—We present a discriminative part-based approach for human action recognition from video sequences using motion features. Our model is based on the recently proposed hidden condi...
Sets of local features that are invariant to common image transformations are an effective representation to use when comparing images; current methods typically judge feature set...
Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
Today's category-level object recognition systems largely focus on fronto-parallel views of objects with characteristic texture patterns. To overcome these limitations, we pr...
We combine local texture features (PCA-SIFT), global features (shape context), and spatial features within a single multi-layer AdaBoost model of object class recognition. The fir...
Wei Zhang 0002, Bing Yu, Gregory J. Zelinsky, Dimi...