e technique is based on abstract execution profiles, called event signatures, and it operates at a higher level of abstraction than, for example, commonly used instruction-set sim...
In this paper we present a framework combining differential geometry and scale-space to show that local geometric invariants of image contours such as tangent, curvature and deriv...
In this paper, a novel multi-cue collaborative kernel tracking algorithm is proposed. A new constraint based on the property of cross ratio invariant enables tracking of objects i...
Invariant feature representations for 3D objects are one of the basic needs in 3D object retrieval and classification. One tool to obtain rotation invariance are Spherical Harmonic...
This paper presents a novel line-based affine invariant object location methodology. Our algorithm employs a new line-based transformation space decomposition technique to exploit...