Multi-scale stacked sequential learning

Carlo Gatta, Eloi Puertas, Oriol Pujol

    Research output: Contribution to journalArticleResearchpeer-review

    22 Citations (Scopus)

    Abstract

    Sequential learning is the discipline of machine learning that deals with dependent data such that neighboring labels exhibit some kind of relationship. The paper main contribution is two-fold: first, we generalize the stacked sequential learning, highlighting the key role of neighboring interactions modeling. Second, we propose an effective and efficient way of capturing and exploiting sequential correlations that takes into account long-range interactions. We tested the method on two tasks: text lines classification and image pixel classification. Results on these tasks clearly show that our approach outperforms the standard stacked sequential learning as well as state-of-the-art conditional random fields. © 2011 Elsevier Ltd. All rights reserved.
    Original languageEnglish
    Pages (from-to)2414-2426
    JournalPattern Recognition
    Volume44
    Issue number10-11
    DOIs
    Publication statusPublished - 1 Oct 2011

    Keywords

    • Contextual classification
    • Multiresolution
    • Multiscale
    • Stacked sequential learning

    Fingerprint Dive into the research topics of 'Multi-scale stacked sequential learning'. Together they form a unique fingerprint.

    Cite this