Wyner-Ziv video coding (WZVC) is a new paradigm for video compression with the prediction frames possibly only available at the decoder. It exploits the statistics between the sou...
DjVu is a document codec that uses a truncated embedded significance tree to achieve both resolution and image quality scalability. In this paper, the probability model for the t...
This paper presents a novel frame-layer rate control technique that adaptively determines the frame complexity for bit allocation in order to satisfy the target bit-rate constraint...
In this contribution, we present an algorithm for lowcomplexity global motion estimation, that works with block-coded video (e.g. MPEG-2). A superimposed global motion model is fi...
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several par...