It has recently been shown that only a small number of samples from a low-rank matrix are necessary to reconstruct the entire matrix. We bring this to bear on computer vision prob...
Face recognition in video has gained wide attention due to its role in designing surveillance systems. One of the main advantages of video over still frames is that evidence accumu...
A major drawback of block-based still-image or video-compression methods at low rates is the visible block boundaries that are also known as blocking artifacts. Several methods hav...
Bahadir K. Gunturk, Yucel Altunbasak, Russell M. M...
—In a standard transform coding scheme of images or video, the decoder can be implemented by a table-lookup technique without the explicit use of an inverse transformation. In th...
We extend the successful 2D robust feature concept into the third dimension in that we produce a descriptor for a reconstructed 3D surface region. The descriptor is perspectively ...