Supporting Multitasking in Video Conferencing using Gaze Tracking and On-Screen Activity Detection

The use of videoconferencing in the workplace has been steadily growing. While multitasking during video conferencing is often necessary, it is also viewed as impolite and sometimes unacceptable. One potential contributor to negative attitudes towards such multitasking is the disrupted sense of eye contact that occurs when an individual shifts their gaze away to another screen, for example, in a dual-monitor setup, common in office settings. We present an approach to improve a sense of eye contact over videoconferencing in dual-monitor setups. Our approach uses computer vision and desktop activity detection to dynamically choose the camera with the best view of a user's face. We describe two alternative implementations of our solution (RGB-only, and a combination of RGB and RGB-D cameras). We then describe results from an online experiment that shows the potential of our approach to significantly improve perceptions of a person's politeness and engagement in the meeting.