Name
Abstract | ||
|---|---|---|
We propose a novel statistical manifold modeling approach that is capable of classifying poses of object categories from video sequences by simultaneously minimizing the intra-class variability and maximizing inter-pose distance. Following the intuition that an object part based representation and a suitable part selection process may help achieve our purpose, we formulate the part selection problem from a statistical manifold modeling perspective and treat part selection as adjusting the manifold of the object (parameterized by pose) by means of the manifold “alignment” and “expansion” operations. We show that manifold alignment and expansion are equivalent to minimizing the intra-class distance given a pose while increasing the inter-pose distance given an object instance respectively. We formulate and solve this (otherwise intractable) part selection problem as a combinatorial optimization problem using graph analysis techniques. Quantitative and qualitative experimental analysis validates our theoretical claims. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICCV.2011.6126340 | ICCV |
Keywords | Field | DocType |
optimisation,manifold expansion,video signal processing,object part,object category,suitable part selection process,video sequences,graph analysis techniques,statistical analysis,object instance,statistical manifold modeling perspective,combinatorial optimization problem,part selection process,pose estimation,intraclass distance,pose classification,image classification,manifold alignment,quantitative experimental analysis,image sequences,object detection,expansion operations,novel statistical manifold modeling,intra-class variability,graph theory,robust object,inter-pose distance,robust object pose estimation,part selection,qualitative experimental analysis,part selection problem,experimental analysis,optimization,trajectory,statistical manifold,trajectory optimization,manifolds,estimation | Graph theory,Object detection,Computer vision,Parameterized complexity,Pattern recognition,Computer science,Manifold alignment,Power graph analysis,Pose,Artificial intelligence,Statistical manifold,Manifold | Conference |
Volume | Issue | ISSN |
2011 | 1 | 1550-5499 |
ISBN | Citations | PageRank |
978-1-4577-1101-5 | 18 | 0.71 |
References | Authors | |
23 | 4 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Liang Mei | 1 | 25 | 1.20 |
| Jingen Liu | 2 | 807 | 34.41 |
| Alfred O. Hero III | 3 | 2600 | 301.12 |
| Silvio Savarese | 4 | 3975 | 161.69 |