Title
Accelerating temporal action proposal generation via high performance computing
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.
Year
DOI
Venue
2019
10.1007/s11704-021-0173-7
FRONTIERS OF COMPUTER SCIENCE
Keywords
DocType
Volume
temporal convolution, temporal action proposal eneration, deep learning
Journal
16
Issue
ISSN
Citations 
4
2095-2228
0
PageRank 
References 
Authors
0.34
0
7
Name
Order
Citations
PageRank
Tian Wang1216.47
Shiye Lei200.68
Youyou Jiang300.68
Zihang Deng400.34
Xin Su500.34
Hichem Snoussi650962.19
Chang Choi726139.04