Dr. Zhu's research expertise spans the areas of 3D computer vision, machine learning, human-computer interaction (HCI), augmented reality, video representations, multimodal sensing and processing, and various applications in education, environment, robotics, surveillance, transportation, security inspection, art analysis and assistive technologies. He has published over 190 peer-reviewed technical papers in the related fields. Currently he is mainly working with various research issues and applications of human and computer vision and multimodal sensing, supported by AFOSR, AFRL, ARO, DHS, NSF, ODNI as well as industry.