The influence of temporal information on human action recognition with large number of classes

Ramana ORUGANTI, Roland GOECKE

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    2 Citations (Scopus)

    Abstract

    Human action recognition from video input has seen much interest over the last decade. In recent years, the trend is clearly towards action recognition in real-world, unconstrained conditions (i.e. not acted) with an ever growing number of action classes. Much of the work so far has used single frames or sequences of frames where each frame was treated individually. This paper investigates the contribution that temporal information can make to human action recognition in the context of a large number of action classes. The key contributions are: (i) We propose a complementary information channel to the Bag-of- Words framework that models the temporal occurrence of the local information in videos. (ii) We investigate the influence of sensible local information whose temporal occurrence is more vital than any local information. The experimental validation on action recognition datasets with the largest number of classes to date shows the effectiveness of the proposed approach.
    Original languageEnglish
    Title of host publication2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014)
    Editors bouzerdoum, Wang, Ogunbona, Li, Phung
    Place of PublicationWollongong Austraia
    PublisherIEEE, Institute of Electrical and Electronics Engineers
    Pages1-8
    Number of pages8
    ISBN (Electronic)9781479954094
    ISBN (Print)9781479954100
    DOIs
    Publication statusPublished - 25 Nov 2014
    Event2014 International Conference on Digital Image Computing, Techniques and Applications - Wollongong, Wollongong, Australia
    Duration: 25 Nov 201427 Nov 2014

    Conference

    Conference2014 International Conference on Digital Image Computing, Techniques and Applications
    Abbreviated titleDICTA 2014
    CountryAustralia
    CityWollongong
    Period25/11/1427/11/14

    Cite this

    ORUGANTI, R., & GOECKE, R. (2014). The influence of temporal information on human action recognition with large number of classes. In bouzerdoum, Wang, Ogunbona, Li, & Phung (Eds.), 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014) (pp. 1-8). Wollongong Austraia: IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/DICTA.2014.7008131
    ORUGANTI, Ramana ; GOECKE, Roland. / The influence of temporal information on human action recognition with large number of classes. 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014). editor / bouzerdoum ; Wang ; Ogunbona ; Li ; Phung. Wollongong Austraia : IEEE, Institute of Electrical and Electronics Engineers, 2014. pp. 1-8
    @inproceedings{5293737bf3f64b07932c3441492d5a5b,
    title = "The influence of temporal information on human action recognition with large number of classes",
    abstract = "Human action recognition from video input has seen much interest over the last decade. In recent years, the trend is clearly towards action recognition in real-world, unconstrained conditions (i.e. not acted) with an ever growing number of action classes. Much of the work so far has used single frames or sequences of frames where each frame was treated individually. This paper investigates the contribution that temporal information can make to human action recognition in the context of a large number of action classes. The key contributions are: (i) We propose a complementary information channel to the Bag-of- Words framework that models the temporal occurrence of the local information in videos. (ii) We investigate the influence of sensible local information whose temporal occurrence is more vital than any local information. The experimental validation on action recognition datasets with the largest number of classes to date shows the effectiveness of the proposed approach.",
    keywords = "Human Action Recognition, Temporal information, Bag of Words",
    author = "Ramana ORUGANTI and Roland GOECKE",
    year = "2014",
    month = "11",
    day = "25",
    doi = "10.1109/DICTA.2014.7008131",
    language = "English",
    isbn = "9781479954100",
    pages = "1--8",
    editor = "bouzerdoum and Wang and Ogunbona and Li and Phung",
    booktitle = "2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014)",
    publisher = "IEEE, Institute of Electrical and Electronics Engineers",
    address = "United States",

    }

    ORUGANTI, R & GOECKE, R 2014, The influence of temporal information on human action recognition with large number of classes. in bouzerdoum, Wang, Ogunbona, Li & Phung (eds), 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014). IEEE, Institute of Electrical and Electronics Engineers, Wollongong Austraia, pp. 1-8, 2014 International Conference on Digital Image Computing, Techniques and Applications, Wollongong, Australia, 25/11/14. https://doi.org/10.1109/DICTA.2014.7008131

    The influence of temporal information on human action recognition with large number of classes. / ORUGANTI, Ramana; GOECKE, Roland.

    2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014). ed. / bouzerdoum; Wang; Ogunbona; Li; Phung. Wollongong Austraia : IEEE, Institute of Electrical and Electronics Engineers, 2014. p. 1-8.

    Research output: A Conference proceeding or a Chapter in BookConference contribution

    TY - GEN

    T1 - The influence of temporal information on human action recognition with large number of classes

    AU - ORUGANTI, Ramana

    AU - GOECKE, Roland

    PY - 2014/11/25

    Y1 - 2014/11/25

    N2 - Human action recognition from video input has seen much interest over the last decade. In recent years, the trend is clearly towards action recognition in real-world, unconstrained conditions (i.e. not acted) with an ever growing number of action classes. Much of the work so far has used single frames or sequences of frames where each frame was treated individually. This paper investigates the contribution that temporal information can make to human action recognition in the context of a large number of action classes. The key contributions are: (i) We propose a complementary information channel to the Bag-of- Words framework that models the temporal occurrence of the local information in videos. (ii) We investigate the influence of sensible local information whose temporal occurrence is more vital than any local information. The experimental validation on action recognition datasets with the largest number of classes to date shows the effectiveness of the proposed approach.

    AB - Human action recognition from video input has seen much interest over the last decade. In recent years, the trend is clearly towards action recognition in real-world, unconstrained conditions (i.e. not acted) with an ever growing number of action classes. Much of the work so far has used single frames or sequences of frames where each frame was treated individually. This paper investigates the contribution that temporal information can make to human action recognition in the context of a large number of action classes. The key contributions are: (i) We propose a complementary information channel to the Bag-of- Words framework that models the temporal occurrence of the local information in videos. (ii) We investigate the influence of sensible local information whose temporal occurrence is more vital than any local information. The experimental validation on action recognition datasets with the largest number of classes to date shows the effectiveness of the proposed approach.

    KW - Human Action Recognition

    KW - Temporal information

    KW - Bag of Words

    U2 - 10.1109/DICTA.2014.7008131

    DO - 10.1109/DICTA.2014.7008131

    M3 - Conference contribution

    SN - 9781479954100

    SP - 1

    EP - 8

    BT - 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014)

    A2 - bouzerdoum, null

    A2 - Wang, null

    A2 - Ogunbona, null

    A2 - Li, null

    A2 - Phung, null

    PB - IEEE, Institute of Electrical and Electronics Engineers

    CY - Wollongong Austraia

    ER -

    ORUGANTI R, GOECKE R. The influence of temporal information on human action recognition with large number of classes. In bouzerdoum, Wang, Ogunbona, Li, Phung, editors, 2014 International Conference on Digital Image Computing: Techniques and Applications (DICTA 2014). Wollongong Austraia: IEEE, Institute of Electrical and Electronics Engineers. 2014. p. 1-8 https://doi.org/10.1109/DICTA.2014.7008131