Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Gait is an attractive biometric for vision-based human identification. Previous work on existing public data sets has shown that shape cues yield improved recognition rates compar...
Reliable recognition of objects is an important capabaility in the progress towards getting agents to accomplish and assist in a variety of useful tasks such as search and rescue ...
Gaussian processes have been widely used as a method for inferring the pose of articulated bodies directly from image data. While able to model complex non-linear functions, they ...
Current approaches to motion category recognition typically focus on either full spatiotemporal volume analysis (holistic approach) or analysis of the content of spatiotemporal in...