轻量级骨架动作识别模型，用频域分析提升效率与精度
FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
- 通过重构频域算子和简化注意力模块实现轻量化设计
- 参数量仅为现有方法的60%，在三大数据集上表现更优
- 适合边缘设备部署，特别适合资源受限场景
基于Transformer的人体骨骼动作识别已发展多年，但其复杂度高、参数量大，限制了在资源受限环境中的应用。本文提出FreqMixFormerV2，基于频域感知混合Transformer，通过重新设计频域算子优化高低频参数调整，并简化频域感知注意力模块，显著降低模型复杂度。该设计在保持强鲁棒性的同时大幅减少参数量，使模型可在极低资源下高效部署，仅损失微小精度。在标准数据集NTU RGB+D、NTU RGB+D 120和NW-UCLA上的全面评估表明，该模型以仅60%的参数量超越现有最先进方法，在效率与精度之间取得更优平衡。
原文摘要 · Abstract (English)
Transformer-based human skeleton action recognition has been developed for years. However, the complexity and high parameter count demands of these models hinder their practical applications, especially in resource-constrained environments. In this work, we propose FreqMixForemrV2, which was built upon the Frequency-aware Mixed Transformer (FreqMixFormer) for identifying subtle and discriminative actions with pioneered frequency-domain analysis. We design a lightweight architecture that maintains robust performance while significantly reducing the model complexity. This is achieved through a redesigned frequency operator that optimizes high-frequency and low-frequency parameter adjustments, and a simplified frequency-aware attention module. These improvements result in a substantial reduction in model parameters, enabling efficient deployment with only a minimal sacrifice in accuracy. Comprehensive evaluations of standard datasets (NTU RGB+D, NTU RGB+D 120, and NW-UCLA datasets) demonstrate that the proposed model achieves a superior balance between efficiency and accuracy, outperforming state-of-the-art methods with only 60% of the parameters.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。