The advent of social tagging systems has enabled a new community-based view of the Web in which objects like images, videos, and Web pages are annotated by thousands of users. Und...
In this paper we introduce a template-based method for recognizing human actions called Action MACH. Our approach is based on a Maximum Average Correlation Height (MACH) filter. A...
Composite images are synthesized from existing photographs by artists who make concept art, e.g., storyboards for movies or architectural planning. Current techniques allow an art...
Matthew Johnson, Gabriel J. Brostow, Jamie Shotton...
The dynamic texture (DT) is a probabilistic generative model, defined over space and time, that represents a video as the output of a linear dynamical system (LDS). The DT model ...
The increase of personal digital cameras with video functionality and video-enabled camera phones has increased the amount of user-generated videos on the Web. People are spending ...
Smitashree Choudhury, John G. Breslin, Alexandre P...