Visual Computing and Machine Intelligence

VCMI (Visual Computing and Machine Intelligence) is a research area focused on the application of machine learning methodologies to the challenging conditions posed by visual data. The development of intelligent decision-support systems is based on the visual understanding of data, combined with other available information, thereby enhancing the analysis and decision-making process. This area’s mission is to contribute significantly to the next generation of intelligent systems by equipping them with reasoning capabilities based on various data types, such as images, video, or other signals. We conduct research on both fundamental and applied problems in computer vision, image processing, machine learning, and decision-support systems grounded in automatic data analysis. Within these main research directions, our group places particular emphasis on specific domains, such as medical image analysis; biometrics and biological signal analysis; driver/passenger monitoring and autonomous driving; and more fundamental topics in computer vision, such as ordinal classification.