.png){kind=icon}
返回
Accelerating temporal action proposal generation via high performance computing
.png){kind=icon}
PRE
AI
DOI：10.1007/s11704-021-0173-7.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
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.
Keyword:
temporal convolution
temporal action proposal eneration
deep learning
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
4.6
论文数:
1.6K
被引数:
2.8K
机构
引用论文
.png){kind=icon}
Microstructure and magnetic properties of sintered NdFeB magnets with improved impact toughness
PREAI
分享收藏
Detection of proliferative responses to ESAT-6 and CFP-10 by FASCIA assay for diagnosis of Mycobacterium tuberculosis infection通过筋膜试验检测对ESAT-6和CFP-10的增殖反应以诊断结核分枝杆菌感染
PREAI
分享收藏
查看更多内容