VideoMob is an interactive video platform and an artwork that enables strangers visiting different installation locations to interact across time and space through a computer interface that detects their presence, video-records their actions while automatically removing the video background through computer vision, and co-situates visitors as part of the same digital environment. Through the combination of individual user videos to form a digital crowd, strangers are connected through the graphic display. Our work is inspired by the way distant people can interact with each other through technology and influenced by artists working in the realm of interactive art. We deployed VideoMob in a variety of settings, locations, and contexts to observe hundreds of visitors’ reactions. By analyzing behavioral data collected through depth cameras from our 1,068 recordings across eight venues, we studied how participants behave when given the opportunity to record their own video portrait into the artwork. We report the specific activity performed in front of the camera and the influences that existing crowds impose on new participants. Our analysis informs the integration of a series of possible novel interaction paradigms based on real-time analysis of the visitors’ behavior through specific computer vision and machine learning techniques that have the potential to increase the engagement of the artworks’s visitors and to impact user experience.