We explore a polar representation of optical flow in which each element of the brightness motion field is represented by its magnitude and orientation instead of its Cartesian p...
While most existing enhancement tools for photographs have universal auto-enhancement functionality, recent research [8] shows that users can have personalized preferences. In thi...
We propose a factor-graph-based approach to joint channel-estimationand-decoding of bit-interleaved coded orthogonal frequency division multiplexing (BICM-OFDM). In contrast to ex...
We extend our earlier work on deep-structured conditional random field (DCRF) and develop deep-structured hidden conditional random field (DHCRF). We investigate the use of this n...
Inducing a grammar from text has proven to be a notoriously challenging learning task despite decades of research. The primary reason for its difficulty is that in order to induce...