R. Jagadeesh Kannan
Papers
1
Total Citations
4
H-Index
1
About
R. Jagadeesh Kannan is a leading researcher at the intersection of computer vision and video compression, with a primary focus on developing efficient deep learning models for real-time video analysis. His most cited work introduces a novel and optimized YOLO (You Only Look Once) object detection framework specifically designed for H.265 encoded video frames—a critical advancement given the widespread adoption of this high-efficiency video coding standard. By tailoring the YOLO architecture to operate directly on compressed video streams, Kannan’s approach significantly reduces computational overhead while maintaining high detection accuracy, addressing a key bottleneck in applications like surveillance, autonomous systems, and multimedia analytics. This contribution has garnered early recognition, with his 2025 paper already accumulating 4 citations, signaling growing impact in the field. Kannan’s research bridges the gap between video codec optimization and real-time AI inference, offering practical solutions for resource-constrained environments. His work is particularly valuable for students and engineers seeking to understand how modern deep learning can be harmonized with video compression standards to enable smarter, faster visual processing systems.
Research Focus
Key Achievements
Top Papers
- 1A novel and optimized YOLO model for H.265 encoded video frames4 citations · 2025