By reconstructing time-varying geometry one frame at a time, one ignores the continuity of natural motion, wasting useful information about the underlying video-image formation pr...
This paper presents a comparative study of methods for video copy detection. Different state-of-the-art techniques, using various kinds of descriptors and voting functions, are d...
Julien Law-To, Li Chen, Alexis Joly, Ivan Laptev, ...
Generating artificial classic mosaics from digital images is an area of NPR rendering that has recently seen several successful approaches. A sequence of mosaic images creates a u...
We propose a novel method for the problem of 3D surface mesh segmentation. This mesh segmentation method is based on differential geometry and geodesic distance information. In ou...
This paper presents a novel framework for detecting non-flat abandoned objects by matching a reference and a target video sequences. The reference video is taken by a moving camera...