University Library
  • Login
A gateway to Melbourne's research publications
Minerva Access is the University's Institutional Repository. It aims to collect, preserve, and showcase the intellectual output of staff and students of the University of Melbourne for a global audience.
View Item 
  • Minerva Access
  • Engineering
  • Computing and Information Systems
  • Computing and Information Systems - Research Publications
  • View Item
  • Minerva Access
  • Engineering
  • Computing and Information Systems
  • Computing and Information Systems - Research Publications
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

    Learning latent global network for Skeleton-based action prediction

    Thumbnail
    Citations
    Scopus
    Web of Science
    Altmetric
    5
    4
    Author
    Ke, Q; Bennamoun, M; Rahmani, H; An, S; Sohel, F; Boussaid, F
    Date
    2020-01-01
    Source Title
    IEEE Transactions on Image Processing
    Publisher
    IEEE
    University of Melbourne Author/s
    Ke, Qiuhong
    Affiliation
    Computing and Information Systems
    Metadata
    Show full item record
    Document Type
    Journal Article
    Citations
    Ke, Q., Bennamoun, M., Rahmani, H., An, S., Sohel, F. & Boussaid, F. (2020). Learning latent global network for Skeleton-based action prediction. IEEE Transactions on Image Processing, 29, pp.959-970. https://doi.org/10.1109/TIP.2019.2937757.
    Access Status
    Access this item via the Open Access location
    URI
    http://hdl.handle.net/11343/253984
    DOI
    10.1109/TIP.2019.2937757
    Open Access URL
    https://eprints.lancs.ac.uk/id/eprint/136503/1/bare_jrnl7.pdf
    Abstract
    Human actions represented with 3D skeleton sequences are robust to clustered backgrounds and illumination changes. In this paper, we investigate skeleton-based action prediction, which aims to recognize an action from a partial skeleton sequence that contains incomplete action information. We propose a new Latent Global Network based on adversarial learning for action prediction. We demonstrate that the proposed network provides latent long-term global information that is complementary to the local action information of the partial sequences and helps improve action prediction. We show that action prediction can be improved by combining the latent global information with the local action information. We test the proposed method on three challenging skeleton datasets and report state-of-the-art performance.

    Export Reference in RIS Format     

    Endnote

    • Click on "Export Reference in RIS Format" and choose "open with... Endnote".

    Refworks

    • Click on "Export Reference in RIS Format". Login to Refworks, go to References => Import References


    Collections
    • Minerva Elements Records [45770]
    • Computing and Information Systems - Research Publications [1456]
    Minerva AccessDepositing Your Work (for University of Melbourne Staff and Students)NewsFAQs

    BrowseCommunities & CollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects
    My AccountLoginRegister
    StatisticsMost Popular ItemsStatistics by CountryMost Popular Authors