We present a method for automatically learning discriminative image patches for the recognition of given object classes. The approach applies discriminative training of log-linear...
We introduce a novel set of features for robust object recognition. Each element of this set is a complex feature obtained by combining position- and scale-tolerant edgedetectors ...
Visually extracted 2D and 3D information have their own advantages and disadvantages that complement each other. Therefore, it is important to be able to switch between the differ...
Emre Baseski, Nicolas Pugeault, Sinan Kalkan, Dirk...
We present a two-layer hierarchical formulation to exploit different levels of contextual information in images for robust classification. Each layer is modeled as a conditional f...
This paper presents a probabilistic part-based approach for texture and object recognition. Textures are represented using a part dictionary found by quantizing the appearance of ...