Multiple Instance Learning (MIL) is a special kind of supervised learning problem that has been studied actively in recent years. In this paper, we propose an approach based on On...
Chengcui Zhang, Xin Chen, Min Chen, Shu-Ching Chen...
Having accurate left ventricle (LV) segmentations across a cardiac cycle provides useful quantitative (e.g. ejection fraction) and qualitative information for diagnosis of certain ...
Estimating the paths that moving objects can take through the fields of view of possibly non-overlapping cameras, also known as their activity topology, is an important step in t...
Graphical models have become the basic framework for topic based probabilistic modeling. Especially models with latent variables have proved to be effective in capturing hidden str...
Abstract— Categorizing visual elements is fundamentally important for autonomous mobile robots to get intelligence such as new object acquisition and topological place classific...