Fuzzy velocity-based temporal dependency for SVM-driven realistic facial animation

Authors:
Pith Xie;Yiqiang Chen;Junfa Liu;Dongrong Xiao
Affiliations:
Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China and Department of Information Science and Communication, Nanjing University of Information Science and Technology, Na ...;Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China;Department of Information Science and Communication, Nanjing University of Information Science and Technology, Nanjing, China
Venue:
PRICAI'06 Proceedings of the 9th Pacific Rim international conference on Artificial intelligence
Year:
2006

Citing 9
Cited 0

Synthesizing realistic facial expressions from photographs

Proceedings of the 25th annual conference on Computer graphics and interactive techniques
Real-Time Facial Animation based upon a Bank of 3D Facial Expressions

CA '98 Proceedings of the Computer Animation
Reconstruction of Movies of Facial Expressions

RATFG-RTS '01 Proceedings of the IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems (RATFG-RTS'01)
Pattern Classification (2nd Edition)

Pattern Classification (2nd Edition)
Long Short-Term Memory

Neural Computation
Principal component analysis for facial animation

ICASSP '01 Proceedings of the Acoustics, Speech, and Signal Processing, 2001. on IEEE International Conference - Volume 03
Fuzzy methods in machine learning and data mining: Status and prospects

Fuzzy Sets and Systems
On neurobiological, neuro-fuzzy, machine learning, and statistical pattern recognition techniques

IEEE Transactions on Neural Networks
Analysis of switching dynamics with competing support vector machines

IEEE Transactions on Neural Networks

Quantified Score

Hi-index	0.00

Visualization

Abstract

Driving a realistic facial animation with Support Vector Machine (SVM) requires determining the shape-to-wrinkle correspondence, which includes not only spatial dependency, but also temporal dependency. A few available frameworks(e.g., Recurrent Neural Network and Long Short-Term Memory), represent temporal dependency as the dependency of output on position input series, which however may bring about spatial redundancy in some cases. We argue that temporal dependency should be represented as the dependency of output on velocity input series. Besides, due to the weak temporal dependency between shape change and wrinkle change, we put forward Fuzzy Embedding to convert velocity into fuzzy velocity. The shape-wrinkle synthesis demonstrates that, in determining the temporal dependency between wrinkle change and shape change, fuzzy velocity provides more valuable information than velocity and thus enhances the degree of the realism effectively.