# Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition

arXiv: https://arxiv.org/abs/2402.02210 · HTML: https://mlsanity.com/paper/2402.02210/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 21 references that are in the map.
- First posted on arXiv 3 Feb 2024.

## Builds on (most cited first, 14 of 14)

- [Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/1801.07455/) (2018)
- [NTU RGB+D: A Large Scale Dataset for 3D Human Activity Analysis](https://mlsanity.com/paper/1604.02808/) (2016)
- [Disentangling and Unifying Graph Convolutions for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2003.14111/) (2020)
- [Channel-wise Topology Refinement Graph Convolution for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2107.12213/) (2021)
- [FineGym: A Hierarchical Video Dataset for Fine-grained Action Understanding](https://mlsanity.com/paper/2004.06704/) (2020)
- [Wavelet Diffusion Models are fast and scalable Image Generators](https://mlsanity.com/paper/2211.16152/) (2022)
- [Co-occurrence Feature Learning from Skeleton Data for Action Recognition and Detection with Hierarchical Aggregation](https://mlsanity.com/paper/1804.06055/) (2018)
- [Skeleton-based Action Recognition via Spatial and Temporal Transformer Networks](https://mlsanity.com/paper/2008.07404/) (2020)
- [Constructing Stronger and Faster Baselines for Skeleton-based Action Recognition](https://mlsanity.com/paper/2106.15125/) (2021)
- [Hierarchically Decomposed Graph Convolutional Networks for Skeleton-Based Action Recognition](https://mlsanity.com/paper/2208.10741/) (2022)
- [PYSKL: Towards Good Practices for Skeleton Action Recognition](https://mlsanity.com/paper/2205.09443/) (2022)
- [Learning Discriminative Representations for Skeleton Based Action Recognition](https://mlsanity.com/paper/2303.03729/) (2023)
- [Wavelet Integrated CNNs for Noise-Robust Image Classification](https://mlsanity.com/paper/2005.03337/) (2020)
- [Learning Multi-Granular Spatio-Temporal Graph Network for Skeleton-based Action Recognition](https://mlsanity.com/paper/2108.04536/) (2021)

## Built on by (most cited first, 5 of 5)

- [Revealing Key Details to See Differences: A Novel Prototypical Perspective for Skeleton-based Action Recognition](https://mlsanity.com/paper/2411.18941/) (2024)
- [Frequency-Semantic Enhanced Variational Autoencoder for Zero-Shot Skeleton-based Action Recognition](https://mlsanity.com/paper/2506.22179/) (2025)
- [SRENet: Spectral Re-Entry Network for Point Cloud Action Recognition](https://mlsanity.com/paper/2606.03160/) (2026)
- [OMG-Bench: A New Challenging Benchmark for Skeleton-based Online Micro Hand Gesture Recognition](https://mlsanity.com/paper/2512.16727/) (2025)
- [Affinity Contrastive Learning for Skeleton-based Human Activity Understanding](https://mlsanity.com/paper/2601.16694/) (2026)

## Abstract (arXiv)

Skeleton-based action recognition has attracted much attention, benefiting from its succinctness and robustness. However, the minimal inter-class variation in similar action sequences often leads to confusion. The inherent spatiotemporal coupling characteristics make it challenging to mine the subtle differences in joint motion trajectories, which is critical for distinguishing confusing fine-grained actions. To alleviate this problem, we propose a Wavelet-Attention Decoupling (WAD) module that utilizes discrete wavelet transform to effectively disentangle salient and subtle motion features in the time-frequency domain. Then, the decoupling attention adaptively recalibrates their temporal responses. To further amplify the discrepancies in these subtle motion features, we propose a Fine-grained Contrastive Enhancement (FCE) module to enhance attention towards trajectory features by contrastive learning. Extensive experiments are conducted on the coarse-grained dataset NTU RGB+D and the fine-grained dataset FineGYM. Our methods perform competitively compared to state-of-the-art methods and can discriminate confusing fine-grained actions well.