Leonid's research interests mainly lie in the areas of computer vision, machine learning, and computer graphics, but also borderline fields of psychology and humanoid robotics. He is particularly interested in statistical and machine learning models for problems of visual inference, understanding and reasoning; including language+vision, human motion analysis, activity recognition, object detection, scene understanding, representation learning, graphical models, probabilistic and hierarchical inference. He also enjoys cross disciplinary research that lays on the intersection of computer vision, machine learning and computer graphics.