In this paper, we develop a general classification framework called Kullback-Leibler Boosting, or KLBoosting. KLBoosting has following properties. First, classification is based o...
—The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single frame object recogn...
Naive Bayes Nearest Neighbor (NBNN) has recently been proposed as a powerful, non-parametric approach for object classification, that manages to achieve remarkably good results t...
Tinne Tuytelaars, Mario Fritz, Kate Saenko, Trevor...
A novel scheme is proposed for achieving motion segmentation in low-frame rate videos, with application to temporal super resolution. Probabilistic generative models are commonly ...
We propose a novel objective function for discriminatively tuning log-linear machine translation models. Our objective explicitly optimizes the BLEU score of expected n-gram count...