Rohita Mocharla

Papers

Total Citations

H-Index

About

Rohita Mocharla is a researcher at the forefront of computer vision and human action recognition, with a particular focus on bridging the gap between synthetic and real-world data. Her most-cited work, "Synthetic-to-Real Domain Adaptation for Action Recognition: A Dataset and Baseline Performances" (2023, 24 citations), tackles a critical challenge in deep learning: the high variability in subject appearance, backgrounds, and viewpoints that limits the generalization of deep neural networks. By introducing a novel dataset and establishing baseline performances for domain adaptation, Mocharla has provided the research community with essential tools to train robust action recognition models without relying on massive, manually annotated real-world videos. This contribution is especially valuable for applications in surveillance, human-computer interaction, and autonomous systems, where labeled data is scarce or expensive. Her work demonstrates a keen ability to identify practical bottlenecks in AI deployment and offers scalable solutions, making her a rising voice in the field of domain adaptation and video understanding.