K M Adarsh

Papers

Total Citations

H-Index

About

K M Adarsh is a researcher in computer vision and deep learning, with a focused interest in human action recognition—a challenging domain that involves interpreting and classifying human activities from video data. His major contribution lies in developing a novel deep learning framework that integrates Mediapipe for real-time pose estimation with Long Short-Term Memory (LSTM) networks to model temporal dynamics in human motion. This approach effectively decodes stance and movement information, enabling robust recognition of complex actions. Although his most-cited works have garnered 2 citations each, they represent foundational steps in applying lightweight, efficient architectures to video-based activity analysis. Adarsh’s work is particularly notable for its practical emphasis on leveraging Mediapipe’s skeletal tracking to reduce computational overhead while maintaining accuracy, making it suitable for real-world applications like surveillance, healthcare monitoring, and human-computer interaction. His research contributes to the growing body of knowledge on bridging pose estimation and sequence modeling, offering a scalable solution for action recognition tasks. As an emerging voice in this field, Adarsh’s efforts highlight the potential of combining classical computer vision techniques with modern deep learning to address pressing challenges in automated video understanding.