DREAM Project (EU FP7, 2014-2018)

imgproject_dream-project-eu-fp7-2014-2018
The project is funded by EU FP7 Framework and lasts for 4 years.The main objective of this post is to develop and implement novel computer vision and learning algorithms for human activity analysis (gesture, gaze and facial expression) especially tempo-spatial gaze pattern analysis and behaviour patterns analysis of ASD children. Yu H., Liu H. (2014) Linear Regression for Head Pose Analysis, , IEEE World Congress on Computational Intelligence, Beijing, China, 2014; Yu H., Ju Z. Liu H. (2014) I...

Dynamic 3D Facial Expression Reconstruction and Analysis

imgproject_dynamic-3d-facial-expression-reconstruction-and-analysis
This project investigates novel methods for flexibly synthesizing any arbitrary meaningful dynamic 3D facial expression in the absence of actor performance data for that expression. With techniques from computer graphics, we synthesized random arbitrary dynamic facial expression animations. The synthesis was controlled by parametrically modulating Action Units (AUs) taken from the Facial Action Coding System (FACS). We presented these to human observers and instructed them to categorize the anim...

Cross-cultural Investigation of 4D Facial Expressions

imgproject_cross-cultural-investigation-of-4d-facial-expressions
Since Darwin's seminal works, the universality of facial expressions of emotion has remained one of the longest standing debates in the biological and social sciences. Here, we refute this assumed universality. Using a unique computer graphics platform that combines generative grammars with visual perception, we accessed the mind's eye of 30 Western and Eastern culture individuals and reconstructed their mental representations of the six basic facial expressions of emotion. Crosscultural compari...

3D Human Body Reconstruction and Perception

imgproject_3d-human-body-reconstruction-and-perception
First, This project investigates methods for creating LOD models from real human body scan data. Second this project investigates whether attractive bodies signal low FA to observers, and, if so, which aspects of attractive bodies are most predictive of lower FA. Body size and shape seem to have been sexually selected in a variety of species, including humans, but little is known about what attractive bodies signal about underlying genotypic or phenotypic quality. Our results indicate that FA-an...