The paper describes a multi-layer video coder based on spatiotemporal scalability and data partitioning. The coder consists of two parts: a low-resolution coder and full-resolutio...
In this paper, a one-pass multi-layer rate-distortion optimization algorithm is proposed for quality scalable video coding. To improve the overall coding efficiency, the MB mode ...
While Active Learning (AL) has already been shown to markedly reduce the annotation efforts for many sequence labeling tasks compared to random selection, AL remains unconcerned a...
We introduce a new perceptron-based discriminative learning algorithm for labeling structured data such as sequences, trees, and graphs. Since it is fully kernelized and uses poin...
We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...