Strengthening Skeletal Action Recognizers via Leveraging Temporal Patterns

arxiv(2022)

引用 0|浏览11
暂无评分
摘要
Skeleton sequences are compact and lightweight. Numerous skeleton-based action recognizers have been proposed to classify human behaviors. In this work, we aim to incorporate components that are compatible with existing models and further improve their accuracy. To this end, we design two temporal accessories: discrete cosine encoding (DCE) and chronological loss (CRL). DCE facilitates models to analyze motion patterns from the frequency domain and meanwhile alleviates the influence of signal noise. CRL guides networks to explicitly capture the sequence's chronological order. These two components consistently endow many recently-proposed action recognizers with accuracy boosts, achieving new state-of-the-art (SOTA) accuracy on two large datasets.
更多
查看译文
关键词
skeletal action recognizers,temporal
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