Finding correspondences between two (widely) separated views is essential for several computer vision tasks, such as structure and motion estimation and object recognition. In the...
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovati...
This paper presents a semi-supervised learning (SSL) approach to find similarities of images using statistics of local matches. SSL algorithms are well known for leveraging a larg...
We study a class of functional which can be used for matching objects which can be represented as mappings from a fixed interval, I, to some "feature space." This class o...