Corpus ID: 15857769

Context Forest for efficient object detection with large mixture models

  title={Context Forest for efficient object detection with large mixture models},
  author={Davide Modolo and A. Vezhnevets and V. Ferrari},
  • Davide Modolo, A. Vezhnevets, V. Ferrari
  • Published 2015
  • Computer Science
  • ArXiv
  • We present Context Forest (ConF), a technique for predicting properties of the objects in an image based on its global appearance. Compared to standard nearest-neighbour techniques, ConF is more accurate, fast and memory efficient. We train ConF to predict which aspects of an object class are likely to appear in a given image (e.g. which viewpoint). This enables to speed-up multi-component object detectors, by automatically selecting the most relevant components to run on that image. This is… CONTINUE READING

    Figures, Tables, and Topics from this paper.


    Publications referenced by this paper.
    Object Detection with Discriminatively Trained Part Based Models
    • 8,333
    • PDF
    Learning Spatial Context: Using Stuff to Find Things
    • 427
    • PDF
    Ensemble of exemplar-SVMs for object detection and beyond
    • 811
    • Highly Influential
    • PDF
    Do We Need More Training Data or Better Models for Object Detection?
    • 167
    • PDF
    Blocks That Shout: Distinctive Parts for Scene Classification
    • 393
    • PDF