This paper addresses the problem of using appearance and motion models in classifying and tracking objects when detailed information of the object’s appearance is not available....
We present a compressed domain scheme that is able to recognize and localize actions in real-time1 . The recognition problem is posed as performing an action video query on a test ...
Our goal is to fit the multiple instances (or structures) of a generic model existing in data. Here we propose a novel model selection scheme to estimate the number of genuine str...
Relationships that link static documents discussed during meetings to the corresponding speech transcripts can be of various kinds. The most important ones, thematic links, quotat...
This paper presents a lexical post-processing optimization for handwritten word recognition. The aim of this work is to explore the combination of different lexical postprocessing...