We develop an optical flow estimation framework that focuses on motion estimation over time formulated in a Dynamic Bayesian Network. It realizes a spatiotemporal integration of ...
Volker Willert, Marc Toussaint, Julian Eggert, Edg...
In solving complex visual learning tasks, adopting multiple descriptors to more precisely characterize the data has been a feasible way for improving performance. These representa...
We present an algorithm for generating referring expressions in open domains. Existing algorithms work at the semantic level and assume the availability of a classification for at...
Previous studies have shown that the quantification of volumetric blood flow from a color Doppler image (CDI) is a feasible approach to eliminate technical obstacles in the tradit...
For large data sets in medicine and science, efficient isosurface extraction and rendering is crucial for interactive visualization. Previous GPU acceleration techniques have been...