Research summary
Computer vision is a field that studies the use of computers to automatically perceive and understand visual content in order to make predictions or inform decisions. A key component of computer vision is learning: it enables the acquisition of sophisticated models of the visual world from large images.
As Canada Research Chair in Computer Vision and Machine Learning, Dr. Leonid Sigal is studying some of the fundamental challenges associated with computer vision. These include learning from limited, structured and/or multi-modal data (images plus descriptive text and sound) and developing new neural architectures and objectives. Sigal and his research team plan to use their discoveries to come up with solutions for applications in data curation, content creation, augmented reality and medicine.