Object Detection with Discriminatively Trained Part-Based Models

@article{Forsyth2014ObjectDW,
  title={Object Detection with Discriminatively Trained Part-Based Models},
  author={David A. Forsyth},
  journal={IEEE Computer},
  year={2014},
  volume={47},
  pages={6-7}
}
• Lighting. When an object is in bright light, it looks brighter than when it’s in shadow, so a program can’t just look at image intensity values. • Within-class variation. Different instances of the same kind of object can look quite different to one another. For example, a green station wagon and a red convertible are both cars, so a program can’t simply compare a picture to one example. • Aspect. The same object can look very different when viewed at from different directions—pick up a book… CONTINUE READING

Similar Papers

Topics from this paper.

Citations

Publications citing this paper.
SHOWING 1-10 OF 5,360 CITATIONS, ESTIMATED 83% COVERAGE

Fast Pedestrian Detection in Surveillance Video Based on Soft Target Training of Shallow Random Forest

  • IEEE Access
  • 2019
VIEW 15 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

A High-Precision Eccentric Tracking Algorithm of Laser Interfering Targets Based on Kernel Correlation Filtering

  • 2018 IEEE 3rd International Conference on Image, Vision and Computing (ICIVC)
  • 2018
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

A NOVEL SEMI-SUPERVISED DETECTION APPROACH WITH WEAK ANNOTATION

  • 2018 IEEE Southwest Symposium on Image Analysis and Interpretation (SSIAI)
  • 2018
VIEW 7 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

End-to-End Learning of Latent Deformable Part-Based Representations for Object Detection

  • International Journal of Computer Vision
  • 2018
VIEW 11 EXCERPTS
CITES BACKGROUND & METHODS
HIGHLY INFLUENCED

Fast Automatic Vehicle Annotation for Urban Traffic Surveillance

  • IEEE Transactions on Intelligent Transportation Systems
  • 2018
VIEW 8 EXCERPTS
CITES METHODS
HIGHLY INFLUENCED

FILTER CITATIONS BY YEAR

2012
2019

CITATION STATISTICS

  • 1,285 Highly Influenced Citations

  • Averaged 580 Citations per year over the last 3 years

References

Publications referenced by this paper.
SHOWING 1-5 OF 5 REFERENCES

Montrer que aZ ∩ bZ est un idéal de Z

  • Montrer que aZ ∩ bZ est un idéal de Z

Montrer que l'ensemble aZ + bZ est un idéal de Z. (Rappel : un idéal de Z est un sous ensemble de Z non vide, stable par addition et par multiplication)

  • Montrer que l'ensemble aZ + bZ est un idéal de Z. (Rappel : un idéal de Z est un sous ensemble de Z non vide, stable par addition et par multiplication)

Montrer que si aZ + bZ = dZ, alors d est le pgcd de a et b

  • Montrer que si aZ + bZ = dZ, alors d est le pgcd de a et b

Montrer que si aZ ∩ bZ = dZ, alors d = ppcm(a, b)

  • Montrer que si aZ ∩ bZ = dZ, alors d = ppcm(a, b)

Rappel : aZ = {a

Montrer Que A|b Si Et Seulement Si Bz ⊂ Az
  • Rappel : aZ = {a