Optical character recognition (OCR) remains a difficult problem for noisy documents or documents not scanned at high resolution. Many current approaches rely on stored font models...
Andrew Kae, Gary Huang, Erik Learned-miller, Carl ...
We present a technique that compresses a string w by enumerating all the substrings of w. The substrings are enumerated from the shortest to the longest and in lexicographic order...
In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
Large-scale cluster-based Internet services often host partitioned datasets to provide incremental scalability. The aggregation of results produced from multiple partitions is a f...
We present the 3D Video Recorder, a system capable of recording, processing, and playing three–dimensional video from multiple points of view. We first record 2D video streams f...