ML Anthology

Context Aware Topic Model for Scene Recognition

Zhenxing Niu, Gang Hua, Xinbo Gao, Qi Tian
CVPR 2012 pp. 2743-2750
doi:10.1109/CVPR.2012.6247997 /cvpr/2012/niu2012cvpr-context/

Abstract

We present a discriminative latent topic model for scene recognition. The capacity of our model is originated from the modeling of two types of visual contexts, i.e., the category specific global spatial layout of different scene elements, and the reinforcement of the visual coherence in uniform local regions. In contrast, most previous methods for scene recognition either only modeled one of these two visual contexts, or just totally ignored both of them. We cast these two coupled visual contexts in a discriminative Latent Dirichlet Allocation framework, namely context aware topic model. Then scene recognition is achieved by Bayesian inference given a target image. Our experiments on several scene recognition benchmarks clearly demonstrated the advantages of the proposed model.

CVPR Semantic Scholar

Cite

Text

Niu et al. "Context Aware Topic Model for Scene Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247997

Markdown

[Niu et al. "Context Aware Topic Model for Scene Recognition." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/niu2012cvpr-context/) doi:10.1109/CVPR.2012.6247997

BibTeX

@inproceedings{niu2012cvpr-context,
  title     = {{Context Aware Topic Model for Scene Recognition}},
  author    = {Niu, Zhenxing and Hua, Gang and Gao, Xinbo and Tian, Qi},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2743-2750},
  doi       = {10.1109/CVPR.2012.6247997},
  url       = {https://mlanthology.org/cvpr/2012/niu2012cvpr-context/}
}