Natural user interaction devices such as Microsoft Kinect create tremendous excitements and opportunities for researchers and technologists in multimedia computing. Despite commercial success of these devices, we are still the early stage of an evolution towards natural and seamless interaction between computer and human. To build a truly natural user interface, we need multi‐disciplinary collaboration and innovation from researchers in computer vision, computer graphics, CHI, signal processing, and related areas. In this talk, I will use recent technological advances with Microsoft Kinect to illustrate core technologies employed by today’s natural user interfaces. I will also try to identify a few emerging research themes in this new and exciting area.