• Login
    View Item 
    •   Home
    • Research
    • Preprints
    • View Item
    •   Home
    • Research
    • Preprints
    • View Item
    JavaScript is disabled for your browser. Some features of this site may not work without it.

    Browse

    All of KAUSTCommunitiesIssue DateSubmit DateThis CollectionIssue DateSubmit Date

    My Account

    Login

    Quick Links

    Open Access PolicyORCID LibguidePlumX LibguideSubmit an Item

    Statistics

    Display statistics

    Boundary-sensitive Pre-training for Temporal Localization in Videos

    • CSV
    • RefMan
    • EndNote
    • BibTex
    • RefWorks
    Thumbnail
    Name:
    Preprintfile1.pdf
    Size:
    12.28Mb
    Format:
    PDF
    Description:
    Pre-print
    Download
    Type
    Preprint
    Authors
    Xu, Mengmeng cc
    Perez-Rua, Juan-Manuel
    Escorcia, Victor
    Martinez, Brais
    Zhu, Xiatian
    Ghanem, Bernard cc
    Xiang, Tao
    KAUST Department
    Electrical Engineering Program
    Electrical Engineering
    Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
    Date
    2020-11-21
    Permanent link to this record
    http://hdl.handle.net/10754/666111
    
    Metadata
    Show full item record
    Abstract
    Many video analysis tasks require temporal localization thus detection of content changes. However, most existing models developed for these tasks are pre-trained on general video action classification tasks. This is because large scale annotation of temporal boundaries in untrimmed videos is expensive. Therefore no suitable datasets exist for temporal boundary-sensitive pre-training. In this paper for the first time, we investigate model pre-training for temporal localization by introducing a novel boundary-sensitive pretext (BSP) task. Instead of relying on costly manual annotations of temporal boundaries, we propose to synthesize temporal boundaries in existing video action classification datasets. With the synthesized boundaries, BSP can be simply conducted via classifying the boundary types. This enables the learning of video representations that are much more transferable to downstream temporal localization tasks. Extensive experiments show that the proposed BSP is superior and complementary to the existing action classification based pre-training counterpart, and achieves new state-of-the-art performance on several temporal localization tasks.
    Publisher
    arXiv
    arXiv
    2011.10830
    Additional Links
    https://arxiv.org/pdf/2011.10830
    Collections
    Preprints; Electrical Engineering Program; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division

    entitlement

     
    DSpace software copyright © 2002-2021  DuraSpace
    Quick Guide | Contact Us | Send Feedback
    Open Repository is a service hosted by 
    Atmire NV
     

    Export search results

    The export option will allow you to export the current search results of the entered query to a file. Different formats are available for download. To export the items, click on the button corresponding with the preferred download format.

    By default, clicking on the export buttons will result in a download of the allowed maximum amount of items. For anonymous users the allowed maximum amount is 50 search results.

    To select a subset of the search results, click "Selective Export" button and make a selection of the items you want to export. The amount of items that can be exported at once is similarly restricted as the full export.

    After making a selection, click one of the export format buttons. The amount of items that will be exported is indicated in the bubble next to export format.