Haresh Rengaraj Rajamohan

Papers

Total Citations

H-Index

About

Haresh Rengaraj Rajamohan is a researcher advancing the field of machine learning for fine-grained action identification, with a particular focus on high-temporal-resolution analysis. His work bridges computer vision and kinematic data to enable automatic recognition of rapid, sub-second movements—a challenging problem with critical applications in robotics, smart health, and rehabilitation. Rajamohan’s major contributions include the creation of **StrokeRehab**, a benchmark dataset for sub-second action identification (5 citations), which provides a standardized platform for evaluating models on short-duration actions. He also developed **sequence-to-sequence modeling** approaches for action identification at high temporal resolution (2 citations), pushing beyond traditional coarse action recognition (e.g., running or climbing) to capture nuanced, rapid behaviors. Though his citation counts are modest, his work is foundational for emerging applications in automated rehabilitation monitoring and assistive robotics. By focusing on the temporal granularity of human movement, Rajamohan is helping to unlock new possibilities for real-time, context-aware systems that can respond to subtle changes in human activity.