The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...
Learning visual classifiers for object recognition from weakly labeled data requires determining correspondence between image regions and semantic object classes. Most approaches u...
We present a novel 3D object retrieval method that relies upon a hybrid descriptor which is composed of 2D features based on depth buffers and 3D features based on spherical harmo...
Panagiotis Papadakis, Ioannis Pratikakis, Theohari...
Kernel descriptors provide a unified way to generate rich visual feature sets by turning pixel attributes into patch-level features, and yield impressive results on many object rec...
Liefeng Bo, Kevin Lai, Xiaofeng Ren and Dieter Fox
In this paper the problem of matching freeform surface features against measured point data is studied. The motivation for this investigation is the recent demand for fast and rob...
Joris S. M. Vergeest, Sander Spanjaard, Jos J. O. ...