Sudhir Gaikwad

Papers

Total Citations

H-Index

About

Sudhir Gaikwad is a researcher advancing the field of computer vision and human activity recognition (HAR). His work focuses on the fusion of vision-based features to improve the accuracy and robustness of activity classification systems. In his most-cited paper, "Fusion of Vision Based Features for Human Activity Recognition" (2023), Gaikwad explores how combining multiple visual cues—such as spatial, temporal, and motion features—can significantly enhance machine learning models' ability to distinguish between complex human actions. This contribution addresses a critical challenge in HAR, where single-feature approaches often fall short in real-world, dynamic environments. With 5 citations already, his research is gaining traction among peers working on intelligent surveillance, assistive robotics, and human-computer interaction. Gaikwad’s work underscores the importance of integrative approaches in computer vision, offering a pathway toward more reliable and context-aware activity recognition systems. His efforts are particularly valuable for students and researchers seeking to understand how feature fusion can bridge the gap between raw visual data and meaningful action classification.