Accelerating temporal action proposal generation via high performance computing  

作　　者：Tian Wang Shiye Lei Youyou Jiang Choi Chang Hichem Snoussi Guangcun Shan Yao Fu 

机构地区：[1]Institute of Artificial Intelligence,Beihang University,Beijing,100191,China [2]School of Automation Science and Electrical Engineering,Beihang University,Beijing,100191,China [3]School of Software,Tsinghua University,Beijing,100084,China [4]Department of Computer Engineering,Gachon University,Seongnam,13120,South Korea [5]Institute Charles Delaunay-LM2S FRE CNRS 2019,University of Technology of Troyes,Troyes,10010,France [6]School of Instrumentation Science and Opto-electronics Engineering,Beihang University,Beijing,100191,China [7]Changchun Institute of Optics,Fine Mechanics and Physics,Chinese Academy of Sciences,Changchun,130033,China

出　　处：《Frontiers of Computer Science》2022年第4期59-68,共10页中国计算机科学前沿（英文版）

基　　金：supported by the National Key Research and Development Program of China(2016YFE0204200);the National Natural Science Foundation of China(Grant Nos,61972016,62032016);Bejing 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).

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.

关 键 词：temporal convolution temporal action proposal generation deep learning 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]