EigenTracking: Robust Matching and Tracking of Articulated Objects Using a View-Based Representation
International Journal of Computer Vision
Proceedings of the 27th annual conference on Computer graphics and interactive techniques
Estimation of parameters and eigenmodes of multivariate autoregressive models
ACM Transactions on Mathematical Software (TOMS)
Numerical Recipes in C: The Art of Scientific Computing
Numerical Recipes in C: The Art of Scientific Computing
Transformation-Invariant Clustering Using the EM Algorithm
IEEE Transactions on Pattern Analysis and Machine Intelligence
Mixtures of Local Linear Subspaces for Face Recognition
CVPR '98 Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Transformed Component Analysis: Joint Estimation of Spatial Transformations and Image Components
ICCV '99 Proceedings of the International Conference on Computer Vision-Volume 2 - Volume 2
Learning to Detect Multi-View Faces in Real-Time
ICDL '02 Proceedings of the 2nd International Conference on Development and Learning
A Framework for Modeling Appearance Change in Image Sequences
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Improved Fast Gauss Transform and Efficient Kernel Density Estimation
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Data Driven Image Models through Continuous Joint Alignment
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning appearance and transparency manifolds of occluded objects in layers
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Probabilistic models for joint clustering and time-warping of multidimensional curves
UAI'03 Proceedings of the Nineteenth conference on Uncertainty in Artificial Intelligence
Modeling the manifolds of images of handwritten digits
IEEE Transactions on Neural Networks
IEEE Transactions on Signal Processing
Learning appearance and transparency manifolds of occluded objects in layers
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
| Hi-index | 0.00 |
Dimensionality reduction techniques such as principal componentanalysis and factor analysis are used to discover a linear mappingbetween high-dimensional data samples and points in alower-dimensional subspace. Previously, Frey and Jojic introducedtransformation-invariant component analysis (TCA) to learn a linearmapping, invariant to a set of known form of globaltransformations. However, parameter estimation in that model usingthe previously-proposed expectation maximization (EM) algorithmrequired scalar operations in the order of N2where N is the dimensionality of each training example. Thisis prohibitive for many applications of interest such as modelingmid-to large-size images, where, for instance, iN may be ashigh as 786432 (512×512 RGB image). In this paper, we presentan efficient algorithm that reduces the computational requirementsto order of NlogN. With this speedup, we show theeffectiveness of transformation-invariant component analysis invarious applications including tracking, learning video textures,clustering, object recognition and object detection in images.Software for TCA can be downloaded from http://www.psi.toronto.edu/fastTCA.htm