Muhammad Sharif
Papers
1
Total Citations
99
H-Index
1
About
Muhammad Sharif is a leading figure in computer vision and deep learning, with a particular focus on biometrics and pedestrian analysis. His most cited work, "Appearance based pedestrians’ gender recognition by employing stacked auto encoders in deep learning" (2018), has garnered 99 citations, underscoring its impact on automated gender classification from visual data. This research pioneered the use of stacked autoencoders to extract robust features from pedestrian appearances, significantly advancing the accuracy and efficiency of real-world surveillance and human-computer interaction systems. Sharif's contributions extend to developing novel deep learning architectures that address challenges in feature extraction and classification under varying conditions. His work is widely recognized for bridging theoretical advances with practical applications, influencing subsequent studies in gender recognition, person re-identification, and behavioral analysis. By integrating stacked autoencoders with traditional deep learning frameworks, Sharif has provided a foundational methodology that continues to inspire researchers exploring non-invasive biometric identification. His research remains a key reference for those seeking to understand and improve automated pedestrian analysis in complex environments.
Research Focus
Key Achievements
Top Papers
- 1