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

    16 Citations (Scopus)
    62 Downloads (Pure)

    Abstract

    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
    PublisherIEEE Computer Society Press
    Pages-
    Number of pages4
    ISBN (Print)978-1-4244-2175-6
    DOIs
    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
    https://www.ieee.org/conferences_events/conferences/conferencedetails/index.html?Conf_ID=13355

    Publication series

    Name
    PublisherIEEE Computer Society Press

    Conference

    Conference19th International Conference on Pattern Recognition 2008
    Abbreviated titleICPR 2008
    CountryUnited States
    CityTampa
    Period8/12/0811/12/08
    Other8 - 11 Dec 2008
    Internet address

    Keywords

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

    Cite this

    Hatun, K., & Duygulu, P. (2008). Pose Sentences: A new representation for action recognition using sequence of pose words. In International Conference on Pattern Recognition (pp. -). Piscataway: IEEE Computer Society Press. https://doi.org/10.1109/ICPR.2008.4761702
    Hatun, Kardelen ; Duygulu, Pinar. / Pose Sentences: A new representation for action recognition using sequence of pose words. International Conference on Pattern Recognition. Piscataway : IEEE Computer Society Press, 2008. pp. -
    @inproceedings{1ce92ce1621244e3b3bd8b35b20e728c,
    title = "Pose Sentences: A new representation for action recognition using sequence of pose words",
    abstract = "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.",
    keywords = "EWI-14780, CR-I.4, string matching, METIS-268949, IR-70808, Action recognition, bag-of-words",
    author = "Kardelen Hatun and Pinar Duygulu",
    note = "10.1109/ICPR.2008.4761702",
    year = "2008",
    month = "12",
    doi = "10.1109/ICPR.2008.4761702",
    language = "Undefined",
    isbn = "978-1-4244-2175-6",
    publisher = "IEEE Computer Society Press",
    pages = "--",
    booktitle = "International Conference on Pattern Recognition",

    }

    Hatun, K & Duygulu, P 2008, Pose Sentences: A new representation for action recognition using sequence of pose words. in International Conference on Pattern Recognition. IEEE Computer Society Press, Piscataway, pp. -, 19th International Conference on Pattern Recognition 2008, Tampa, United States, 8/12/08. https://doi.org/10.1109/ICPR.2008.4761702

    Pose Sentences: A new representation for action recognition using sequence of pose words. / Hatun, Kardelen; Duygulu, Pinar.

    International Conference on Pattern Recognition. Piscataway : IEEE Computer Society Press, 2008. p. -.

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

    TY - GEN

    T1 - Pose Sentences: A new representation for action recognition using sequence of pose words

    AU - Hatun, Kardelen

    AU - Duygulu, Pinar

    N1 - 10.1109/ICPR.2008.4761702

    PY - 2008/12

    Y1 - 2008/12

    N2 - 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.

    AB - 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.

    KW - EWI-14780

    KW - CR-I.4

    KW - string matching

    KW - METIS-268949

    KW - IR-70808

    KW - Action recognition

    KW - bag-of-words

    U2 - 10.1109/ICPR.2008.4761702

    DO - 10.1109/ICPR.2008.4761702

    M3 - Conference contribution

    SN - 978-1-4244-2175-6

    SP - -

    BT - International Conference on Pattern Recognition

    PB - IEEE Computer Society Press

    CY - Piscataway

    ER -

    Hatun K, Duygulu P. Pose Sentences: A new representation for action recognition using sequence of pose words. In International Conference on Pattern Recognition. Piscataway: IEEE Computer Society Press. 2008. p. - https://doi.org/10.1109/ICPR.2008.4761702