The hierarchy of untimed equivalences is well understood for action-based systems. This is not the case for timed systems, where it is, for example, possible to detect concurrency ...
—To date many activity spotting approaches are static: once the system is trained and deployed it does not change anymore. There are substantial shortcomings of this approach, sp...
We propose a visual event recognition framework for consumer domain videos by leveraging a large amount of loosely labeled web videos (e.g., from YouTube). First, we propose a new...
This paper describes a fully automatic twostage machine learning architecture that learns temporal relations between pairs of events. The first stage learns the temporal attribut...
We present a novel framework for learning to interpret and generate language using only perceptual context as supervision. We demonstrate its capabilities by developing a system t...