Loading...
Please wait, while we are loading the content...
Similar Documents
Generative Modeling for Continuous Non-Linearly Embedded Visual Inference (2004)
| Content Provider | CiteSeerX |
|---|---|
| Author | Jepson, Allan Sminchisescu, Cristian |
| Abstract | Many difficult visual perception problems, like 3D human motion estimation, can be formulated in terms of inference using complex generative models, defined over high-dimensional state spaces. Despite progress, optimizing such models is difficult because prior knowledge cannot be flexibly integrated in order to reshape an initially designed representation space. Nonlinearities, inherent sparsity of high-dimensional training sets, and lack of global continuity makes dimensionality reduction challenging and lowdimensional search inefficient. To address these problems, we present a learning and inference algorithm that restricts visual tracking to automatically extracted, non-linearly embedded, lowdimensional spaces. This formulation produces a layered generative model with reduced state representation, that can be estimated using efficient continuous optimization methods. Our prior flattening method allows a simple analytic treatment of low-dimensional intrinsic curvature constraints, and allows consistent interpolation operations. We analyze reduced manifolds for human interaction activities, and demonstrate that the algorithm learns continuous generative models that are useful for tracking and for the reconstruction of 3D human motion in monocular video. 1. |
| File Format | |
| Publisher Date | 2004-01-01 |
| Access Restriction | Open |
| Subject Keyword | Global Continuity Inherent Sparsity Efficient Continuous Optimization Method Low-dimensional Intrinsic Curvature Constraint Prior Knowledge Cannot Prior Flattening Method Representation Space Human Motion Estimation Layered Generative Model Simple Analytic Treatment Continuous Non-linearly Embedded Visual Inference Reduced State Representation Human Motion Lowdimensional Search Inefficient High-dimensional Training Set Consistent Interpolation Operation Inference Algorithm Dimensionality Reduction Challenging Generative Modeling Human Interaction Activity Reduced Manifold Complex Generative Model Lowdimensional Space Many Difficult Visual Perception Problem Continuous Generative Model Monocular Video High-dimensional State Space |
| Content Type | Text |
