Learning Visual Intelligence: Foundations and Applications of Computer Vision

•Understand the fundamental concepts and development of computer vision, including image representation, visual features, and core vision tasks such as image classification, object detection, and segmentation.
•Gain knowledge of learning-based approaches for visual understanding, including visual feature learning, and self-supervised learning methods for images and videos.
•Understand spatiotemporal representations in video understanding and action recognition.
•Understand the principles and applications of medical image analysis, including image segmentation, detection, AI-assisted diagnosis, cancer detection, and virtual image enhancement.
•Acquire insight into how computer vision systems are designed, evaluated, and applied in real-world scenarios through lectures, case studies, and a mini report.

Person in charge: Guoying Zhao
Teaching assistant: Mengjiong Bai
Teacher: Yingli Tian

Lecture slides and selected researcher papers.

Lecture participation and complete a mini report.

Teacher will provide contact teaching while students can join either on site or online.