ML Anthology

SUN Attribute Database: Discovering, Annotating, and Recognizing Scene Attributes

Genevieve Patterson, James Hays
CVPR 2012 pp. 2751-2758
doi:10.1109/CVPR.2012.6247998 /cvpr/2012/patterson2012cvpr-sun/

Abstract

In this paper we present the first large-scale scene attribute database. First, we perform crowd-sourced human studies to find a taxonomy of 102 discriminative attributes. Next, we build the "SUN attribute database" on top of the diverse SUN categorical database. Our attribute database spans more than 700 categories and 14,000 images and has potential for use in high-level scene understanding and fine-grained scene recognition. We use our dataset to train attribute classifiers and evaluate how well these relatively simple classifiers can recognize a variety of attributes related to materials, surface properties, lighting, functions and affordances, and spatial envelope properties.

PDF CVPR Semantic Scholar

Cite

Text

Patterson and Hays. "SUN Attribute Database: Discovering, Annotating, and Recognizing Scene Attributes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012. doi:10.1109/CVPR.2012.6247998

Markdown

[Patterson and Hays. "SUN Attribute Database: Discovering, Annotating, and Recognizing Scene Attributes." IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2012.](https://mlanthology.org/cvpr/2012/patterson2012cvpr-sun/) doi:10.1109/CVPR.2012.6247998

BibTeX

@inproceedings{patterson2012cvpr-sun,
  title     = {{SUN Attribute Database: Discovering, Annotating, and Recognizing Scene Attributes}},
  author    = {Patterson, Genevieve and Hays, James},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year      = {2012},
  pages     = {2751-2758},
  doi       = {10.1109/CVPR.2012.6247998},
  url       = {https://mlanthology.org/cvpr/2012/patterson2012cvpr-sun/}
}