InsightInsight
IPIC-Ribbon-Horizontal-2-Small
  • About
    • What We Do
    • Governance
    • Equality, Diversity and Inclusion
  • People
    • Work With Us
    • Senior Leadership
    • Principal Investigators
    • Funded Investigators
    • Research and Operations
  • Research
    • Central Bank PhD Programme
    • Excellence
    • Funding Collaboration
    • MSCA Postdoctoral Fellowships
    • National Projects
    • European Projects
  • Industry
    • Collaborate
    • Insight Brochure
    • Commercialisation
    • Contact
  • Public Engagement
    • Meet the Team
    • Highlights
    • Insight Scholarship
  • News
    • Spotlight on Research
    • Events
    • Newsletter
    • Press Releases
  • Contact
  • About
    • What We Do
    • Governance
    • Equality, Diversity and Inclusion
  • People
    • Work With Us
    • Senior Leadership
    • Principal Investigators
    • Funded Investigators
    • Research and Operations
  • Research
    • Central Bank PhD Programme
    • Excellence
    • Funding Collaboration
    • MSCA Postdoctoral Fellowships
    • National Projects
    • European Projects
  • Industry
    • Collaborate
    • Insight Brochure
    • Commercialisation
    • Contact
  • Public Engagement
    • Meet the Team
    • Highlights
    • Insight Scholarship
  • News
    • Spotlight on Research
    • Events
    • Newsletter
    • Press Releases
  • Contact

Extracting captions from long videos with multiple actors and multiple actions

Insight>Projects>Extracting captions from long videos with multiple actors and multiple actions

Funding Programme or Company Name:

Enterprise Partnership Postgraduate Fellowship

Funding Body:

Irish Research Council (IRC)

Description:

Video security, e.g. CCTV, is extremely important to ensure that our cities, citizens and society remain safe. Current approaches require labour intensive human oversight where multiple lengthy videos need to be reviewed before the event of interest can be observed and appropriate action taken. The humans involved in this important task are overloaded and require support from novel technologies that could help e.g. systems that help them to quickly summarise, index and navigate video content. One of the most compact and interpretable ways of conveying information is using text to describe what takes place in a video. It has been recognized by the United Technology Research Center Ireland (UTRC) that this kind of technology could significantly extend their solutions portfolio for video security in buildings, which is a key market. Thus the aim of my PhD is to create a novel technique to extract text descriptions/captions from security videos. The current works in these fields are limited to a single actor and single actions and current datasets consist of short videos, seconds in duration, with a very limited textual vocabulary. This project will aim to extend the existing techniques to apply them to longer videos with multiple actors and actions Using state of the art deep learning techniques, like recurrent neural networks and attention models, I will investigate adding other features such as pose estimation, to predict actions, or people re-identification, to produce a richer textual description of the video

Insight Contact:

Noel O’Connor

Application Domain:

Connected Health

Research Group:

Media Analytics

Associated Theme for Application Domain:

  • Connected Health-Chronic Disease Management & Rehabilitation
  • The Discovery Economy-The Analytical Society
  • The Discovery Economy-Discovery Analytics

Involved Institution:

Dublin City University (DCU)

Non-Insight Contact:

Luis Lebron Ca

Funding Body Logo:

Insight_host_partners_funder
Ireland's European Structural and Investment Funds Programme 2014-2022 logo
European Union European Regional Development Fund logo
  • Privacy Statement
  • Copyright Statement
  • Data Protection Notice
  • Accessibility Statement