Sparse features have traditionally been tracked from frame to frame independently of one another. We propose a framework in which features are tracked jointly. Combining ideas fro...
We develop a linear model of commonly observed joint color changes in images due to variation in lighting and certain non-geometric camera parameters. This is done by observing ho...
Multiple Instance Learning (MIL) provides a framework for training a discriminative classifier from data with ambiguous labels. This framework is well suited for the task of learni...
Carolina Galleguillos, Boris Babenko, Andrew Rabin...
Abstract. This paper presents a novel approach to sign language recognition that provides extremely high classification rates on minimal training data. Key to this approach is a 2 ...
Richard Bowden, David Windridge, Timor Kadir, Andr...
In this paper we present a symmetry-based approach which can be used to detect humans and to extract biometric characteristics from video image-sequences. The method employs a simp...