Saved in:
Bibliographic Details
Main Authors: Wu, Wenhan, Wang, Pengfei, Chen, Chen, Lu, Aidong
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2412.20621
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912172263604224
author Wu, Wenhan
Wang, Pengfei
Chen, Chen
Lu, Aidong
author_facet Wu, Wenhan
Wang, Pengfei
Chen, Chen
Lu, Aidong
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2412_20621
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
Wu, Wenhan
Wang, Pengfei
Chen, Chen
Lu, Aidong
Computer Vision and Pattern Recognition
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.
title FreqMixFormerV2: Lightweight Frequency-aware Mixed Transformer for Human Skeleton Action Recognition
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2412.20621