Raveendran Paramesran
Papers
1
Total Citations
7
H-Index
1
About
Raveendran Paramesran is a leading researcher in computer vision and deep learning, with a primary focus on video understanding and action recognition. His most notable contribution is the development of ActNetFormer, a pioneering Transformer-ResNet hybrid architecture for semi-supervised action recognition in videos. This work, published in 2024, has already garnered 7 citations, demonstrating its immediate impact on the field. Paramesran's research addresses the critical challenge of learning from limited labeled data, enabling more efficient and scalable video analysis. His hybrid approach combines the spatial feature extraction strengths of ResNet with the temporal modeling capabilities of Transformers, achieving state-of-the-art performance in semi-supervised settings. Beyond this flagship work, his broader research interests encompass deep learning architectures, video analytics, and human activity understanding. Paramesran's contributions are particularly valuable for applications in surveillance, human-computer interaction, and autonomous systems, where robust action recognition from minimal supervision is essential. His work continues to influence the development of more efficient and accurate video understanding models, making him a notable figure in the evolving landscape of computer vision research.
Research Focus
Key Achievements
Top Papers
- 1