Learning Collections of Part Models for Object Recognition

Ian Endres, Kevin J. Shih, Johnston Jiaa, Derek Hoiem

CVPR 2013

doi:10.1109/CVPR.2013.126 /cvpr/2013/endres2013cvpr-learning/

Abstract

We propose a method to learn a diverse collection of discriminative parts from object bounding box annotations. Part detectors can be trained and applied individually, which simplifies learning and extension to new features or categories. We apply the parts to object category detection, pooling part detections within bottom-up proposed regions and using a boosted classifier with proposed sigmoid weak learners for scoring. On PASCAL VOC 2010, we evaluate the part detectors' ability to discriminate and localize annotated keypoints. Our detection system is competitive with the best-existing systems, outperforming other HOG-based detectors on the more deformable categories.

PDF CVPR Semantic Scholar

Cite

Text

Endres et al. "Learning Collections of Part Models for Object Recognition." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.126

Markdown

[Endres et al. "Learning Collections of Part Models for Object Recognition." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/endres2013cvpr-learning/) doi:10.1109/CVPR.2013.126

BibTeX

@inproceedings{endres2013cvpr-learning,
  title     = {{Learning Collections of Part Models for Object Recognition}},
  author    = {Endres, Ian and Shih, Kevin J. and Jiaa, Johnston and Hoiem, Derek},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.126},
  url       = {https://mlanthology.org/cvpr/2013/endres2013cvpr-learning/}
}