Conditional random fields (CRFs) are graphical models for modeling the probability of labels given the observations. They have traditionally been trained with using a set of obser...
Xinhua Zhang, Douglas Aberdeen, S. V. N. Vishwanat...
The problems of dense stereo reconstruction and object class segmentation can both be formulated as Conditional Random Field based labelling problems, in which every pixel in the ...
Lubor Ladicky, Paul Sturgess, Christopher Russell,...
We present a discriminative part-based approach for the recognition of object classes from unsegmented cluttered scenes. Objects are modeled as flexible constellations of parts co...
Detecting moving objects using stationary cameras is an important precursor to many activity recognition, object recognition and tracking algorithms. In this paper, three innovati...
We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...