“Robots do not need to look like robots … the most important part is to (have the robot) understand what the human is thinking … Human, the weakest link!”
Dr. Yang’s research centers around the long lasting ancient quest: how to create intelligent agents that can understand human? His perspective to approach this quest is from the angle of visual perception. Why do robots perceive, how do robots perceive, what do robots perceive and when do robots perceive, to understand us? Over the last decade, Dr. Yang has been exploring problems and solutions stem from Computer Vision (more specifically, Active Vision), synergistically together with Natural Language Processing and AI reasoning, for the purpose of Robotic visual learning. His current research focuses on human manipulation action understanding, explainable methods for visual recognition and Robotic visual learner.
• Yezhou: Tech talk “Vision-Language integration challenges and needs in Robotics” at the 3rd integrating Vision and Language training school, Sep 5th, Athens, Greece.
• Yezhou: Tech talk “Active Perception Beyond Appearance, and its Robotic Applications” at the Brain team, Google Inc.
• Invited talk “Active Perception Beyond Appearance, and its Robotic Applications” at the Center for Vision, Cognition, Learning and Autonomy, University of California Los Angeles, April 2017;
• Visual Interpretation of Manipulation Actions for Cognitive Robots at GPUs for Deep Learning and Embedded Technologies Workshop at Arizona State University, June 2016;
• Human Manipulation Action Understanding for Cognitive Robots, at Carnegie Mellon University VASC Seminar, May 2016;
• Visual Interpretation of Manipulation Actions part II, at Mid-Atlantic Computer Vision (MACV) Workshop 2016, John Hopkins University, April 2016;
• Human Manipulation Action Understanding for Cognitive Robots, at Princeton Computer Vision Seminar, Feb 2016;
• Grasping type, Action Intention, and Manipulation Semantics, at Institute of Cyber-systems and Control, Zhejiang University, August 2015;
• Visual Interpretation of Manipulation Actions part I, at Mid-Atlantic Computer Vision (MACV) Workshop 2014, Virginia Tech University, April 18th 2014;
• Plenary Socratic Dialogue, the Manipulation Action Language, together with Prof. Yiannis Aloimonos at Humanoids 2013, Oct 17th 2013;