Ideally, visual learning algorithms should be generalizable, for dealing with any unseen domain shift when deployed in a new target environment; and d...

Skeletonization algorithms are used as basic methods to solve tracking problems, pose estimation, or predict animal group behavior. Traditional skelet...

Terahertz (THz) tomographic imaging has recently attracted significant attention thanks to its non-invasive, non-destructive, non-ionizing, material-c...

In this paper, we propose a novel image coding framework with semantic-aware visual decomposition towards extremely low bitrate compression. In partic...

An approach is proposed for recovering affine correspondences (ACs) from orientation- and scale-covariant, e.g., SIFT, features exploiting pre-estimat...