Abstract
Temporal action proposal generation aims to output the starting and ending times of each potential action for long videos and often suffers from high computation cost. To address the issue, we propose a new temporal convolution network called Multipath Temporal ConvNet (MTCN). In our work, one novel high performance ring parallel architecture based is further introduced into temporal action proposal generation in order to respond to the requirements of large memory occupation and a large number of videos. Remarkably, the total data transmission is reduced by adding a connection between multiple-computing load in the newly developed architecture. Compared to the traditional Parameter Server architecture, our parallel architecture has higher efficiency on temporal action detection tasks with multiple GPUs. We conduct experiments on ActivityNet-1.3 and THUMOS14, where our method outperforms-other state-of-art temporal action detection methods with high recall and high temporal precision. In addition, a time metric is further proposed here to evaluate the speed performancein the distributed training process.
Similar content being viewed by others
References
Muhammad K, Hamza R, Ahmad J, Lloret J, Wang H, Baik S. Secure surveillance framework for IoT systems using probabilistic image encryption. IEEE Transactions on Industrial Informatics, 2018, 14(8): 3679–3689
Sajjad M, Haq I U, Lloret J, Ding W, Muhammad K. Robust image hashing based efficient authentication for smart industrial environment. IEEE Transactions on Industrial Informatics, 2019, 15(12): 6541–6550
Wang T, Qiao M, Lin Z, Li C, Snoussi H, Liu Z, Choi C. Generative neural networks for anomaly detection in crowded scenes. IEEE Transactions on Information Forensics and Security, 2018, 14(5): 1390–1399
Muhammad K, Khan S, Palade V, Mehmood I, De Albuquerque V H. Edge intelligence-assisted smoke detection in foggy surveillance environments. IEEE Transactions on Industrial Informatics, 2019, 16(2): 1067–1075
Wang T, Miao Z, Chen Y, Zhou Y, Shan G, Snoussi H. Aed-net: an abnormal event detection network. Engineering, 2019, 5(5): 930–939
Caba Heilbron F, Escorcia V, Ghanem B, Carlos Niebles J. Activitynet: a large-scale video benchmark for human activity understanding. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2015, 961–970
Jiang Y G, Liu J, Zamir A. R, Toderici G, Laptev I, Shah M, Sukthankar R. Thumos challenge: action recognition with a large number of classes. 2014
Lin T, Zhao X, Su H, Wang C, Yang M. BSN: boundary sensitive network for temporal action proposal generation. In: Proceedings of the European Conference on Computer Vision. 2018, 3–19
Buch S, Escorcia V, Shen C, Ghanem B, Carlos Niebles J. SST: singlestream temporal action proposals. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2017, 2911–2920
Caba Heilbron F, Carlos Niebles J, Ghanem B. Fast temporal activity proposals for efficient detection of human actions in untrimmed videos. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1914–1923
Escorcia V, Heilbron F. C, Niebles J. C, Ghanem B. Daps: deep action proposals for action understanding. In: Proceedings of the European Conference on Computer Vision. 2016, 768–784
Shou Z, Wang D, Chang SF. Temporal action localization in untrimmed videos via multi-stage cnns. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1049–1058
Dean J, Corrado G, Monga R, Chen K, Devin M, Mao M, Senior A, Tucker P, Yang K, Le Q V, et al. Large scale distributed deep networks. In: Proceedings of the Advances in Neural Information Processing Systems. 2012, 1223–1231
Karaman S, Seidenari L, Del Bimbo A. Fast saliency based pooling of fisher encoded dense trajectories. In: Proceedings of the European Conference on Computer Vision THUMOS Workshop. 2014
Wang L, Qiao Y, Tang X. Action recognition and detection by combining motion and appearance features. THUMOS14 Action Recognition Challenge, 2014, 1(2): 2
Wang T, Chen Y, Lin Z, Zhu A, Li Y, Snoussi H, Wang H. Recapnet: action proposal generation mimicking human cognitive process. IEEE Transactions on Cybernetics, 2020, DOI: https://doi.org/10.1109/TCYB.2020.2965196
Gao J, Yang Z, Chen K, Sun C, Nevatia R. Turn tap: temporal unit regression network for temporal action proposals. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 3628–3636
Zhao Y, **ong Y, Wang L, Wu Z, Tang X, Lin D. Temporal action detection with structured segment networks. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 2914–2923
Jian M, Lam K M, Dong J, Shen L. Visual-patch-attention-aware saliency detection. IEEE Transactions on Cybernetics, 2014, 45(8): 1575–1586
Jian M, Qi Q, Dong J, Yin Y, Lam K M. Integrating qdwd with pattern distinctness and local contrast for underwater saliency detection. Journal of Visual Communication and Image Representation, 2018, 53: 31–41
Jian M, Qi Q, Yu H, Dong J, Cui C, Nie X, Zhang H, Yin Y, Lam K M. The extended marine underwater environment database and baseline evaluations. Applied Soft Computing, 2019, 80: 425–437
Wang T, Chen Y, Lv H, Teng J, Snoussi H, Tao F. Online detection of action start via soft computing for smart city. IEEE Transactions on Industrial Informatics, 2020, 17(1): 524–533
Wang H, Kläser A, Schmid C, Liu C L. Action recognition by dense trajectories. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2011, 3169–3176
Feichtenhofer C, Pinz A, Zisserman A. Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 1933–1941
Wang L, **ong Y, Wang Z, Qiao Y, Lin D, Tang X, Van Gool L. Temporal segment networks: towards good practices for deep action recognition. In: Proceedings of the European Conference on Computer Vision. 2016, 20–36
Tran D, Bourdev L, Fergus R, Torresani L, Paluri M. Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE International Conference on Computer Vision. 2015, 4489–4497
Dean J, Ghemawat S. Mapreduce: simplified data processing on large clusters. Communications of the ACM, 2008, 51(1): 107–113
Low Y, Bickson D, Gonzalez J, Guestrin C, Kyrola A, Hellerstein J M. Distributed graphlab: a framework for machine learning and data mining in the cloud. Proceedings of the VLDB Endowment, 2012, 5(8): 716–727
Hu J, Shen L, Sun G. Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2018, 7132–7141
Simonyan K, Zisserman A. Two-stream convolutional networks for action recognition in videos. In: Proceedings of the 27th International Conference on Neural Information Processing Systems. 2014, 568–576
Abadi M, Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado G S, Davis A, Dean J, Devin M, et al. Tensorflow: Large-scale machine learning on heterogeneous distributed systems. 2016, ar**v preprint ar**v: 1603.04467
Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. 2015, ar**v preprint ar**v: 1502.03167
He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 2016, 770–778
Dai X, Singh B, Zhang G, Davis L. S, Qiu Chen Y. Temporal context network for activity localization in videos. In: Proceedings of the IEEE International Conference on Computer Vision. 2017, 5793–5802
Ghanem B, Niebles J C, Snoek C, Heilbron F C, Alwassel H, Khrisna R, Escorcia V, Hata K, Buch S. Activitynet challenge 2017 summary. 2017, ar**v preprint ar**v: 1710.08011
Acknowledgements
This work was partially supported by the National Key Research and Development Program of China (2016YFE0204200), the National Natural Science Foundation of China (Grant Nos. 61972016, 62032016), Bei**g Natural Science Foundation (L191007), the Fundamental Research Funds for the Central Universities (YWF-21-BJ-J-313 and YWF-20-BJ-J-612), Open Research Fund of Digital Fujian Environment Monitoring Internet of Things Laboratory Foundation (202004). The experimental platform is provided by Marc Casas at the Barcelona Supercomputing Center (BSC).
Author information
Authors and Affiliations
Corresponding author
Additional information
Tian Wang received the BE degree and MS degree from **’an Jiaotong University, China in 2007 and 2010, respectively. He received his PhD degree from University of Technology of Troyes, France in 2014. He is an associate professor at the Institute of Artificial Intelligence, Beihang University, China. His research interests include artificial intelligence, machine learning, computer vision and pattern recognition.
Shiye Lei received the BS degree from Beihang University, China. He is currently pursing the MS degree with School of Computer Science, University of Sydney, Australia. His current research interests include machine learning and theinterpretability of neural networks.
Youyou Jiang received the BS degree and MS degree from **’an Jiaotong University and Tsinghua-University, China, respectively. His current research interests include machine learning and its applications.
Choi Chang received BS, MS and PhD degrees in Computer Engineering from Chosun University, Korea in 2005, 2007, and 2012, respectively. After that, he worked at the same university as a research professor for several years, and then he has moved to Gachon University since 2020. He was awarded the academic awards from the graduate school of Chosun University in 2012. He also received a Korean government scholarship for graduate students (PhD course) in 2008. His research interests include intelligent information processing, semantic web, smart IoT system and intelligent system security.
Hichem Snoussi received his PhD degrees from the University of Paris-Sud, France in 2003. Since 2010, he has been a full professor at the University of Technology of Troyes, France. His research interests include signal processing, computer vision and machine learning.
Guangcun Shan received the PhD degree from City University of Hong Kong, China in 2013, and the BE degree from **’an Jiaotong University, China in 2004, respectively. He is a full professor under the support of National Talent Program at Beihang University, China. His research interests include the machine learningalgorithm, first-principle calculation of functional materials, the model design and fabrication of MEMS sensors and 2D material-based wearable flexible electronics.
Yao Fu received the PhD degree from Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, China in 2012. She is currently an Associate Professor with Changchun Institute of Optics, Fine Mechanics and Physics, Chinese Academy of Sciences, China. Her research interests include remote sensing optical imaging and image processing.
Electronic supplementary material
Rights and permissions
About this article
Cite this article
Wang, T., Lei, S., Jiang, Y. et al. Accelerating temporal action proposal generation via high performance computing. Front. Comput. Sci. 16, 164317 (2022). https://doi.org/10.1007/s11704-021-0173-7
Received:
Accepted:
Published:
DOI: https://doi.org/10.1007/s11704-021-0173-7