Name
Abstract | ||
|---|---|---|
To deal with multi-modality in human pose estimation, mixture models or local models are introduced. However, problems with over-fitting and generalization are caused by our necessarily limited data, and the regression parameters need to be determined without resorting to slow and processor-hungry techniques, such as cross validation. To compensate these problems, we have developed a semi-parametric regression model in latent space with variational inference. Our method performed competitively in comparison to other current methods. |
Year | DOI | Venue |
|---|---|---|
2011 | 10.1109/ICIP.2011.6116293 | 2011 18th IEEE International Conference on Image Processing |
Keywords | Field | DocType |
Image motion analysis,unsupervised learning,regression model,latent variable model | Regression,Pattern recognition,Regression analysis,Computer science,Inference,Latent variable model,Pose,Artificial intelligence,Semiparametric model,Cross-validation,Mixture model | Conference |
Volume | Issue | ISSN |
null | null | 1522-4880 |
ISBN | Citations | PageRank |
978-1-4577-1304-0 | 0 | 0.34 |
References | Authors | |
6 | 6 | |
Name | Order | Citations | PageRank |
|---|---|---|---|
| Yan Tian | 1 | 25 | 2.14 |
| Yonghua Jia | 2 | 4 | 0.73 |
| Yuan Shi | 3 | 6 | 2.24 |
| Yong Liu | 4 | 0 | 0.34 |
| Hao Ji | 5 | 145 | 15.60 |
| Leonid Sigal | 6 | 2163 | 124.33 |