Md Asif Jalal

Papers

Total Citations

H-Index

About

Md Asif Jalal’s research lies at the intersection of computer vision, human-computer interaction, and assistive technology, with a primary focus on sign language understanding and human action recognition. His most influential work, “American Sign Language Posture Understanding with Deep Neural Networks” (2018, 43 citations), makes a significant contribution by applying deep learning to interpret the complex visual grammar of American Sign Language—a vital step toward bridging communication gaps for the deaf and hard-of-hearing community. This paper addresses the challenge of recognizing nuanced hand postures and facial expressions that form the backbone of sign language, demonstrating how neural networks can decode these non-verbal cues with increasing accuracy. Building on this foundation, Jalal’s subsequent work, “Dual Stream Spatio-Temporal Motion Fusion With Self-Attention For Action Recognition” (2019, 4 citations), introduces an innovative architecture that fuses spatial and temporal motion features using self-attention mechanisms. This approach enhances the robustness of action recognition in realistic, cluttered environments—a critical advancement for applications in human-robot interaction and intelligent surveillance. Though still early in his career, Jalal’s contributions are already shaping how machines perceive and respond to human gestures, with his citation record reflecting growing interest in his methods. His research promises to make technology more inclusive and intuitive, particularly for users who rely on non-verbal communication.