The compositional nature of visual objects significantly limits their representation complexity and renders learning of structured object models tractable. Adopting this modeling ...
Abstract. Movies and TV are a rich source of diverse and complex video of people, objects, actions and locales "in the wild". Harvesting automatically labeled sequences o...
Timothee Cour, Chris Jordan, Eleni Miltsakaki, Ben...
Subspace learning approaches have attracted much attention in academia recently. However, the classical batch algorithms no longer satisfy the applications on streaming data or la...
Jun Yan, Benyu Zhang, Shuicheng Yan, Qiang Yang, H...
We focus on characterizing spatial region data when distinct classes of structural patterns are present. We propose a novel statistical approach based on a supervised framework for...
Despina Kontos, Vasileios Megalooikonomou, Marc J....
The growing need of software infrastructure able to create, maintain and ease the evolution of scientific data, promotes the development of digital libraries in order to provide th...