Software available at http://disi.unitn.it/~uijlings or http://koen.me/research/
For object recognition, the current state-of-the-art is based on exhaustive search. However, to ...
In computer-aided design and meshing, it is often important to identify the discontinuities (singularities) in coarse surface meshes. Due to the potential low resolution and noise...
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
—There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context mod...
On-line pen input benefits greatly from mode detection when the user is in a free writing situation, where he is allowed to write, to draw, and to generate gestures. Mode detecti...