Ganesh Krishnasamy
Papers
1
Total Citations
7
H-Index
1
About
Ganesh Krishnasamy is a researcher at the forefront of video understanding and semi-supervised learning, with a focus on bridging the gap between efficient model design and real-world data scarcity. His key contributions lie in developing hybrid architectures that combine the representational power of transformers with the proven efficiency of convolutional neural networks. His most cited work, "ActNetFormer: Transformer-ResNet Hybrid Method for Semi-supervised Action Recognition in Videos" (2024), introduces a novel framework that leverages both labeled and unlabeled video data to achieve robust action recognition, a critical challenge in surveillance, human-computer interaction, and autonomous systems. With 7 citations in its first year, this paper has quickly gained traction for its practical approach to reducing annotation costs while maintaining high accuracy. Krishnasamy’s research is particularly notable for its emphasis on semi-supervised techniques, which are essential for scaling video analysis in domains where labeled data is expensive or difficult to obtain. His work continues to influence the development of more data-efficient and computationally feasible models for dynamic visual tasks.
Research Focus
Key Achievements
Top Papers
- 1