An empirical study of context in object detection

  title={An empirical study of context in object detection},
  author={S. Divvala and Derek Hoiem and J. Hays and Alexei A. Efros and M. Hebert},
  journal={2009 IEEE Conference on Computer Vision and Pattern Recognition},
  • S. Divvala, Derek Hoiem, +2 authors M. Hebert
  • Published 2009
  • Computer Science
  • 2009 IEEE Conference on Computer Vision and Pattern Recognition
  • This paper presents an empirical evaluation of the role of context in a contemporary, challenging object detection task - the PASCAL VOC 2008. Previous experiments with context have mostly been done on home-grown datasets, often with non-standard baselines, making it difficult to isolate the contribution of contextual information. In this work, we present our analysis on a standard dataset, using top-performing local appearance detectors as baseline. We evaluate several different sources of… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    The Role of Context for Object Detection and Semantic Segmentation in the Wild
    • 628
    • PDF
    Quantifying and Transferring Contextual Information in Object Detection
    • 43
    • PDF
    Contextual Object Detection With Spatial Context Prototypes
    • 9
    Multi-class object localization by combining local contextual interactions
    • 89
    • PDF
    Object Localization with Global and Local Context Kernels
    • 47
    • PDF
    Contextual boost for pedestrian detection
    • 75
    • Highly Influenced
    • PDF
    A Tree-Based Context Model for Object Recognition
    • 133
    • PDF


    Publications referenced by this paper.
    A Critical View of Context
    • 184
    • PDF
    The role of context in object recognition
    • 770
    • PDF
    Objects in Context
    • 697
    • PDF
    Statistical Context Priming for Object Detection
    • 173
    • PDF
    Learning Spatial Context: Using Stuff to Find Things
    • 428
    • PDF
    Histograms of oriented gradients for human detection
    • 25,817
    • PDF
    A hierarchical field framework for unified context-based classification
    • 277
    • PDF
    Scene Segmentation Using the Wisdom of Crowds
    • 47
    • PDF
    A Statistical Model for General Contextual Object Recognition
    • 310
    • PDF
    LabelMe: A Database and Web-Based Tool for Image Annotation
    • 2,676
    • PDF