Abstract
Human action recognition aims to classify trimmed videos based on the action being performed by one or more agents. It can be applied to a large variety of tasks, such as surveillance systems, intelligent homes, health monitoring, and human-computer interaction. Despite the significant progress achieved through image-based deep networks, video understanding still faces challenges in modeling spatiotemporal relations. The inclusion of temporal information in the network may lead to significant growth in the training cost. To address this issue, we explore complementary handcrafted features to feed pre-trained two-dimensional (2D) networks in a multi-stream fashion. In addition to the commonly used RGB and optical flow streams, we propose the use of a stream based on visual rhythm images that encode long-term information. Previous works have shown that either RGB or optical flow streams may benefit from pre-training on ImageNet since they maintain a certain level of object shape. The visual rhythm, on the other hand, harshly deforms the silhouettes of the actors and objects. Therefore, we develop a different pre-training procedure for the latter stream using visual rhythm images extracted from a large and challenging video dataset, the Kinetics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
H. Bilen, B. Fernando, E. Gavves, A. Vedaldi, Action recognition with dynamic image networks. IEEE Trans. Pattern Anal. Mach. Intell. 40(12), 2799–2813 (2018)
J.Y. Bouguet, Pyramidal implementation of the affine lucas kanade feature tracker description of the algorithm. Intel Corp. 5(1–10), 4 (2001)
J. Carreira, A. Zisserman, Quo vadis, action recognition? a new model and the kinetics dataset, in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 4724–4733
K. Chatfield, K. Simonyan, A. Vedaldi, A. Zisserman, Return of the devil in the details: delving deep into convolutional nets (2014), pp. 1–11, arXiv:14053531
V. Choutas, P. Weinzaepfel, J. Revaud, C. Schmid, PoTion: pose motion representation for action recognition, in IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 7024–7033
D.T. Concha, H. de Almeida Maia, H. Pedrini, H. Tacon, A. de Souza Brito, H. de Lima Chaves, M.B. Vieira Multi-stream convolutional neural networks for action recognition in video sequences based on adaptive visual rhythms, in IEEE International Conference on Machine Learning and Applications (IEEE, 2018), pp. 473–480
I. Gori, J.K. Aggarwal, L. Matthies, M.S. Ryoo, Multitype activity recognition in robot-centric scenarios. IEEE Robot. Autom. Lett. 1(1), 593–600 (2016)
K. He, X. Zhang, S. Ren, J. Sun, Deep residual learning for image recognition, in IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 770–778
S. Ji, W. Xu, M. Yang, K. Yu, 3D convolutional neural networks for human action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 35(1), 221–231 (2013)
R. Kahani, A. Talebpour, A. Mahmoudi-Aznaveh, A correlation based feature representation for first-person activity recognition. Multimed. Tools Appl. 78(15), 21673–21694 (2019)
A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, L. Fei-Fei, Large-scale video classification with convolutional neural networks, in IEEE Conference on Computer Vision and Pattern Recognition (2014), pp. 1725–1732
W. Kay, J. Carreira, K. Simonyan, B. Zhang, C. Hillier, S. Vijayanarasimhan, F. Viola, T. Green, T. Back, P. Natsev, M. Suleyman, A. Zisserman, The kinetics human action video dataset (2017), pp. 1–22, arXiv:170506950
H. Kim, J. Lee, J.H. Yang, S. Sull, W.M. Kim, S.M.H. Song, Visual rhythm and shot verification. Multimed. Tools Appl. 15(3), 227–245 (2001)
H. Kuehne, H. Jhuang, R. Stiefelhagen, T. Serre, HMDB51: a large video database for human motion recognition, High Performance Computing in Science and Engineering (Springer, Berlin, 2013), pp. 571–582
D. Li, T. Yao, L. Duan, T. Mei, Y. Rui, Unified spatio-temporal attention networks for action recognition in videos. IEEE Trans. Multimed. 416–428 (2018)
J.Y.H. Ng, M. Hausknecht, S. Vijayanarasimhan, O. Vinyals, R. Monga, G. Toderici, Beyond short snippets: deep networks for video classification, in IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 4694–4702
C.W. Ngo, T.C. Pong, R.T. Chin, Camera break detection by partitioning of 2D spatio-temporal images in MPEG domain, in IEEE International Conference on Multimedia Computing and Systems, vol. 1 (IEEE, 1999), pp. 750–755
X. Peng, L. Wang, X. Wang, Y. Qiao, Bag of visual words and fusion methods for action recognition: comprehensive study and good practice. Comput. Vis. Image Underst. 150, 109–125 (2016)
H. Rahmani, A. Mian, M. Shah, Learning a deep model for human action recognition from novel viewpoints. IEEE Trans. Pattern Anal. Mach. Intell. 40(3), 667–681 (2018)
M. Ravanbakhsh, H. Mousavi, M. Rastegari, V. Murino, L.S. Davis, Action recognition with image based CNN features (2015), pp. 1–10, arXiv:151203980
O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, L. Fei-Fei, ImageNet large scale visual recognition challenge. Int. J. Comput. Vis. 115(3), 211–252 (2015)
M.S. Ryoo, L. Matthies, First-person activity recognition: feature, temporal structure, and prediction. Int. J. Comput. Vis. 119(3), 307–328 (2016)
J. Shi, C. Tomasi, Good features to track, in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 1994), pp. 593–600
K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, in Advances in Neural Information Processing Systems (2014), pp. 568–576
K. Simonyan, A. Zisserman, Very deep convolutional networks for large-scale image recognition, in International Conference on Learning Representations (2015), pp. 1–14
K. Soomro, A.R. Zamir, M. Shah, UCF101: a dataset of 101 human actions classes from videos in the wild (2012), pp. 1–7, arXiv:12120402
M.R. Souza, Digital video stabilization: algorithms and evaluation. Master’s thesis, Institute of Computing, University of Campinas, Campinas, Brazil, 2018
L. Sun, K. Jia, K. Chen, D.Y. Yeung, B.E. Shi, S. Savarese, Lattice long short-term memory for human action recognition, in IEEE International Conference on Computer Vision (2017), pp. 2147–2156
S. Sun, Z. Kuang, L. Sheng, W. Ouyang, W. Zhang, Optical flow guided feature: a fast and robust motion representation for video action recognition, in IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 1390–1399
C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, A. Rabinovich, Going deeper with convolutions, in IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 1–12
C. Szegedy, V. Vanhoucke, S. Ioffe, J. Shlens, Z. Wojna, Rethinking the inception architecture for computer vision, in IEEE Conference on Computer Vision and Pattern Recognition (2016), pp. 2818–2826
B.S. Torres, H. Pedrini, Detection of complex video events through visual rhythm. Vis. Comput. 1–21 (2016)
D. Tran, H. Wang, L. Torresani, J. Ray, Y. LeCun, M. Paluri, A closer look at spatiotemporal convolutions for action recognition, in IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 6450–6459
Z. Tu, W. Xie, J. Dauwels, B. Li, J. Yuan, Semantic cues enhanced multi-modality multi-stream CNN for action recognition. IEEE Trans. Circuits Syst. Video Technol. 29(5), 1423–1437 (2018)
G. Varol, I. Laptev, C. Schmid, Long-term temporal convolutions for action recognition. IEEE Trans. Pattern Anal. Mach. Intell. 40(6), 1510–1517 (2018)
L. Wang, Y. Qiao, X. Tang, Action recognition with trajectory-pooled deep-convolutional descriptors, in IEEE Conference on Computer Vision and Pattern Recognition (2015), pp. 4305–4314
L. Wang, Y. Xiong, Z. Wang, Y. Qiao, Towards good practices for very deep two-stream convnets (2015), pp. 1–5, arXiv:150702159
L. Wang, Y. Xiong, Z. Wang, Y. Qiao, D. Lin, X. Tang, L. Van Gool, Temporal segment networks: towards good practices for deep action recognition, in European Conference on Computer Vision (Springer, 2016), pp. 20–36
Y. Wang, M. Long, J. Wang, P.S. Yu, Spatiotemporal pyramid network for video action recognition, in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2017), pp. 2097–2106
H. Wang, Y. Yang, E. Yang, C. Deng, Exploring hybrid spatio-temporal convolutional networks for human action recognition. Multimed. Tools Appl. 76(13), 15065–15081 (2017)
J. Wang, A. Cherian, F. Porikli, S. Gould, Video representation learning using discriminative pooling, in IEEE Conference on Computer Vision and Pattern Recognition (2018), pp. 1149–1158
M.A. Wani, F.A. Bhat, S. Afzal, A.I. Khan, Advances in Deep Learning, vol. 57 (Springer, Berlin, 2020)
H. Yang, C. Yuan, B. Li, Y. Du, J. Xing, W. Hu, S.J. Maybank, Asymmetric 3D convolutional neural networks for action recognition. Pattern Recognit. 85, 1–12 (2019)
W. Zhu, J. Hu, G. Sun, X. Cao, Y. Qiao, A key volume mining deep framework for action recognition, in IEEE Conference on Computer Vision and Pattern Recognition (IEEE, 2016), pp. 1991–1999
J. Zhu, Z. Zhu, W. Zou, End-to-end video-level representation learning for action recognition, in 24th International Conference on Pattern Recognition (IEEE, 2018), pp. 645–650
Y. Zhu, PyTorch implementation of popular two-stream frameworks for video action recognition (2019), https://github.com/bryanyzhu/two-stream-pytorch
Acknowledgements
The authors thank FAPESP (grants #2017/09160-1 and #2017/12646-3), CNPq (grant #305169/2015-7), CAPES and FAPEMIG for their financial support. The authors are also grateful to NVIDIA for the donation of a GPU as part of the GPU Grant Program.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2020 Springer Nature Singapore Pte Ltd.
About this chapter
Cite this chapter
de Almeida Maia, H. et al. (2020). Action Recognition in Videos Using Multi-stream Convolutional Neural Networks. In: Wani, M., Kantardzic, M., Sayed-Mouchaweh, M. (eds) Deep Learning Applications. Advances in Intelligent Systems and Computing, vol 1098. Springer, Singapore. https://doi.org/10.1007/978-981-15-1816-4_6
Download citation
DOI: https://doi.org/10.1007/978-981-15-1816-4_6
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-15-1815-7
Online ISBN: 978-981-15-1816-4
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)