We introduce spatial PACT (Principal component Analysis of Census Transform histograms), a new representation for recognizing instances and categories of places or scenes. Both pl...
We propose a novel variant of the conjugate gradient algorithm, Kernel Conjugate Gradient (KCG), designed to speed up learning for kernel machines with differentiable loss functio...
We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
Whereas most existing action recognition methods require computationally demanding feature extraction and/or classification, this paper presents a novel real-time solution that ut...
We present a novel approach for fast object class recognition incorporating contextual information into boosting. The object is represented as a constellation of generalized corre...