Given a large collection of objects, finding all pairs of similar objects, namely similarity join, is widely used to solve various problems in many application domains.Computation ...
Dongjoo Lee, Jaehui Park, Junho Shim, Sang-goo Lee
Most recent class-level object recognition systems work with visual words, i.e., vector quantized local descriptors. In this paper we examine the feasibility of a dataindependent ...
Visual dictionaries have been successfully applied to "bags-of-points" image representations for generic object recognition. Usually the choice of low-level interest reg...
We present a method to classify images into different categories of pornographic content to create a system for filtering pornographic images from network traffic. Although differ...
A new feature descriptor is presented for object and scene recognition. The new approach, called CDIKP, uniquely combines the scale-invariant feature detection with a robust proje...