Matching local features across images is often useful when comparing or recognizing objects or scenes, and efficient techniques for obtaining image-to-image correspondences have b...
We study the challenging problem of maneuvering object tracking with unknown dynamics, i.e., forces or torque. We investigate the underlying causes of object kinematics, and propo...
This paper presents a composite blind digital watermarking technique, CompMark, to hide a visually meaningful grayscale logo in a host image. The multi-resolution fusion principle...
This paper deals with the fully automatic extraction of classifiable person features out of a video stream with challenging background. Basically the task can be split in two part...
Text detection is fundamental to video information retrieval and indexing. Existing methods cannot handle well those texts with different contrast or embedded in a complex backgro...