Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition
CoRR(2024)
摘要
Skeleton-based action recognition has attracted much attention, benefiting
from its succinctness and robustness. However, the minimal inter-class
variation in similar action sequences often leads to confusion. The inherent
spatiotemporal coupling characteristics make it challenging to mine the subtle
differences in joint motion trajectories, which is critical for distinguishing
confusing fine-grained actions. To alleviate this problem, we propose a
Wavelet-Attention Decoupling (WAD) module that utilizes discrete wavelet
transform to effectively disentangle salient and subtle motion features in the
time-frequency domain. Then, the decoupling attention adaptively recalibrates
their temporal responses. To further amplify the discrepancies in these subtle
motion features, we propose a Fine-grained Contrastive Enhancement (FCE) module
to enhance attention towards trajectory features by contrastive learning.
Extensive experiments are conducted on the coarse-grained dataset NTU RGB+D and
the fine-grained dataset FineGYM. Our methods perform competitively compared to
state-of-the-art methods and can discriminate confusing fine-grained actions
well.
更多查看译文
关键词
Fine-grained action recognition,Discrete Wavelet Transform,frequency decoupling,contrastive learning
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