Outlier rejection in high-dimensional deformable models
Image and Vision Computing
EM enhancement of 3D head pose estimated by point at infinity
Image and Vision Computing
Multi-View AAM Fitting and Construction
International Journal of Computer Vision
Multi-View AAM Fitting and Construction
International Journal of Computer Vision
High Resolution Tracking of Non-Rigid Motion of Densely Sampled 3D Data Using Harmonic Maps
International Journal of Computer Vision
Simultaneous Facial Action Tracking and Expression Recognition in the Presence of Head Motion
International Journal of Computer Vision
ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Comparing Feature Point Tracking with Dense Flow Tracking for Facial Expression Recognition
IWINAC '09 Proceedings of the 3rd International Work-Conference on The Interplay Between Natural and Artificial Computation: Part II: Bioinspired Applications in Artificial and Natural Computation
Real-time 2D+3D facial action and expression recognition
Pattern Recognition
Analyzing facial expression by fusing manifolds
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Person-similarity weighted feature for expression recognition
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part II
Audio-visual spontaneous emotion recognition
ICMI'06/IJCAI'07 Proceedings of the ICMI 2006 and IJCAI 2007 international conference on Artifical intelligence for human computing
Recognition of 3D facial expression dynamics
Image and Vision Computing
| Hi-index | 0.00 |
Facial motions produce not only facial feature points motions,but also subtle appearance changes such as wrinklesand shading changes. These subtle changes are importantyet difficult issues for both analysis (tracking) and synthesis(animation). Previous approaches were mostly basedon models learned from extensive training appearance examples.However, the space of all possible facial motionappearance is huge. Thus, it is not feasible to collect samplescovering all possible variations due to lighting conditions,individualities, and head poses. Therefore, it is difficultto adapt such models to new conditions. In this paper,we present an adaptive technique for analyzing subtle facialappearance changes. We propose a new ratio-imagebased appearance feature, which is independent of a person'sface albedo. This feature is used to track face appearancevariations based on exemplars. To adapt the exemplarappearance model to new people and lighting conditions,we develop an online EM-based algorithm. Experimentsshow that the proposed method improves classification resultsin a facial expression recognition task, where a varietyof people and lighting conditions are involved.