Vijay John

Papers

Total Citations

H-Index

About

Dr. Vijay John’s research sits at the intersection of computer vision, robotics, and human-robot interaction, with a core focus on multimodal perception. His major contributions lie in advancing object recognition and emotion recognition by fusing data from diverse sensors—such as RGB-D cameras and audio-visual inputs—using deep learning. His highly cited 2019 survey on RGB-D-based object recognition with multimodal convolutional neural networks (57 citations) provides a foundational roadmap for real-world robotic vision, addressing the challenge of recognizing objects in cluttered environments by integrating depth and color information. More recently, his 2022 work on audio and video-based emotion recognition using multimodal transformers (25 citations) pushes the frontier of human-robot interaction, employing transformer architectures to better capture emotional cues from both speech and facial expressions. This work is notable for its potential to make robots more socially aware and responsive. With a growing citation impact, Dr. John’s research is shaping how machines perceive and interact with the world, offering practical solutions for autonomous systems and assistive robotics.