Video editors are facing the challenge of montage editing when dealing with massive amount of video shots. Watching videos one by one to search for low-level features manually is time-consuming. ViVid is an interactive system for extracting and visualizing low-level video features for particular target videos. ViVid is a generic tool for computer-assisted montage and for the design of generative video arts, which takes advantage of the video features for rendering the piece. The system computes and visualizes the hue, saturation, brightness, motion direction, motion intensity, entropy and contrast features. Instead of visualizing original feature data frame by frame, we re-arranged the data and used both statistics of video feature data and frame level data to represent the video. The system uses dashboards to visualize multiple dimensional data in multiple views.

Research paper

Fan J., Pasquier P., Fadel L.M., Bizzocchi J. (2017) ViVid: A Video Feature Visualization Engine. In: Marcus A., Wang W. (eds) Design, User Experience, and Usability: Understanding Users and Contexts. DUXU 2017. Lecture Notes in Computer Science, vol 10290. Springer, Cham ViVid: A Video Feature Visualization Engine

Download PDF