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

@article{Wang2016WhatsWW,
  title={What’s Wrong with That Object? Identifying Images of Unusual Objects by Modelling the Detection Score Distribution},
  author={Peng Wang and L. Liu and C. Shen and Zi Huang and A. V. D. Hengel and H. Shen},
  journal={2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2016},
  pages={1573-1581}
}
  • Peng Wang, L. Liu, +3 authors H. Shen
  • Published 2016
  • Computer Science
  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • This paper studies the challenging problem of identifying unusual instances of known objects in images within an "open world" setting. That is, we aim to find objects that are members of a known class, but which are not typical of that class. Thus the "unusual object" should be distinguished from both the "regular object" and the "other objects". Such unusual objects may be of interest in many applications such as surveillance or quality control. We propose to identify unusual objects by… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    Automatic Understanding of Image and Video Advertisements
    • 53
    • Open Access
    Seeing What is Not There: Learning Context to Determine Where Objects are Missing
    • 16
    • Open Access
    An anomaly-introduced learning method for abnormal event detection
    • 15
    KÄDING ET AL.: ACTIVE LEARNING FOR REGRESSION TASKS WITH EMOC
    • 2018

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 22 REFERENCES
    Selective Search for Object Recognition
    • 3,540
    • Open Access
    The Pascal Visual Object Classes (VOC) Challenge
    • 8,114
    • Open Access
    Very Deep Convolutional Networks for Large-Scale Image Recognition
    • 39,022
    • Open Access
    Detecting Irregularities in Images and in Video
    • 300
    • Highly Influential
    • Open Access
    Context models and out-of-context objects
    • 75
    • Highly Influential
    • Open Access
    Efficient additive kernels via explicit feature maps
    • 459
    • Open Access
    Gaussian Processes for Machine Learning (Adaptive Computation and Machine Learning)
    • 1,818
    • Open Access
    Online detection of unusual events in videos via dynamic sparse coding
    • 331
    • Highly Influential
    • Open Access