—Effective image retrieval by content from database requires that visual image properties are used instead of textual labels to properly index and recover pictorial data. Retriev...
To leverage large-scale weakly-tagged images for computer vision tasks (such as object detection and scene recognition), a novel cross-modal tag cleansing and junk image filtering...
Image classification is a critical task for both humans and computers. One of the challenges lies in the large scale of the semantic space. In particular, humans can recognize tens...
We propose a method to automatically transform mesh animations into animation collages, i.e. moving assemblies of shape primitives from a database given by an artist. An animation...