Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914737030168576 |
|---|---|
| author | Chang, Haochen Chen, Jing Li, Yilin Chen, Jixiang Zhang, Xiaofeng |
| author_facet | Chang, Haochen Chen, Jing Li, Yilin Chen, Jixiang Zhang, Xiaofeng |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2402_02210 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition Chang, Haochen Chen, Jing Li, Yilin Chen, Jixiang Zhang, Xiaofeng Computer Vision and Pattern Recognition Multimedia 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. |
| title | Wavelet-Decoupling Contrastive Enhancement Network for Fine-Grained Skeleton-Based Action Recognition |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2402.02210 |