Umm e Sadima

Papers

Total Citations

H-Index

About

Umm e Sadima is a rising researcher in computer vision, with a focus on egocentric perception and hybrid deep learning architectures. Her work addresses the critical challenge of object recognition from first-person perspectives—a domain essential for assistive technologies, augmented reality, and human-computer interaction. Her most-cited paper, "EgoVision: a YOLO-ViT hybrid for robust egocentric object recognition" (2025), introduces a novel fusion of You Only Look Once (YOLO) and Vision Transformer (ViT) models to overcome issues like occlusion, motion blur, and viewpoint variability inherent in egocentric video. This contribution demonstrates her ability to bridge real-time detection with transformer-based attention mechanisms, offering a practical solution for wearable and mobile platforms. While her citation count is still growing, the work’s timeliness and technical innovation signal strong potential for impact. Umm e Sadima’s research is particularly relevant for students and engineers developing next-generation AR glasses, prosthetic vision systems, or autonomous agents that must interpret human-centered environments. Her approach exemplifies how hybrid models can push the boundaries of robust, real-world computer vision.