Improved Multimodal Integration with Attention for Live Nepali Sign Language Interpretation
This work introduces a framework for attention-based multimodal integration in real-time Nepali Sign Language (NSL) interpretation by combining hand landmarks, face details, and pose information. I have fine-tuned on frame series from five NSL gestures; as a result, the system attains 97.39% validation precision and 31.18 FPS on a GPU. Experiments reveal 83.48% precision in five-epoch scratch training and 46.96% absent ImageNet initialization. The codebase is shared openly to promote NSL inclusivity.
Institutions
- Nepal Academy of Science and Technology (NP)
Publication Details
- Journal
- Zenodo (CERN European Organization for Nuclear Research)
- Published
- 2025-10-22
- DOI
- https://doi.org/10.5281/zenodo.17418647
- Primary Topic
- Hand Gesture Recognition Systems
- Type
- article
- Field-Weighted Citation Impact
- 0.00