Learning variable-length Markov models of behavior

Aphrodite Galata, Neil Johnson, David Hogg

    Research output: Contribution to journalArticlepeer-review


    In recent years there has been an increased interest in the modeling and recognition of human activities involving highly structured and semantically rich behavior such as dance, aerobics, and sign language. A novel approach for automatically acquiring stochastic models of the high-level structure of an activity without the assumption of any prior knowledge is presented. The process involves temporal segmentation into plausible atomic behavior components and the use of variable-length Markov models for the efficient representation of behaviors. Experimental results that demonstrate the synthesis of realistic sample behaviors and the performance of models for long-term temporal prediction are presented.
    Original languageEnglish
    Pages (from-to)398-413
    Number of pages15
    JournalComputer Vision and Image Understanding
    Issue number3
    Publication statusPublished - Mar 2001


    • Behavior prediction
    • Behavior synthesis
    • Computer animation
    • Hidden Markov models
    • Markov models
    • Modeling behavior
    • N-grams
    • Probabilistic finite state automata
    • Statistical grammars
    • Variable-length Markov models


    Dive into the research topics of 'Learning variable-length Markov models of behavior'. Together they form a unique fingerprint.

    Cite this