Abstract
Skeleton-aware sign language recognition (SLR) has gained popularity due to its ability to remain unaffected by background information and its lower computational requirements. Current methods utilize spatial graph modules and temporal modules to capture spatial and temporal features, respectively. However, their spatial graph modules are typically built on fixed graph structures such as graph convolutional networks or a single learnable graph, which only partially explore joint relationships. Additionally, a simple temporal convolution kernel is used to capture temporal information, which may not fully capture the complex movement patterns of different signers. To overcome these limitations, we propose a new spatial architecture consisting of two concurrent branches, which build input-sensitive joint relationships and incorporates specific domain knowledge for recognition, respectively. These two branches are followed by an aggregation process to distinguishe important joint connections. We then propose a new temporal module to model multi-scale temporal information to capture complex human dynamics. Our method achieves state-of-the-art accuracy compared to previous skeleton-aware methods on four large-scale SLR benchmarks. Moreover, our method demonstrates superior accuracy compared to RGB-based methods in most cases while requiring much fewer computational resources, bringing better accuracy-computation trade-off. Code is available at https://github.com/hulianyuyy/DSTA-SLR.- Anthology ID:
- 2024.lrec-main.484
- Volume:
- Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)
- Month:
- May
- Year:
- 2024
- Address:
- Torino, Italia
- Editors:
- Nicoletta Calzolari, Min-Yen Kan, Veronique Hoste, Alessandro Lenci, Sakriani Sakti, Nianwen Xue
- Venues:
- LREC | COLING
- SIG:
- Publisher:
- ELRA and ICCL
- Note:
- Pages:
- 5450–5460
- Language:
- URL:
- https://aclanthology.org/2024.lrec-main.484
- DOI:
- Cite (ACL):
- Lianyu Hu, Liqing Gao, Zekang Liu, and Wei Feng. 2024. Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition. In Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pages 5450–5460, Torino, Italia. ELRA and ICCL.
- Cite (Informal):
- Dynamic Spatial-Temporal Aggregation for Skeleton-Aware Sign Language Recognition (Hu et al., LREC-COLING 2024)
- PDF:
- https://preview.aclanthology.org/landing_page/2024.lrec-main.484.pdf