Abstract | ||
---|---|---|
We introduce a new class of probabilistic latent vari- able model called the Implicit Mixture of Conditional Re- stricted Boltzmann Machines (imCRBM) for use in human pose tracking. Key properties of the imCRBM are as fol- lows: (1) learning is linear in the number of training exem- plars so it can be learned from large datasets; (2) it learns coherent models of multiple activities; (3) it automatically discovers atomic "movemes"; and (4) it can infer transi- tions between activities, even when such transitions are not present in the training set. We describe the model and how it is learned and we demonstrate its use in the context of Bayesian filtering for multi-view and monocular pose track- ing. The model handles difficult scenarios including multi- ple activities and transitions among activities. We report state-of-the-art results on the HumanEva dataset. |
Year | DOI | Venue |
---|---|---|
2010 | 10.1109/CVPR.2010.5540157 | Computer Vision and Pattern Recognition |
Keywords | Field | DocType |
Boltzmann machines,filtering theory,image motion analysis,pose estimation,probability,3D human pose tracking,Bayesian filtering,HumanEva dataset,dynamical binary latent variable models,imCRBM,implicit mixture of conditional restricted Boltzmann machines,monocular pose tracking,multiview pose tracking | Data modeling,Pose tracking,Computer science,Pose,Latent variable,Artificial intelligence,Probabilistic logic,Monocular,Binary number,Computer vision,Pattern recognition,Latent variable model,Machine learning | Conference |
Volume | Issue | ISSN |
2010 | 1 | 1063-6919 |
ISBN | Citations | PageRank |
978-1-4244-6984-0 | 72 | 2.14 |
References | Authors | |
24 | 4 |
Name | Order | Citations | PageRank |
---|---|---|---|
Graham W. Taylor | 1 | 1523 | 127.22 |
Leonid Sigal | 2 | 2163 | 124.33 |
David J. Fleet | 3 | 5236 | 550.74 |
geoffrey e hinton | 4 | 40435 | 4751.69 |