Frequency Guidance Matters: Skeletal Action Recognition by Frequency-Aware Mixed Transformer

Wenhan Wu, Ce Zheng, Zihao Yang, Chen Chen, Srijan Das, Aidong Lu

Abstract: Recently, transformers have demonstrated great potential for modeling long-term dependencies from skeleton sequences and thereby gained ever-increasing attention in skeleton action recognition. However, the existing transformer-based approaches heavily rely on the naive attention mechanism for capturing the spatiotemporal features, which falls short in learning discriminative representations that exhibit similar motion patterns. To address this challenge, we introduce the Frequency-aware Mixed Transformer (FreqMixFormer), specifically designed for recognizing similar skeletal actions with subtle discriminative motions. First, we introduce a frequency-aware attention module to unweave skeleton frequency representations by embedding joint features into frequency attention maps, aiming to distinguish the discriminative movements based on their frequency coefficients. Subsequently, we develop a mixed transformer architecture to incorporate spatial features with frequency features to model the comprehensive frequency-spatial patterns. Additionally, a temporal transformer is proposed to extract the global correlations across frames. Extensive experiments show that FreqMiXFormer outperforms SOTA on 3 popular skeleton action recognition datasets, including NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets. Codes will be publicly available.

Primary Subject Area: [Content] Vision and Language

Secondary Subject Area: [Experience] Multimedia Applications

Relevance To Conference: This work, through the development of the Frequency-Aware Mixed Transformer (FreqMixFormer), makes a significant contribution to multimedia/multimodal processing by enhancing the ability of systems to recognize and interpret complex human actions from skeletal data. By distinguishing subtle differences in skeletal movements, FreqMixFormer facilitates a deeper understanding of human behavior, enriching multimodal interaction systems and improving user experience in various applications, from interactive gaming and virtual reality to surveillance and healthcare monitoring.

Submission Number: 2173