A model of facial behaviour

We wish to model the way in which faces move in video sequences. We represent facial behaviour as a sequence of short actions. Each action is a sample from a statistical model representing the variability in the way it is performed. The ordering of actions is defined using a variable length Markov model. Action models and variable length Markov model are trained from a long (20000 frames) video sequence of a talking face. We propose a novel method of quantitatively evaluating the quality of the synthesis by measuring overlaps of parameter histograms. We apply this method to compare our technique with an alternative model that uses an autoregressive process.

[1]  Shaogang Gong,et al.  Learning Intrinsic Video Content Using Levenshtein Distance in Graph Partitioning , 2002, ECCV.

[2]  Christopher J. Taylor,et al.  Modelling 'Talking Head' Behaviour , 2003, BMVC.

[3]  Timothy F. Cootes,et al.  Active Appearance Models , 2001, IEEE Trans. Pattern Anal. Mach. Intell..

[4]  Dana Ron,et al.  The power of amnesia: Learning probabilistic automata with variable memory length , 1996, Machine Learning.

[5]  Shaogang Gong,et al.  Auto clustering for unsupervised learning of atomic gesture components using minimum description length , 2001, Proceedings IEEE ICCV Workshop on Recognition, Analysis, and Tracking of Faces and Gestures in Real-Time Systems.

[6]  Timothy F. Cootes,et al.  Statistical models of appearance for medical image analysis and computer vision , 2001, SPIE Medical Imaging.

[7]  Dana Ron,et al.  The Power of Amnesia , 1993, NIPS.

[8]  Richard Szeliski,et al.  Video textures , 2000, SIGGRAPH.

[9]  Andrew Blake,et al.  Learning Dynamics of Complex Motions from Image Sequences , 1996, ECCV.

[10]  Daniela Hall,et al.  Statistical Gesture Recognition Through Modelling of Parameter Trajectories , 1999, Gesture Workshop.

[11]  Timothy F. Cootes,et al.  Modelling Facial Behaviours , 2002, BMVC.

[12]  Dorin Comaniciu,et al.  Mean shift analysis and applications , 1999, Proceedings of the Seventh IEEE International Conference on Computer Vision.

[13]  Jitendra Malik,et al.  Normalized cuts and image segmentation , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[14]  Christoph Bregler,et al.  Learning and recognizing human dynamics in video sequences , 1997, Proceedings of IEEE Computer Society Conference on Computer Vision and Pattern Recognition.

[15]  David C. Hogg,et al.  Reactive Memories: An Interactive Talking-Head , 2001, BMVC.

[16]  David C. Hogg,et al.  Learning Variable-Length Markov Models of Behavior , 2001, Comput. Vis. Image Underst..

[17]  David C. Hogg,et al.  The acquisition and use of interaction behaviour models , 1998, Proceedings. 1998 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (Cat. No.98CB36231).

[18]  M. Wand.  Data-Based Choice of Histogram Bin Width , 1997 .

[19]  Neill W. Campbell,et al.  Practical Generation of Video Textures using the Auto-Regressive Process , 2002, BMVC.

[20]  Neill W. Campbell,et al.  Video textures using the auto-regressive process , 2002, SIGGRAPH '02.