•  English
    • Persian
    • English
  •   Login
  • Ferdowsi University of Mashhad
  • |
  • Information Center and Central Library
    • Persian
    • English
  • Home
  • Source Types
    • Journal Paper
    • Ebook
    • Conference Paper
    • Standard
    • Protocol
    • Thesis
  • Use Help
View Item 
  •   FUM Digital Library
  • Fum
  • Articles
  • ProfDoc
  • View Item
  •   FUM Digital Library
  • Fum
  • Articles
  • ProfDoc
  • View Item
  • All Fields
  • Title
  • Author
  • Year
  • Publisher
  • Subject
  • Publication Title
  • ISSN
  • DOI
  • ISBN
Advanced Search
JavaScript is disabled for your browser. Some features of this site may not work without it.

Enhancing Human Action Recognition through Temporal Saliency

Author:
ویدا عادلی مسبب
,
احسان فضل ارثی
,
احد هراتی
,
Vida Adeli Mosabbeb
,
Ehsan Fazl-Ersi
,
Ahad Harati
Year
: 2018
Abstract: Images and videos have become ubiquitous in every aspects of life due to the growing digital recording devices. It has encouraged the development of algorithms that can analyze video content and perform human action recognition. This paper investigates the challenging problem of action recognition by outlining a new approach to represent a video sequence. A novel framework is developed to produce informative features for action labeling in a weakly-supervised learning (WSL) approach both during training and testing. Using appearance and motion information, the goal is to identify frame regions that are likely to contain actions. A three-stream convolutional neural network is adopted and improved by proposing a method based on extracting actionness regions. This results in less computation as it is processing only some parts of an RGB frame and also interpret less non-activity related regions, which can mislead the recognition system. We exploit UCF sports dataset as our evaluation benchmark, which is a dataset of realistic sports videos. We will show that our proposed approach could outperform other existing state-of-the art methods.
URI: https://libsearch.um.ac.ir:443/fum/handle/fum/3398176
Keyword(s): Action recognition,Motion,Region proposal,Convolutional Neural Networks,Actionness
Collections :
  • ProfDoc
  • Show Full MetaData Hide Full MetaData
  • Statistics

    Enhancing Human Action Recognition through Temporal Saliency

Show full item record

contributor authorویدا عادلی مسببen
contributor authorاحسان فضل ارثیen
contributor authorاحد هراتیen
contributor authorVida Adeli Mosabbebfa
contributor authorEhsan Fazl-Ersifa
contributor authorAhad Haratifa
date accessioned2020-06-06T14:28:27Z
date available2020-06-06T14:28:27Z
date copyright5/14/2018
date issued2018
identifier urihttps://libsearch.um.ac.ir:443/fum/handle/fum/3398176
description abstractImages and videos have become ubiquitous in every aspects of life due to the growing digital recording devices. It has encouraged the development of algorithms that can analyze video content and perform human action recognition. This paper investigates the challenging problem of action recognition by outlining a new approach to represent a video sequence. A novel framework is developed to produce informative features for action labeling in a weakly-supervised learning (WSL) approach both during training and testing. Using appearance and motion information, the goal is to identify frame regions that are likely to contain actions. A three-stream convolutional neural network is adopted and improved by proposing a method based on extracting actionness regions. This results in less computation as it is processing only some parts of an RGB frame and also interpret less non-activity related regions, which can mislead the recognition system. We exploit UCF sports dataset as our evaluation benchmark, which is a dataset of realistic sports videos. We will show that our proposed approach could outperform other existing state-of-the art methods.en
languageEnglish
titleEnhancing Human Action Recognition through Temporal Saliencyen
typeConference Paper
contenttypeExternal Fulltext
subject keywordsAction recognitionen
subject keywordsMotionen
subject keywordsRegion proposalen
subject keywordsConvolutional Neural Networksen
subject keywordsActionnessen
identifier linkhttps://profdoc.um.ac.ir/paper-abstract-1069138.html
identifier articleid1069138
  • About Us
نرم افزار کتابخانه دیجیتال "دی اسپیس" فارسی شده توسط یابش برای کتابخانه های ایرانی | تماس با یابش
DSpace software copyright © 2019-2022  DuraSpace