Attribute and simile classifiers for face verification

@article{Kumar2009AttributeAS,
  title={Attribute and simile classifiers for face verification},
  author={Neeraj Kumar and Alexander C. Berg and Peter N. Belhumeur and Shree K. Nayar},
  journal={2009 IEEE 12th International Conference on Computer Vision},
  year={2009},
  pages={365-372}
}
We present two novel methods for face verification. Our first method - “attribute” classifiers - uses binary classifiers trained to recognize the presence or absence of describable aspects of visual appearance (e.g., gender, race, and age). Our second method - “simile” classifiers - removes the manual labeling required for attribute classification and instead learns the similarity of faces, or regions of faces, to specific reference people. Neither method requires costly, often brittle… CONTINUE READING

Results and Topics from this paper.

Key Quantitative Results

  • Furthermore, both the attribute and simile classifiers improve on the current state-of-the-art for the LFW data set, reducing the error rates compared to the current best by 23.92% and 26.34%, respectively, and 31.68% when combined.

Explore Further: Topics Discussed in This Paper

Citations

Publications citing this paper.
SHOWING 1-10 OF 977 CITATIONS, ESTIMATED 33% COVERAGE

Face retrieval using frequency decoded local descriptor

  • Multimedia Tools and Applications
  • 2018
VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Deep learning for content-based video retrieval in film and television production

  • Multimedia Tools and Applications
  • 2017
VIEW 4 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Empowering Simple Binary Classifiers for Image Set Based Face Recognition

  • International Journal of Computer Vision
  • 2017
VIEW 11 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Hallucinating Compressed Face Images

  • International Journal of Computer Vision
  • 2017
VIEW 12 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

Simultaneous Feature and Dictionary Learning for Image Set Based Face Recognition

  • IEEE Transactions on Image Processing
  • 2017
VIEW 14 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

A Novel Solution to Test Face Recognition Methods on the Training Data Set

VIEW 9 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Face Recognition based on Deep Neural Network

VIEW 6 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Face recognition in uncontrolled environments

  • 2015
VIEW 16 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2009
2019

CITATION STATISTICS

  • 179 Highly Influenced Citations

  • Averaged 126 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-10 OF 36 REFERENCES

Estimating age

A. Gallagher, T. Chen
  • gender, and identity using first name priors. CVPR
  • 2008
VIEW 1 EXCERPT

LFW results using a combined Nowak plus MERL recognizer

G. Huang, M. Jones, E. Learned-Miller
  • 2008
VIEW 1 EXCERPT

A Study of Face Recognition as People Age

  • 2007 IEEE 11th International Conference on Computer Vision
  • 2007
VIEW 1 EXCERPT

Face Recognition Algorithms Surpass Humans Matching Faces Over Changes in Illumination

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
VIEW 1 EXCERPT

Learning Visual Similarity Measures for Comparing Never Seen Objects

  • 2007 IEEE Conference on Computer Vision and Pattern Recognition
  • 2007
VIEW 2 EXCERPTS

Similar Papers

Loading similar papers…