# A Low-Cost Hybrid Reservoir Computing Model for Isolated Sign Language Video Recognition

arXiv: https://arxiv.org/abs/2608.03444 · HTML: https://mlsanity.com/paper/2608.03444/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 6 of its 34 references that are in the map.
- First posted on arXiv 4 Aug 2026.

## Builds on (most cited first, 6 of 6)

- [Deep Compression: Compressing Deep Neural Networks with Pruning, Trained Quantization and Huffman Coding](https://mlsanity.com/paper/1510.00149/) (2015)
- [Word-level Deep Sign Language Recognition from Video: A New Large-scale Dataset and Methods Comparison](https://mlsanity.com/paper/1910.11006/) (2019)
- [A Survey on Reservoir Computing and its Interdisciplinary Applications Beyond Traditional Machine Learning](https://mlsanity.com/paper/2307.15092/) (2023)
- [Sign Language Recognition Analysis using Multimodal Data](https://mlsanity.com/paper/1909.11232/) (2019)
- [Sign Language Recognition using Bidirectional Reservoir Computing](https://mlsanity.com/paper/2512.00777/) (2025)
- [Sign Language Recognition using Parallel Bidirectional Reservoir Computing](https://mlsanity.com/paper/2512.19451/) (2025)

## Abstract (arXiv)

Sign language recognition (SLR) enhances communication between hearing and hearing-impaired individuals. Although deep learning (DL) has achieved promising performance in SLR, its high computational cost limits deployment on edge devices. To address this challenge, we propose a lightweight reservoir computing (RC)-based approach for SLR. In the proposed method, MediaPipe extracts body and hand keypoints to capture the spatial and temporal dynamics of gestures. These keypoints are then processed by a hybrid reservoir computing (HRC) architecture that combines deep reservoir computing (DRC) and bidirectional reservoir computing (BRC), transforming the input into a high-dimensional dynamic representation. A ridge regression model maps the final HRC state to class labels. This HRC-based SLR method achieved Top-1, Top-5, and Top-10 accuracies of 61.12%, 86.05%, and 92.56%, respectively, on the Word-Level American Sign Language 100 (WLASL100) video dataset, demonstrating competitive performance compared to deep learning-based approaches. Additionally, due to the lightweight nature of RC, the training time was drastically reduced to only a few seconds compared with DL-based methods such as Bi-GRU.This method offers low computational cost, showing its potential for deployment on edge devices.