Max Robotics — Global Service Robot Directory + US Certification

About

Ahmed A. Abdelrahman is a computer vision researcher whose work centers on gaze estimation, face recognition, and deep learning-based perception systems. He is best known for developing **L2CS-Net**, a fine-grained gaze estimation framework designed for unconstrained, real-world environments. This influential work, which has accumulated over 105 citations, addresses longstanding challenges in appearance-based gaze prediction by leveraging convolutional neural networks to deliver more robust and accurate gaze direction estimates — a capability with broad implications for human-robot interaction, autonomous driving, and virtual reality applications. Building on this foundation, Abdelrahman has continued refining gaze estimation methodologies, including a novel approach combining regression and classification losses to further improve angular accuracy in the wild. His research also extends to face recognition, where he proposed an attention-integrated multi-level CNN architecture that balances efficiency and robustness without the computational overhead typical of large-scale verification systems. Collectively, Abdelrahman's contributions reflect a consistent drive to make deep learning models more practical and deployable in real-world scenarios. With a growing citation record and multiple publications addressing core challenges in visual perception, he is establishing himself as a meaningful contributor to the applied computer vision community.