Computer Vision: A Modern Approach
Computer Vision: A Modern Approach
Training products of experts by minimizing contrastive divergence
Neural Computation
Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data
ICML '01 Proceedings of the Eighteenth International Conference on Machine Learning
A Mixed-State Condensation Tracker with Automatic Model-Switching
ICCV '98 Proceedings of the Sixth International Conference on Computer Vision
Energy-based models for sparse overcomplete representations
The Journal of Machine Learning Research
Discriminative Density Propagation for 3D Human Motion Estimation
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Fields of Experts: A Framework for Learning Image Priors
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Online Selection of Discriminative Tracking Features
IEEE Transactions on Pattern Analysis and Machine Intelligence
Variational Learning for Switching State-Space Models
Neural Computation
Conditional random fields for activity recognition
Proceedings of the 6th international joint conference on Autonomous agents and multiagent systems
| Hi-index | 0.00 |
We propose a new model for the probabilistic estimation of continuous state variables from a sequence of observations, such as tracking the position of an object in video. This mapping is modeled as a product of dynamics experts (features relating the state at adjacent time-steps) and observation experts (features relating the state to the image sequence). Individual features are flexible in that they can switch on or off at each time-step depending on their inferred relevance (or on additional side information), and discriminative in that they need not model the full generative likelihood of the data. When trained conditionally, this permits the inclusion of a broad range of rich features (for example, features relying on observations from multiple time-steps), and allows the relevance of features to be learned from labeled sequences.