Temporal Relevance Analysis for Video Action Models

arxiv(2022)

引用 0|浏览23
暂无评分
摘要
In this paper, we provide a deep analysis of temporal modeling for action recognition, an important but underexplored problem in the literature. We first propose a new approach to quantify the temporal relationships between frames captured by CNN-based action models based on layer-wise relevance propagation. We then conduct comprehensive experiments and in-depth analysis to provide a better understanding of how temporal modeling is affected by various factors such as dataset, network architecture, and input frames. With this, we further study some important questions for action recognition that lead to interesting findings. Our analysis shows that there is no strong correlation between temporal relevance and model performance; and action models tend to capture local temporal information, but less long-range dependencies. Our codes and models will be publicly available.
更多
查看译文
关键词
Temporal analysis,Frame relevance,Video data,Action recognition
AI 理解论文
溯源树
样例
生成溯源树,研究论文发展脉络
Chat Paper
正在生成论文摘要