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...
We present a flexible and highly efficient hardware-assisted volume renderer grounded on the original Projected Tetrahedra (PT) algorithm. Unlike recent similar approaches, our me...
As data volumes increase at a high speed in more and more application fields of science, engineering, information services, etc., the challenges posed by data-intensive computing...
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
We address the texture level-of-detail problem for extremely large surfaces such as terrain during realtime, view-dependent rendering. A novel texture hierarchy is introduced base...