Details
| Originalsprache | Englisch |
|---|---|
| Titel des Sammelwerks | 2013 IEEE Conference on Computer Vision and Pattern Recognition |
| Untertitel | CVPR 2013 |
| Seiten | 755-762 |
| Seitenumfang | 8 |
| ISBN (elektronisch) | 978-1-5386-5672-3 |
| Publikationsstatus | Veröffentlicht - 2013 |
| Veranstaltung | 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013 - Portland, OR, USA / Vereinigte Staaten Dauer: 23 Juni 2013 → 28 Juni 2013 |
Publikationsreihe
| Name | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition |
|---|---|
| ISSN (Print) | 1063-6919 |
Abstract
In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labeling information. Our method is based on generative feature models, i.e., regression functions learned from local descriptors of the same patch collected under different viewpoints. The individual generative models are then clustered in order to create class generative models which form the class representation. At run-time, the pose of the query image is estimated in a maximum a posteriori fashion by combining the regression functions belonging to the matching clusters. We evaluate our approach on the EPFL car dataset and the Pointing'04 face dataset. Experimental results show that our method outperforms by 10% the state-of-the-art in the first dataset and by 9% in the second.
ASJC Scopus Sachgebiete
- Informatik (insg.)
- Software
- Informatik (insg.)
- Maschinelles Sehen und Mustererkennung
Zitieren
- Standard
- Harvard
- Apa
- Vancouver
- BibTex
- RIS
2013 IEEE Conference on Computer Vision and Pattern Recognition: CVPR 2013. 2013. S. 755-762 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).
Publikation: Beitrag in Buch/Bericht/Sammelwerk/Konferenzband › Aufsatz in Konferenzband › Forschung › Peer-Review
}
TY - GEN
T1 - Class Generative Models based on Feature Regression for Pose Estimation of Object Categories
AU - Fenzi, Michele
AU - Leal-Taixe, Laura
AU - Rosenhahn, Bodo
AU - Ostermann, Jorn
PY - 2013
Y1 - 2013
N2 - In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labeling information. Our method is based on generative feature models, i.e., regression functions learned from local descriptors of the same patch collected under different viewpoints. The individual generative models are then clustered in order to create class generative models which form the class representation. At run-time, the pose of the query image is estimated in a maximum a posteriori fashion by combining the regression functions belonging to the matching clusters. We evaluate our approach on the EPFL car dataset and the Pointing'04 face dataset. Experimental results show that our method outperforms by 10% the state-of-the-art in the first dataset and by 9% in the second.
AB - In this paper, we propose a method for learning a class representation that can return a continuous value for the pose of an unknown class instance using only 2D data and weak 3D labeling information. Our method is based on generative feature models, i.e., regression functions learned from local descriptors of the same patch collected under different viewpoints. The individual generative models are then clustered in order to create class generative models which form the class representation. At run-time, the pose of the query image is estimated in a maximum a posteriori fashion by combining the regression functions belonging to the matching clusters. We evaluate our approach on the EPFL car dataset and the Pointing'04 face dataset. Experimental results show that our method outperforms by 10% the state-of-the-art in the first dataset and by 9% in the second.
KW - categorization
KW - Continuous pose estimation
KW - feature learning
KW - generative models
UR - http://www.scopus.com/inward/record.url?scp=84887373554&partnerID=8YFLogxK
U2 - 10.1109/CVPR.2013.103
DO - 10.1109/CVPR.2013.103
M3 - Conference contribution
AN - SCOPUS:84887373554
T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
SP - 755
EP - 762
BT - 2013 IEEE Conference on Computer Vision and Pattern Recognition
T2 - 26th IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2013
Y2 - 23 June 2013 through 28 June 2013
ER -