We propose a novel framework for imposing label ordering constraints in multilabel optimization. In particular, label jumps can be penalized differently depending on the jump dire...
This paper addresses the problem of exactly inferring the maximum a posteriori solutions of discrete multi-label MRFs or CRFs with higher order cliques. We present a framework to ...
We consider the problem of optimizing multilabel MRFs, which is in general NP-hard and ubiquitous in low-level computer vision. One approach for its solution is to formulate it as...
Pushmeet Kohli, Alexander Shekhovtsov, Carsten Rot...
We consider a generalized semi-infinite optimization problem (GSIP) of the form (GSIP) min{f(x) Ix E M}, where M = {x E N"lhi(x ) = 0, i = 1,...,m, G(x,y) /> 0, y E Y(x)} ...
In this paper, we deal with a generative model for multi-label, interactive segmentation. To estimate the pixel likelihoods for each label, we propose a new higher-order formulatio...
Tae Hoon Kim (Seoul National University), Kyoung M...