Abnormal Object Detection by Canonical Scene-Based Contextual Model

@inproceedings{Park2012AbnormalOD,
  title={Abnormal Object Detection by Canonical Scene-Based Contextual Model},
  author={S. Park and Wonsik Kim and Kyoung Mu Lee},
  booktitle={ECCV},
  year={2012}
}
  • S. Park, Wonsik Kim, Kyoung Mu Lee
  • Published in ECCV 2012
  • Computer Science
  • 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
    11 Citations

    Figures and Topics from this paper.

    Context-based abnormal object detection using the fully-connected conditional random fields
    • 5
    Scene-Aware Context Reasoning for Unsupervised Abnormal Event Detection in Videos
    • 1
    Detecting Strange Objects via Visual Attributes
    Landmark detection with surprise saliency using convolutional neural networks
    • F. Tang, D. Lyons, Daniel D. Leeds
    • Computer Science
    • 2016 IEEE International Conference on Multisensor Fusion and Integration for Intelligent Systems (MFI)
    • 2016
    Object-Centric Anomaly Detection by Attribute-Based Reasoning
    • 49
    • Highly Influenced
    • PDF
    Toward a Taxonomy and Computational Models of Abnormalities in Images
    • 10
    • Highly Influenced
    • PDF
    What’s Wrong with That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution
    • 9
    • Highly Influenced
    • PDF
    GODS: Generalized One-Class Discriminative Subspaces for Anomaly Detection
    • J. Wang, A. Cherian
    • Computer Science
    • 2019 IEEE/CVF International Conference on Computer Vision (ICCV)
    • 2019
    • 4
    • PDF
    How Much Time Do You Have? Modeling Multi-Duration Saliency
    • 3
    • PDF

    References

    SHOWING 1-10 OF 26 REFERENCES
    Contextual Models for Object Detection Using Boosted Random Fields
    • 406
    • PDF
    Exploiting hierarchical context on a large database of object categories
    • 295
    • Highly Influential
    • PDF
    Object Detection with Discriminatively Trained Part Based Models
    • 8,473
    • PDF
    Learning Spatial Context: Using Stuff to Find Things
    • 431
    • PDF
    Towards total scene understanding: Classification, annotation and segmentation in an automatic framework
    • 405
    • PDF
    Context models and out-of-context objects
    • 81
    • Highly Influential
    • PDF
    Context based object categorization: A critical survey
    • 320
    • PDF
    Putting Objects in Perspective
    • 470
    • PDF
    What is an object?
    • 894
    • PDF
    Object categorization using co-occurrence, location and appearance
    • 459
    • PDF