This paper describes methods for recovering time-varying shape and motion of nonrigid 3D objects from uncalibrated 2D point tracks. For example, given a video recording of a talkin...
Lorenzo Torresani, Aaron Hertzmann, Christoph Breg...
In this paper we detail the synergies we have observed between the features and limitations of mobile phones, and the usability and accessibility requirements of rural developing ...
We propose new features and algorithms for automating Web-page classification tasks such as content recommendation and ad blocking. We show that the automated classification of We...
Image classification is a well-studied and hard problem in computer vision. We extend a proven solution for classifying web spam to handle images. We exploit the link structure of...
In this paper we address the problem of identifying a broad range of term variations in Japanese web search queries, where these variations pose a particularly thorny problem due ...