To allow the hidden units of a restricted Boltzmann machine to model the transformation between two successive images, Memisevic and Hinton (2007) introduced three-way multiplicat...
—In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. The resulting ...
—One of the major challenges in multi-view imaging is the definition of a representation that reveals the intrinsic geometry of the visual information. Sparse image representati...
Combining learning with vision techniques in interactive image retrieval has been an active research topic during the past few years. However, existing learning techniques either ...
Learning visual models of object categories notoriously requires thousands of training examples; this is due to the diversity and richness of object appearance which requires mode...