Abnormal Object Detection by Canonical Scene-Based Contextual Model

@inproceedings{Park2012AbnormalOD,
  title={Abnormal Object Detection by Canonical Scene-Based Contextual Model},
  author={Sangdon Park and Wonsik Kim and Kyoung Mu Lee},
  booktitle={ECCV},
  year={2012}
}
Contextual modeling is a critical issue in scene understanding. Object detection accuracy can be improved by exploiting tendencies that are common among object configurations. However, conventional contextual models only exploit the tendencies of normal objects; abnormal objects that do not follow the same tendencies are hard to detect through contextual model. This paper proposes a novel generative model that detects abnormal objects by meeting four proposed criteria of success. This model… CONTINUE READING
BETA

Similar Papers

Citations

Publications citing this paper.
SHOWING 1-7 OF 7 CITATIONS

Toward a Taxonomy and Computational Models of Abnormalities in Images

VIEW 8 EXCERPTS
CITES BACKGROUND, METHODS & RESULTS
HIGHLY INFLUENCED

What’s Wrong with That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 7 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Landmark detection with surprise saliency using convolutional neural networks

  • 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
  • 2016
VIEW 1 EXCERPT
CITES BACKGROUND

Object-Centric Anomaly Detection by Attribute-Based Reasoning

  • 2013 IEEE Conference on Computer Vision and Pattern Recognition
  • 2013
VIEW 3 EXCERPTS
CITES BACKGROUND

References

Publications referenced by this paper.
SHOWING 1-10 OF 24 REFERENCES

Exploiting hierarchical context on a large database of object categories

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 8 EXCERPTS
HIGHLY INFLUENTIAL

Context models and out-of-context objects

  • Pattern Recognition Letters
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

SUN database: Large-scale scene recognition from abbey to zoo

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 2 EXCERPTS

What is an object?

  • 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition
  • 2010
VIEW 1 EXCERPT