FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
원문 초록
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.
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
DeepSTEP: Simultaneous Tracking and Estimation of Pose for Animals and Humans
Zero-shot Skeleton-based Action Recognition with Prototype-guided Feature Alignment
HopaDIFF: Holistic-Partial Aware Fourier Conditioned Diffusion for Referring Human Action Segmentation in Multi-Person Scenarios
EPFL-Smart-Kitchen-30: Densely annotated cooking dataset with 3D kinematics to challenge video and language models
EgoExOR: An Ego-Exo-Centric Operating Room Dataset for Surgical Activity Understanding
Spatio-Temporal Joint Density Driven Learning for Skeleton-Based Action Recognition
토론
이 논문과 연결된 포럼 글이 아직 없습니다.