Stacked sequential scale-space taylor context

Carlo Gatta; Francesco Ciompi

doi:10.1109/TPAMI.2013.2297706

Stacked sequential scale-space taylor context

Carlo Gatta, Francesco Ciompi

Research output: Contribution to journal › Article › Research › peer-review

6 Citations (Scopus)

Abstract

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. © 1979-2012 IEEE.

Original language	English
Article number	6701326
Pages (from-to)	1694-1700
Journal	IEEE Transactions on Pattern Analysis and Machine Intelligence
Volume	36
Issue number	8
DOIs	https://doi.org/10.1109/TPAMI.2013.2297706
Publication status	Published - 1 Jan 2014

Keywords

Contextual modeling
semantic image labeling
stacked sequential learning

Access to Document

10.1109/TPAMI.2013.2297706

Cite this

@article{d2858c0c230c4bb48f6aca3bb6fffbc7,

title = "Stacked sequential scale-space taylor context",

abstract = "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. {\textcopyright} 1979-2012 IEEE.",

keywords = "Contextual modeling, semantic image labeling, stacked sequential learning",

author = "Carlo Gatta and Francesco Ciompi",

year = "2014",

month = jan,

day = "1",

doi = "10.1109/TPAMI.2013.2297706",

language = "English",

volume = "36",

pages = "1694--1700",

number = "8",

}

TY - JOUR

T1 - Stacked sequential scale-space taylor context

AU - Gatta, Carlo

AU - Ciompi, Francesco

PY - 2014/1/1

Y1 - 2014/1/1

N2 - 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. © 1979-2012 IEEE.

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. © 1979-2012 IEEE.

KW - Contextual modeling

KW - semantic image labeling

KW - stacked sequential learning

U2 - 10.1109/TPAMI.2013.2297706

DO - 10.1109/TPAMI.2013.2297706

M3 - Article

VL - 36

SP - 1694

EP - 1700

IS - 8

M1 - 6701326

ER -

Stacked sequential scale-space taylor context

Abstract

Keywords

Access to Document

Fingerprint

Cite this