Predicting race from face
We present a framework for estimating race from faces in movie data. Please refer to a detailed survey “Learning race from face: A survey”, Fu S. et. al., 2014 for a discussion on studies on recognizing race from faces. The definitions and taxonomy of race from a computer vision perspective... [Read More]

Animated content
Automatic movie or multimedia content analysis requires audio-video diarization (i.e., “who” appeared? and “when”). For video diarization in particular, where the characters that appear on screen are not known, a key step is to provide a list of characters that form the who appeared component of the system. We refer... [Read More]