Efficient Visual Search of Videos Cast as Text Retrieval

  title={Efficient Visual Search of Videos Cast as Text Retrieval},
  author={Josef Sivic and Andrew Zisserman},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  • Josef Sivic, Andrew Zisserman
  • Published 2009
  • Computer Science, Medicine
  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • We describe an approach to object retrieval which searches for and localizes all the occurrences of an object in a video, given a query image of the object. The object is represented by a set of viewpoint invariant region descriptors so that recognition can proceed successfully despite changes in viewpoint, illumination and partial occlusion. The temporal continuity of the video within a shot is used to track the regions in order to reject those that are unstable. Efficient retrieval is… CONTINUE READING
    Contextual Query Expansion for Image Retrieval
    • 49
    • Highly Influenced
    Randomized visual phrases for object search
    • 76
    • Highly Influenced
    • PDF
    Computer Vision - Algorithms and Applications
    • 3,141
    • Highly Influenced
    • PDF
    Pyramid of Spatial Relatons for Scene-Level Land Use Classification
    • 162
    • PDF
    Video Object Retrieval by Trajectory and Appearance
    • 21
    Advancing large scale object retrieval
    • 6
    • PDF
    Efficient Subframe Video Alignment Using Short Descriptors
    • 36
    • PDF


    Publications referenced by this paper.
    Video Google: a text retrieval approach to object matching in videos
    • 6,407
    • PDF
    Object retrieval with large vocabularies and fast spatial matching
    • 2,694
    • PDF
    Scalable Recognition with a Vocabulary Tree
    • 3,778
    • PDF
    A Combined Corner and Edge Detector
    • 13,150
    • PDF
    A performance evaluation of local descriptors
    • 2,882
    • PDF
    The Anatomy of a Large-Scale Hypertextual Web Search Engine
    • 14,407
    • PDF
    Object Level Grouping for Video Shots
    • 175
    • PDF