Mingjun Zhao, Yakun Yu, Xiaoli Wang, Lei Yang, Di Niu
TL;DR通过深度学习算法和启发式搜索方法相结合,优化视频帧的选取,提高动作识别模型的准确性。
Abstract
Despite the success of deep learning in video understanding tasks, processing
every frame in a video is computationally expensive and often unnecessary in
real-time applications. frame selection aims to extract t