Accelerating temporal action proposal generation via high performance computing

doi:10.1007/s11704-021-0173-7

CIOMP OpenIR

	Accelerating temporal action proposal generation via high performance computing
	T. Wang; S. Y. Lei; Y. Y. Jiang; C. Chang; H. Snoussi; G. C. Shan and Y. Fu
	2022
发表期刊	Frontiers of Computer Science
ISSN	2095-2228
卷号	16 期号:4 页码:10
摘要	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.
DOI	10.1007/s11704-021-0173-7
URL	查看原文
收录类别	SCI
引用统计
文献类型	期刊论文
条目标识符	http://ir.ciomp.ac.cn/handle/181722/65020
专题	中国科学院长春光学精密机械与物理研究所
推荐引用方式 GB/T 7714	T. Wang,S. Y. Lei,Y. Y. Jiang,et al. Accelerating temporal action proposal generation via high performance computing[J]. Frontiers of Computer Science,2022,16(4):10.
APA	T. Wang,S. Y. Lei,Y. Y. Jiang,C. Chang,H. Snoussi,&G. C. Shan and Y. Fu.(2022).Accelerating temporal action proposal generation via high performance computing.Frontiers of Computer Science,16(4),10.
MLA	T. Wang,et al."Accelerating temporal action proposal generation via high performance computing".Frontiers of Computer Science 16.4(2022):10.

条目包含的文件		下载所有文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
Accelerating tempora（3100KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览下载