Bridging Multimodal AI and Human Perception
Welcome to the Computer Vision & Machine Learning Lab. (CVMLab.) at Dongduk Women's University.
Our core research areas include (but are not limited to):
Visual Quality Assessment (IQA/VQA): Human-centric quality evaluation for images and videos.
Deep Multimodal Learning: Integrating text, image, and video data for comprehensive understanding.
Online Continual Learning: Adaptive AI that learns continuously from changing environments.
We welcome motivated students interested in pursuing research in Computer Vision and Image Processing to join our team.
