Semi-supervised nonlinear dimensionality reduction
ICML '06 Proceedings of the 23rd international conference on Machine learning
Temporal motion models for monocular and multiview 3D human body tracking
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Viewpoint invariant exemplar-based 3D human tracking
Computer Vision and Image Understanding - Special issue on modeling people: Vision-based understanding of a person's shape, appearance, movement, and behaviour
Value Regularization and Fenchel Duality
The Journal of Machine Learning Research
Learning to Transform Time Series with a Few Examples
IEEE Transactions on Pattern Analysis and Machine Intelligence
Pattern Recognition Letters
Efficient illumination independent appearance-based face tracking
Image and Vision Computing
Coupled Visual and Kinematic Manifold Models for Tracking
International Journal of Computer Vision
Physics-Based Person Tracking Using the Anthropomorphic Walker
International Journal of Computer Vision
Shared latent dynamical model for human tracking from videos
MCAM'07 Proceedings of the 2007 international conference on Multimedia content analysis and mining
Manifold topological multi-resolution analysis method
Pattern Recognition
Invariant object recognition and pose estimation with slow feature analysis
Neural Computation
Learning nonlinear manifolds from time series
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part II
Learning basic patterns from repetitive texture surfaces under non-rigid deformations
ICIAR'07 Proceedings of the 4th international conference on Image Analysis and Recognition
Proceedings of the 2013 Conference on Eye Tracking South Africa
Hi-index | 0.00 |
The appearance of dynamic scenes is often largely governed by a latent low-dimensional dynamic process. We show how to learn a mapping from video frames to this low-dimensional representation by exploiting the temporal coherence between frames and supervision from a user. This function maps the frames of the video to a low-dimensional sequence that evolves according to Markovian dynamics. This ensures that the recovered low-dimensional sequence represents a physically meaningful process. We relate our algorithm to manifold learning, semi-supervised learning, and system identification, and demonstrate it on the tasks of tracking 3D rigid objects, deformable bodies, and articulated bodies. We also show how to use the inverse of this mapping to manipulate video.