Max Robotics — Global Service Robot Directory + US Certification

About

Dinesh Kumar Vishwakarma is a leading researcher in computer vision and human-centered artificial intelligence, with a primary focus on human activity recognition, person re-identification, and multimodal sentiment analysis. His foundational work on video benchmarks for human action datasets, including his highly cited 2018 review (84 citations), has provided critical frameworks for standardizing evaluation in the field. Vishwakarma has made significant contributions to action recognition through innovative descriptor-based methods, such as his multi-resolution key pose approach (28 citations), which bridges visual cognition and computational efficiency. His deep learning surveys on person re-identification (9 citations) have helped shape modern approaches to cross-camera identity matching, while his recent work on ensembled neural networks for static hand gesture recognition (4 citations) advances sign language understanding and human-robot interaction. Most recently, Vishwakarma has pioneered aspect-based multimodal sentiment analysis, developing a visual-to-emotional-caption translation network (2025) that integrates visual and textual cues for nuanced emotion detection. With over 168 total citations across his most-cited works, his research consistently pushes the boundaries of how machines perceive and interpret human behavior, making him a key figure in the evolution of intelligent visual systems.