Learning Class-to-Image Distance with Object Matchings

Guang-Tong Zhou, Tian Lan, Weilong Yang, Greg Mori

CVPR 2013

doi:10.1109/CVPR.2013.108 /cvpr/2013/zhou2013cvpr-learning/

Abstract

We conduct image classification by learning a class-toimage distance function that matches objects. The set of objects in training images for an image class are treated as a collage. When presented with a test image, the best matching between this collage of training image objects and those in the test image is found. We validate the efficacy of the proposed model on the PASCAL 07 and SUN 09 datasets, showing that our model is effective for object classification and scene classification tasks. State-of-the-art image classification results are obtained, and qualitative results demonstrate that objects can be accurately matched.

PDF CVPR Semantic Scholar

Cite

Text

Zhou et al. "Learning Class-to-Image Distance with Object Matchings." Conference on Computer Vision and Pattern Recognition, 2013. doi:10.1109/CVPR.2013.108

Markdown

[Zhou et al. "Learning Class-to-Image Distance with Object Matchings." Conference on Computer Vision and Pattern Recognition, 2013.](https://mlanthology.org/cvpr/2013/zhou2013cvpr-learning/) doi:10.1109/CVPR.2013.108

BibTeX

@inproceedings{zhou2013cvpr-learning,
  title     = {{Learning Class-to-Image Distance with Object Matchings}},
  author    = {Zhou, Guang-Tong and Lan, Tian and Yang, Weilong and Mori, Greg},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2013},
  doi       = {10.1109/CVPR.2013.108},
  url       = {https://mlanthology.org/cvpr/2013/zhou2013cvpr-learning/}
}