UCLA Statistics Department       Center for Image and Vision Science

Your Location Zhangzhang Si · Research · Current projects
active basis model This work proposes an active basis model, a shared sketch algorithm, and a computational architecture of sum-max maps for representing, learning, and recognizing deformable templates.
hybrid image template In a unified information theoretic framework, we learn hybrid image templates composed of sketch and texture descriptors.
learning with weak supervision Using this image representation we may discover visual objects under weak supervision, i.e. without knowing the true locations, orientations and categories of the visual objects.