Incorporating Scene Context and Object Layout into Appearance Modeling

Hamid Izadinia, Fereshteh Sadeghi, Ali Farhadi

CVPR 2014

doi:10.1109/CVPR.2014.37 /cvpr/2014/izadinia2014cvpr-incorporating/

Abstract

A scene category imposes tight distributions over the kind of objects that might appear in the scene, the appearance of those objects and their layout. In this paper, we propose a method to learn scene structures that can encode three main interlacing components of a scene: the scene category, the context-specific appearance of objects, and their layout. Our experimental evaluations show that our learned scene structures outperform state-of-the-art method of Deformable Part Models in detecting objects in a scene. Our scene structure provides a level of scene understanding that is amenable to deep visual inferences. The scene structures can also generate features that can later be used for scene categorization. Using these features, we also show promising results on scene categorization.

PDF CVPR Semantic Scholar

Cite

Text

Izadinia et al. "Incorporating Scene Context and Object Layout into Appearance Modeling." Conference on Computer Vision and Pattern Recognition, 2014. doi:10.1109/CVPR.2014.37

Markdown

[Izadinia et al. "Incorporating Scene Context and Object Layout into Appearance Modeling." Conference on Computer Vision and Pattern Recognition, 2014.](https://mlanthology.org/cvpr/2014/izadinia2014cvpr-incorporating/) doi:10.1109/CVPR.2014.37

BibTeX

@inproceedings{izadinia2014cvpr-incorporating,
  title     = {{Incorporating Scene Context and Object Layout into Appearance Modeling}},
  author    = {Izadinia, Hamid and Sadeghi, Fereshteh and Farhadi, Ali},
  booktitle = {Conference on Computer Vision and Pattern Recognition},
  year      = {2014},
  doi       = {10.1109/CVPR.2014.37},
  url       = {https://mlanthology.org/cvpr/2014/izadinia2014cvpr-incorporating/}
}