Our research addresses computational vision and human visual perception from the viewpoints of cognition, language, logic, and artificial intelligence. Currently, our emphasis is on the integration of vision and artificial intelligence from the viewpoint of embodied visual and visuo-locomotive perception and interaction.
Basic research is driven by application areas where, for instance, the processing and deep semantic interpretation of (potentially large volumes of) highly dynamic visuo-spatial imagery is central:
Embodied Cognitive Vision for Robotics
Visual Perception and Embodiment Research (e.g., involving eye-tracking)
Commonsense Scene Understanding
Explainable Visual Interpretation
Concept Learning and Inference from Visual Stimuli
Semantic Question-Answering with Image and Video
Basic research projects in our group have led to industrial collaborations in areas as diverse as evidence-based architecture design, cognitive film studies, cognitive robotics.