This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hiera...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
A novel approach to scene categorization is proposed. Similar to previous works of [11, 15, 3, 12], we introduce an intermediate space, based on a low dimensional semantic "t...
We introduce a new image representation that encompasses both the general layout of groups of quantized local invariant descriptors as well as their relative frequency. A graph of...
Parameterized Appearance Models (PAMs) (e.g. eigentracking, active appearance models, morphable models) use Principal Component Analysis (PCA) to model the shape and appearance of...