BriefGPT.xyz
Jul, 2020
VIPriors行动识别挑战赛挑战报告
Challenge report:VIPriors Action Recognition Challenge
HTML
PDF
Zhipeng Luo, Dawei Xu, Zhiguang Zhang
TL;DR
本文研究行动识别问题，结合 SlowFast 网络和 TSM 方法，在视频中提取运动特征可以使用残差帧作为输入和 RGB 帧输入模型的优秀补充，通过3D卷。积（SlowFast）与2D卷积（TSM）的组合取得更好的性能结果，以上实验均在 UCF101 中从头开始训练。
Abstract
This paper is a brief report to our submission to the VIPriors
action recognition
Challenge.
action recognition
has attracted many researchers attention for its full application, but it is still challenging. In t
→