Leads the CVAIR Lab with research interests in deep learning, biomedical image analysis, and explainable AI. Focused on developing clinical decision support systems using generative and multimodal AI.
Working on explainable colorectal cancer segmentation using vision-language models like CLIP and LLaVA.
Research: Focusing on tooth segmentation and the impact of dental mesh resolution on tooth segmentation.
Research: Exploring generative models for synthetic data generation in biomedical imaging.
Research: Tooth landmark localization from 3D dental mesh.
Research: A Vision Transformer and Diffusion-Based Hybrid AI Framework for 3D Human Pose Estimation.
Research: Using Speech and Text to Recognize Swimming Distress Through Gestures.
Research: Deep learning-based human mesh recovery from 2D images guided by textual prompts.