---
res:
  bibo_abstract:
  - We propose a mid-level statistical model for image segmentation that composes
    multiple figure-ground hypotheses (FG) obtained by applying constraints at different
    locations and scales, into larger interpretations (tilings) of the entire image.
    Inference is cast as optimization over sets of maximal cliques sampled from a
    graph connecting all non-overlapping figure-ground segment hypotheses. Potential
    functions over cliques combine unary, Gestalt-based figure qualities, and pairwise
    compatibilities among spatially neighboring segments, constrained by T-junctions
    and the boundary interface statistics of real scenes. Learning the model parameters
    is based on maximum likelihood, alternating between sampling image tilings and
    optimizing their potential function parameters. State of the art results are reported
    on the Berkeley and Stanford segmentation datasets, as well as VOC2009, where
    a 28% improvement was achieved.@eng
  bibo_authorlist:
  - foaf_Person:
      foaf_givenName: Adrian
      foaf_name: Ion, Adrian
      foaf_surname: Ion
      foaf_workInfoHomepage: http://www.librecat.org/personId=29F89302-F248-11E8-B48F-1D18A9856A87
  - foaf_Person:
      foaf_givenName: Joao
      foaf_name: Carreira, Joao
      foaf_surname: Carreira
  - foaf_Person:
      foaf_givenName: Cristian
      foaf_name: Sminchisescu, Cristian
      foaf_surname: Sminchisescu
  bibo_doi: 10.1109/ICCV.2011.6126486
  dct_date: 2012^xs_gYear
  dct_language: eng
  dct_publisher: IEEE@
  dct_title: Image segmentation by figure-ground composition into maximal cliques@
...