通过频域增强提升动作识别精度，实现零样本骨架动作识别新突破
Frequency-Enhanced Diffusion Models: Curriculum-Guided Semantic Alignment for Zero-Shot Skeleton Action Recognition
- 引入频域感知模块，修复扩散模型对高频动作细节的过度平滑问题
- 在NTU RGB+D等3个数据集上达到当前最优性能，准确率显著提升
- 适合关注动作识别、生成模型优化的研究者与工程师
人体动作识别在计算机视觉中至关重要，应用涵盖监控到人机交互。尽管基于骨架的监督方法有效，但其依赖大量标注数据，限制了对新动作的泛化能力。零样本骨架动作识别（ZSAR）成为有前景的方向，但扩散模型存在谱偏差，导致高频动态被过度平滑。本文提出频域感知的骨架-文本匹配扩散模型（FDSM），包含语义引导的频谱残差模块、时间步自适应频谱损失和课程式语义抽象机制，有效恢复细粒度运动细节，在NTU RGB+D、PKU-MMD和Kinetics-skeleton数据集上取得领先性能。代码已公开于https://github.com/yuzhi535/FDSM。
原文摘要 · Abstract (English)
Human action recognition is pivotal in computer vision, with applications ranging from surveillance to human-robot interaction. Despite the effectiveness of supervised skeleton-based methods, their reliance on exhaustive annotation limits generalization to novel actions. Zero-Shot Skeleton Action Recognition (ZSAR) emerges as a promising paradigm, yet it faces challenges due to the spectral bias of diffusion models, which oversmooth high-frequency dynamics. Here, we propose Frequency-Aware Diffusion for Skeleton-Text Matching (FDSM), integrating a Semantic-Guided Spectral Residual Module, a Timestep-Adaptive Spectral Loss, and Curriculum-based Semantic Abstraction to address these challenges. Our approach effectively recovers fine-grained motion details, achieving state-of-the-art performance on NTU RGB+D, PKU-MMD, and Kinetics-skeleton datasets. Code has been made available at https://github.com/yuzhi535/FDSM. Project homepage: https://yuzhi535.github.io/FDSM.github.io/
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。