Projects
Multimodal Perception and Learning for Medical and Autonomous Systems 

• Embedded Computer Vision
  - Efficient model development through knowledge distillation and structured pruning
  - Modeling vehicle–pedestrian interactions and real-time risk assessment
  - Real-time computer vision systems and synthetic data generation for UAV platforms
  - Multimodal perception for assistive autonomy: integrating human state recognition and vision-based wheelchair navigation
  - Advancing egocentric vision for human–AI interaction

• Medical Imaging Applications
  - Surgical AI for intraoperative decision-making: video-language models for workflow understanding
  - Self-supervised representation learning and foundation model adaptation for classification and segmentation to support early diagnosis and progression monitoring of retinal and pathological disorders
  - Multimodal learning for integrated clinical decision-making