Humans communicate with each other mainly through speech. We also use other means of communication for expressing complex ideas. For example, we use handwriting, drawings, and sketches when we describe complex ideas; we communicate our emotions through facial expressions, and gestures.
Although human-human communication takes advantage of all these natural modes of communication, our communication and interaction with computers takes place mainly over keyboard and mouse. However, traditional keyboard and mouse-based interaction methods fail to meet the demands of today’s complex applications, as they were invented in the mid-late 1900’s with the requirements of primitive applications. Our grand vision is to build the foundation for the interaction techniques of the next generation and contribute towards the ambition of redefining human-computer interaction.
More specifically, the central goal in the Lab is to build technologies for enabling natural human-computer interaction by combining techniques from computer vision, machine learning, computer graphics and human-computer interaction. Our work on natural interaction encompasses a number of interaction paradigms and technologies. The work falls under two main categories:
1. Development of core recognition technologies supporting intelligent interaction
2. Development and evaluation of multimodal interaction technologies