PT Journal
AU Carlo Gatta
   Francesco Ciompi
TI Stacked Sequential Scale-Space Taylor Context
SO IEEE Transactions on Pattern Analysis and Machine Intelligence
JI TPAMI
PY 2014
BP 1694
EP 1700
VL 36
IS 8
DI 10.1109/TPAMI.2013.2297706
AB We analyze sequential image labeling methods that sample the posterior label field in order to gather contextual information. We propose an effective method that extracts local Taylor coefficients from the posterior at different scales. Results show that our proposal outperforms state-of-the-art methods on MSRC-21, CAMVID, eTRIMS8 and KAIST2 data sets.
ER