Human Activity Recognition Using Hierarchically-Mined Feature Constellations

A. Oikonomopoulos, Maja Pantic

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

    3 Citations (Scopus)
    43 Downloads (Pure)


    In this paper we address the problem of human activity modelling and recognition by means of a hierarchical representation of mined dense spatiotemporal features. At each level of the hierarchy, the proposed method selects feature constellations that are increasingly discriminative and characteristic of a specific action category, by taking into account how frequently they occur in that action category versus the rest of the available action categories in the training dataset. Each feature constellation consists of n-tuples of features selected in the previous level of the hierarchy and lying within a small spatiotemporal neighborhood. We use spatiotemporal Local Steering Kernel (LSK) features as a basis for our representation, due to their ability and efficiency in capturing the local structure and dynamics of the underlying activities. The proposed method is able to detect activities in unconstrained videos, by back-projecting the activated features at the locations at which they were activated. We test the proposed method on two publicly available datasets, namely the KTH and YouTube datasets of human bodily actions. The acquired results demonstrate the effectiveness of the proposed method in recognising a wide variety of activities.
    Original languageEnglish
    Title of host publicationAdvances in Visual Computing
    Subtitle of host publication9th International Symposium, ISVC 2013, Rethymnon, Crete, Greece, July 29-31, 2013. Proceedings
    Place of PublicationBerlin
    Number of pages10
    ISBN (Print)978-3-642-41913-3
    Publication statusPublished - Jul 2013
    Event9th International Symposium on Visual Computing, ISVC 2013 - Rethymnon, Crete, Greece
    Duration: 29 Jul 201331 Jul 2013
    Conference number: 9

    Publication series

    NameLecture Notes in Computer Science
    PublisherSpringer Verlag
    ISSN (Print)0302-9743
    ISSN (Electronic)1611-3349


    Conference9th International Symposium on Visual Computing, ISVC 2013
    Abbreviated titleISVC
    CityRethymnon, Crete


    • EWI-24342
    • METIS-302661
    • IR-89372
    • HMI-HF: Human Factors


    Dive into the research topics of 'Human Activity Recognition Using Hierarchically-Mined Feature Constellations'. Together they form a unique fingerprint.

    Cite this