Download:
by Ahmed Elgammal
In Proc. of 2nd International Workshop on Generative-Model based vision. GMBV 2004
http://athos.rutgers.edu/~elgammal/pub/GMBV16.pdf
Add To MetaCart
Abstract:
Abstract — Our objective is to learn representations for the shape and the appearance of moving (dynamic) objects that supports tasks such as synthesis, pose recovery, reconstruction and tracking. In this paper we introduce a framework that aim to learn a landmark-free correspondence-free global representations of dynamic appearance manifolds. We use nonlinear dimensionality reduction to achieve an embedding of the global deformation manifold that preserves the geometric structure of the manifold. Given such embedding, a nonlinear mapping is learned from the embedding space into the visual input space. Therefore, any visual input is represented by a linear combination of nonlinear bases functions centered along the manifold in the embedding space. We also show how approximate solution for the inverse mapping can be obtained in a closed form which facilitate recovery of the intrinsic body configuration. We use the framework to learn the gait manifold as an example of a dynamic shape manifold, as well as to learn the manifolds for some simple gestures and facial expressions as examples of dynamic appearance manifolds.
Citations
|
1770
|
Eigenfaces for recognition
– Turk, Pentland
- 1991
|
|
872
|
Principal Component Analysis
– Jolliffe
- 1986
|
|
750
|
Eigenfaecs vs fisherfaces: recognition using class specific linear projection
– Belhumer, Kriegman
- 1997
|
|
749
|
Visual Learning and Recognition of 3D Objects from Appearance
– Murase, Nayar
- 1995
|
|
601
|
Active shape models - their training and application
– Graham
- 1995
|
|
591
|
Nonlinear dimensionality reduction by locally linear embedding
– Roweis, Saul
- 2000
|
|
530
|
Networks for approximation and learning
– Poggio, Girosi
- 1990
|
|
346
|
Eigentracking: Robust matching and tracking of articulated objects using a view-based representation
– Black, Jepson
- 1998
|
|
202
|
Multidimensional scaling
– Cox, Cox
- 1994
|
|
148
|
Voice puppetry
– Brand
- 1999
|
|
110
|
Discriminant analysis of principal components for face recognition," presented at Automatic Face and Gesture Recognition
– Zhao, Chellappa, et al.
- 1998
|
|
102
|
Image representation for visual learning
– Beymer, Poggio
- 1996
|
|
87
|
Probabilistic tracking in a metric space
– Toyama, Blake
- 2001
|
|
68
|
Separating style and content with bilinear models. Neural Computation
– Tenenbaum, Freeman
- 2000
|
|
59
|
Nonlinear manifold learning for visual speech recognition
– Bregler, Omohundro
- 1995
|
|
50
|
C.: Inferring 3D body pose from silhouettes using activity manifold learning
– Elgammal, Lee
- 2004
|
|
49
|
Mapping a manifold of perceptual observations
– Tenenbaum
- 1998
|
|
45
|
Face recognition from long-term observations
– Shakhnarovich, Fisher, et al.
- 2002
|
|
36
|
Parametric appearance representation
– Nayar, Murase, et al.
- 1996
|
|
32
|
Separating style and content on a nonlinear manifold
– Elgammal, Lee
- 2004
|
|
29
|
Learning statistical models of human motion
– Bowden
|
|
23
|
A unifying theorem for spectral embedding and clustering
– Brand, Huang
- 2003
|
|
22
|
Automatic Detection and Tracking of Human Motion with a View-Based Representation
– Fablet, Black
- 2002
|
|
21
|
Learning graphical models of images, videos and their spatial transformations
– Frey, Jojic
- 2000
|
|
12
|
Active object recognition in parametric eigenspace
– Borotschnig, Paletta, et al.
- 1998
|
|
7
|
Principal component analysis over continuous subspaces and intersection of half-spaces
– Levin, Shashua
- 2002
|
|
2
|
Dynamism of a dog on a leash’ or behavior classification by eigen-decomposition of periodic motions
– Goldenberg, Kimmel, et al.
- 2002
|
|
1
|
Multilinear analysis of image ensebles: Tensorfaces
– Vasilescu, Terzopoulos
- 2002
|
