We present a new approach to model visual scenes in image collections, based on local invariant features and probabilistic latent space models. Our formulation provides answers to...
Pedro Quelhas, Florent Monay, Jean-Marc Odobez, Da...
Temporal texture accounts for a large proportion of motion commonly experienced in the visual world. Current temporal texture techniques extract primarily motion-based features for...
—A probabilistic formulation for semantic image annotation and retrieval is proposed. Annotation and retrieval are posed as classification problems where each class is defined as...
Gustavo Carneiro, Antoni B. Chan, Pedro J. Moreno,...
— There has been significant progress recently in object recognition research, but many of the current approaches still fail for object classes with few distinctive features, an...
We describe efficient techniques for construction of large term co-occurrence graphs, and investigate an application to the discovery of numerous fine-grained (specific) topics. A...