We propose a method for learning using a set of feature representations which retrieve different amounts of information at different costs. The goal is to create a more efficient ...
Anelia Angelova, Larry Matthies, Daniel M. Helmick...
This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The conc...
This paper presents a new approach to discriminative modeling for classi cation and labeling. Our method, called Boosting on Multilevel Aggregates (BMA), adds a new class of hiera...
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of different object temporal events in the scene for a coherent and robust...
We propose a graph-based semi-supervised symmetric matching framework that performs dense matching between two uncalibrated wide-baseline images by exploiting the results of sparse...
Jianxiong Xiao, Jingni Chen, Dit-Yan Yeung, Long Q...