Naser Jawas

Naser Jawas

Assistant Professor in Computer Science

Posts by Collection

portfolio

publications

Automatic Sign Language Recognition Using Colour Image Representation of Dense Optical Flow and Multi-Cluster Optical Flow Map

Published in PhD thesis, School of Engineering, University of Warwick, 2024

PhD thesis on automatic sign language recognition from standard RGB video, covering a two-hand tracking algorithm and a recognition system built on a multi-cluster optical flow map.

Recommended citation: Jawas, N. (2024). "Automatic Sign Language Recognition Using Colour Image Representation of Dense Optical Flow and Multi-Cluster Optical Flow Map." PhD thesis, University of Warwick. https://wrap.warwick.ac.uk/id/eprint/190559/
Download Paper

Unsupervised Hand Tracking for Sign Language Recognition via Optical Flow and Previous Tracking Data

Published in IEEE Access, 2026

An unsupervised, model-free hand tracking framework for sign language recognition that uses dense optical flow and temporal consistency, requiring no training data.

Recommended citation: Jawas, N., & Tjahjadi, T. (2026). "Unsupervised Hand Tracking for Sign Language Recognition via Optical Flow and Previous Tracking Data." IEEE Access, 14, 30125–30142. https://doi.org/10.1109/ACCESS.2026.3667503
Download Paper

A Combined Method of Data-Driven Structural Damage Classification by Using Acceleration Data

Published in Machine and Computing Technologies for Sustainable Development (MCT4SD 2025), 2026

A combined data-driven method for classifying structural damage from acceleration data.

Recommended citation: Adha, A., Kurniawan, M., Syarif, F., Wardana, I. N. K., Jawas, N., Harmiyati, & Laory, I. (2026). "A Combined Method of Data-Driven Structural Damage Classification by Using Acceleration Data." In B. Tafuri, S. Kumar, & A. Joshi (Eds.), Machine and Computing Technologies for Sustainable Development: Proceedings of MCT4SD 2025, Volume 3 (pp. 377–386). Lecture Notes in Networks and Systems. Springer, Cham. https://doi.org/10.1007/978-3-032-23716-3_35
Download Paper

Revisiting ST-GCN Design Choices for Skeleton-Based Continuous Sign Language Recognition

Published in Brawijaya International Conference (BIC) 2026 (accepted), 2026

Accepted for presentation at the Brawijaya International Conference (BIC) 2026.

Recommended citation: Jawas, N. (2026). "Revisiting ST-GCN Design Choices for Skeleton-Based Continuous Sign Language Recognition." Brawijaya International Conference (BIC) 2026, Kuala Lumpur, Malaysia. Accepted.

talks

Environment Setup, PyTorch Overview, Dataset and DataLoader

This was the first day of the Introduction to PyTorch Workshop at the Faculty of Computer Science (FILKOM), Universitas Brawijaya. The workshop ran over three Fridays starting on 13 February 2026, and I led two of the three days.

Writing Models, Training and Testing

This was the second day of the Introduction to PyTorch Workshop at the Faculty of Computer Science (FILKOM), Universitas Brawijaya. The workshop ran over three Fridays starting on 13 February 2026, and I led two of the three days.

Object Detection

I was invited to teach Session 8 (Object Detection) of the Nalara Academy online course.

Image Segmentation

I was invited to teach Session 9 (Image Segmentation) of the Nalara Academy online course.

teaching