The objective of this work is automatic detection and identification of individuals in unconstrained consumer video, given a minimal number of labelled faces as training data. Whi...
This paper presents an approach for modeling landmark sites such as the Statue of Liberty based on large-scale contaminated image collections gathered from the Internet. Our system...
Xiaowei Li, Changchang Wu, Christopher Zach, Svetl...
Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Abstract. Successful multi-target tracking requires solving two problems - localize the targets and label their identity. An isolated target's identity can be unambiguously pr...
Abstract. We propose a probabalistic model of single source multimodal generation and show how algorithms for maximizing mutual information can find the correspondences between com...