000169178 001__ 169178
000169178 005__ 20190812205537.0
000169178 02470 $$2ISI$$a000300061900002
000169178 037__ $$aCONF
000169178 041__ $$aeng
000169178 245__ $$aAre Spatial and Global Constraints Really Necessary for Segmentation?
000169178 269__ $$a2011
000169178 260__ $$bIEEE$$c2011
000169178 336__ $$aConference Papers
000169178 520__ $$aMany state-of-the-art segmentation algorithms rely on Markov or Conditional Random Field models designed to enforce spatial and global consistency constraints. This is often accomplished by introducing additional latent variables to the model, which can greatly increase its complexity. As a result, estimating the model parameters or computing the best maximum a posteriori (MAP) assignment becomes a computationally expensive task.
000169178 6531_ $$asegmentation
000169178 700__ $$0242715$$g185205$$aLucchi, Aurélien
000169178 700__ $$0244419$$g201504$$aLi, Yunpeng
000169178 700__ $$aBoix Bosch, Xavier
000169178 700__ $$0242712$$g163328$$aSmith, Kevin
000169178 700__ $$0240252$$g112366$$aFua, Pascal
000169178 7112_ $$cBarcelona$$aIEEE International Conference on Computer Vision (ICCV)
000169178 773__ $$t2011 IEEE International Conference On Computer Vision (ICCV)$$q9-16
000169178 8564_ $$zn/a$$yn/a$$uhttps://infoscience.epfl.ch/record/169178/files/lucchi_ICCV11.pdf$$s2329354
000169178 909C0 $$xU10659$$pCVLAB$$0252087
000169178 909CO $$ooai:infoscience.tind.io:169178$$qGLOBAL_SET$$pconf$$pIC
000169178 917Z8 $$x185205
000169178 917Z8 $$x112366
000169178 937__ $$aEPFL-CONF-169178
000169178 973__ $$rNON-REVIEWED$$sPUBLISHED$$aEPFL
000169178 980__ $$aCONF