Pose Sentences: A new representation for action recognition using sequence of pose words

Kardelen Hatun, Pinar Duygulu

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    18 Citations (Scopus)
    131 Downloads (Pure)


    We propose a method for recognizing human actions in videos. Inspired from the recent bag-of-words approaches, we represent actions as documents consisting of words, where a word refers to the pose in a frame. Histogram of oriented gradients (HOG) features are used to describe poses, which are then vector quantized to obtain pose-words. As an alternative to bag-of-words approaches, that only represent actions as a collection of words by discarding the temporal characteristics of actions, we represent videos as ordered sequence of pose-words, that is as pose sentences. Then, string matching techniques are exploited to find the similarity of two action sequences. In the experiments, performed on data set of Blank et al., 92% performance is obtained.
    Original languageUndefined
    Title of host publicationInternational Conference on Pattern Recognition
    Place of PublicationPiscataway
    Number of pages4
    ISBN (Print)978-1-4244-2175-6
    Publication statusPublished - Dec 2008
    Event19th International Conference on Pattern Recognition 2008 - Tampa Convention Center, Tampa, United States
    Duration: 8 Dec 200811 Dec 2008
    Conference number: 19

    Publication series

    PublisherIEEE Computer Society Press


    Conference19th International Conference on Pattern Recognition 2008
    Abbreviated titleICPR 2008
    Country/TerritoryUnited States
    Other8 - 11 Dec 2008
    Internet address


    • EWI-14780
    • CR-I.4
    • string matching
    • METIS-268949
    • IR-70808
    • Action recognition
    • bag-of-words

    Cite this