2014, 1725–1732.
   Google Scholar
• Ke Q, An S, Bennamoun M, Sohel F, Boussaid F. 2016. SkeletonNet : mining Deep Part Features for 3D Action Recognition. Proc in IEEE Signal Processing Letters,  24(6):731–735, 2017.
   Google Scholar
• Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T. 2011. “HMDB: A large video database for human motion recognition.” 2011 International Conference on Computer Vision, Barcelona, 2011, 2556–2563.
   Google Scholar
• Laptev I. 2005. On space-time interest points. Int J Comput Vis. 64(2–3):107–123.
   Google Scholar
• Li C., Q. Zhong, and D. Xie, 2017. “Skeleton-Based Action Recognition with Convolutional Neural Networks.” July, pp. 597–600.
   Google Scholar
• Li -F-F, Dong W, Deng J, Li K, Socher R, Li-Jia L. 2009. ImageNet: A large-scale hierarchical image database. 2009 IEEE Conf Comput Vis Pattern Recognit. 248–255.
   Google Scholar
• Liu J, Luo J, Shah M, “Recognizing realistic actions from videos ́in the Wild,” 2009 IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. Work. CVPR Work. vol. 2009 IEEE, Miami, Florida City USA, pp. 1996–2003, 2009.
   Google Scholar
• O’Reilly RC, Wyatte D, Herd S, Mingus B, Jilk DJ. 2013. Deep Residual Learning for Image Recognition Kaiming. Front Psychol. 4(APR):428–429.
   Google Scholar
• Poppe R. 2010. A survey on vision-based human action recognition. Image Vis Comput. 28(6):976–990.
   Google Scholar
• Shahroudy A, Liu J, Ng -T-T, Wang G, “NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis,” in In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, Caesars Palace, Las Vegas, Nevada, United States, 2016, pp. 1010–1019.
   Google Scholar
• Shamsolmoali P, Zareapoor M, Jiao S. 2020. AMIL : adversarial Multi-instance Learning for Human Pose Estimation. ACM Trans. Multimedia Comput. Commun. Appl. 16(1):1–23.
   Google Scholar
• Simonyan K, Zisserman A. 2014. Two-Stream Convolutional Networks for Action Recognition in Videos. In Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 1 (NIPS’14). MIT Press, Cambridge, MA, USA, 568–576.
   Google Scholar
• Singh R, Dhillon JK, Kushwaha AKS, Srivastava R. 2018. Depth based enlarged temporal dimension of 3D deep convolutional network for activity recognition. Multimed Tools Appl. 78:30599–30614.
   Google Scholar
• Singh R, Khurana R, Kumar A, Kushwaha S, Srivastava R. 2020. Combining CNN streams of dynamic image and depth data for action recognition. Multimedia Systems Volume. 26:313–322.
   Google Scholar
• Soomro K, Zamir AR, Shah M, “UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild,” November, 2012.
   Google Scholar
• Szegedy C, Wei L, Yangqing J, Pierre S, Scott R, Dragomir A, Dumitru E, Vincent V, Andrew R. 2015. Going deeper with convolutions. Proc IEEE Comput Soc Conf Comput Vis Pattern Recognit. 07–12–June:1–9
   Google Scholar
• Taylor GW, Fergus R, LeCun Y, Bregler C. 2010. Convolutional learning of spatio-temporal features. Lect Notes Comput Sci (Including Subser Lect Notes Artif Intell Lect Notes Bioinformatics). 6316 LNCS(. PART 6):140–153.
   Google Scholar
• Tran D, Bourdev L, Fergus R, Torresani L, Paluri M. 2015. Learning spatiotemporal features with 3D convolutional networks. Proc IEEE Int Conf Comput Vis. 2015(Inter):4489–4497.
   Google Scholar
• Varol G, Laptev I, Schmid C. 2016. in IEEE Transactions on Pattern Analysis and Machine Intelligence. arXiv Prepr arXiv1604 04494. 1510–1517.
   Google Scholar
• Wang J, Cherian A, Porikli F. 2017. Ordered pooling of optical flow sequences for action recognition. 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), Santa Rosa, CA. 168–176
   Google Scholar
• Wang P, Li W, Gao Z, Zhang J, Tang C, Ogunbona PO. 2016. Action Recognition from Depth Maps Using Deep Convolutional Neural Networks. IEEE Trans Human-Machine Syst. 46(4):498–509.
   Google Scholar
• Willems G, Tuytelaars T, Van Gool L. 2008. An Efficient Dense and Scale-Invariant Spatio-Temporal Interest Point Detector. Proc Lecture Notes in Computer Science, Springer, Berlin, Heidelberg. IEEE Int Conf Comput Vis. 5503:2923–2932.
   Google Scholar
• Zolfaghari M, Oliveira GL, Sedaghat N, Brox T. 2017. Chained Multi-stream Networks Exploiting Pose, Motion, and Appearance for Action Classification and Detection. Proc IEEE Int Conf Comput Vis. 2017–Octob(2):2923–2932.
   Google Scholar