… In this paper we propose a novel associative hierarchical random field formulation of
semantic segmentation that allows us to combine models defined over different choices of super-…

… first is the proposal of a new model – the associative hierarchical random field (AHRF), and
a novel … Our new hierarchical random field model allows information from all of the multiple …

… random field model, whose generative nature obliges us to model the joint distribution of the
image data and the corresponding label field, and … the associative hierarchical random field (…

… Motivated by this observation, we propose a hierarchical random field model, that allows
integration of features computed at different levels of the quantisation hierarchy. MAP inference …

… random field model, that represents the action segments and activities in a hierarchical …
benefit of hierarchical modeling of related activities using both motion and context features. …

… Abstract—This letter proposes an associative hierarchical conditional random field (AHCRF)
model to improve the classification accuracy of high-resolution remote sensing images. It …

… The model we consider for this problem is the Associative Hierarchical CRF of Ladicky et
al. [15], which achieved competitive results in recent years’ VOC challenges. We used the …

… extension to hierarchical random fields, … hierarchical CRF proposed in [13], our model
is more expressive and flexible since it considers not only associative but also nonassociative …

… Motivated by this observation, we propose a hierarchical random field model, that allows
integration of features computed at different levels of the quantisation hierarchy. MAP inference …

… a hierarchical conditional random field to deal with the problem of image classification by
modeling spatial and hierarchical structures… Associative hierarchical crfs for object class image …