Describing objects by their attributes

@article{Farhadi2009DescribingOB,
  title={Describing objects by their attributes},
  author={Ali Farhadi and Ian Endres and Derek Hoiem and David A. Forsyth},
  journal={2009 IEEE Conference on Computer Vision and Pattern Recognition},
  year={2009},
  pages={1778-1785}
}
We propose to shift the goal of recognition from naming to describing. Doing so allows us not only to name familiar objects, but also: to report unusual aspects of a familiar object (“spotty dog”, not just “dog”); to say something about unfamiliar objects (“hairy and four-legged”, not just “unknown”); and to learn how to recognize new objects with few or no visual examples. Rather than focusing on identity assignment, we make inferring attributes the core problem of recognition. These… CONTINUE READING

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-10 OF 1,150 CITATIONS

Recent Advances in Zero-Shot Recognition: Toward Data-Efficient Understanding of Visual Content

  • IEEE Signal Processing Magazine
  • 2018
VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Recent Advances in Zero-shot Recognition

  • ArXiv
  • 2017
VIEW 13 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Comparing Attribute Classifiers for Interactive Language Grounding

VIEW 24 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Domain Transfer Learning for Object and Action Recognition

VIEW 28 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

From Visual Attributes to Adjectives through Decompositional Distributional Semantics

  • Transactions of the Association for Computational Linguistics
  • 2015
VIEW 10 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Learning semantic attributes via a common latent space

  • 2014 International Conference on Computer Vision Theory and Applications (VISAPP)
  • 2014
VIEW 13 EXCERPTS
CITES METHODS, RESULTS & BACKGROUND
HIGHLY INFLUENCED

AI Painting: An Aesthetic Painting Generation System

VIEW 4 EXCERPTS
CITES BACKGROUND
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 187 Highly Influenced Citations

  • Averaged 116 Citations per year from 2017 through 2019

References

Publications referenced by this paper.
SHOWING 1-10 OF 33 REFERENCES

Learning to detect unseen object classes by between-class attribute transfer

  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • 2009
VIEW 1 EXCERPT

A discriminatively trained, multiscale, deformable part model

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 1 EXCERPT

Efros . Recognition by association via learning per - exemplar distances

Tomasz Malisiewicz, A. Alexei
  • The big book of concepts
  • 2008

Recognition by association via learning per-exemplar distances

  • 2008 IEEE Conference on Computer Vision and Pattern Recognition
  • 2008
VIEW 1 EXCERPT

Utility data annotation with Amazon Mechanical Turk

  • 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops
  • 2008
VIEW 2 EXCERPTS