Dynamic image analysis requires the estimation of time-varying model parameters (e.g., shape coe cients). This can be11 seen as states of a dynamic model which are restricted to a...
We introduce vlogs as a type of rich human interaction which is multimodal in nature and suitable for new largescale behavioral data analysis. The automatic analysis of vlogs is u...
Urban planners are dealing with problems of urban sprawl and CO2 emissions. The multidimensional character of these phenomena requires new analysis and visualization tools that ar...
Sebastian Petsch, Subhrajit Guhathakurta, Hans Hag...
In this paper, we present an efficient system for action recognition from very short sequences. For action recognition typically appearance and/or motion information of an action ...
This paper introduces a novel high speed convolutional character recognition system. Convolutional mode operation means that no prior localization or segmentation of characters is...