Workshop on Face Analysis: The Intersection of Computer Vision and Human Perception

摘要

The analysis of faces is a very active research area within both the computer vision and the human perception communities, and there is a large array of potential applications and research topics. The two communities have traditionally worked separately, but there are clear benefits to closer collaboration. For instance, humans develop extensive experience in the processing of face identity, age, gender, and non-verbal communication signals such as facial expressions. Thus, tapping into existing knowledge from human facial perception research can enable the targeted design of computer vision facial analysis and synthesis systems with more realistic behavioural facial models and performance. Moreover, computer vision systems can provide many useful tools for research into the human perception of faces such as the generation of photo-realistic and controllable stimuli for perceptual experiments, which enables more subtle manipulation of facial appearance and dynamics than would be possible using natural video capture.