ReTV: Re-Inventing TV for the Interactive Age
  • About
    • Project Overview
    • Partners
    • Related Projects
  • News
    • Blog
    • Events
  • Use Cases
    • Topics Compass: News Discourse Monitoring
    • Content Wizard: Content Adaptation and Publication Online
    • 4U2: Personalised, AI-driven Content
    • Content sWitch: Personalised TV Stream
  • Results
    • Demos
    • Deliverables
    • Publications and Conference Papers
    • Presentations
    • ReTV Webinar
  • DataTV Community
  • Zenodo
  • Contact
ReTV: Re-Inventing TV for the Interactive Age
  • About
    • Project Overview
    • Partners
    • Related Projects
  • News
    • Blog
    • Events
  • Use Cases
    • Topics Compass: News Discourse Monitoring
    • Content Wizard: Content Adaptation and Publication Online
    • 4U2: Personalised, AI-driven Content
    • Content sWitch: Personalised TV Stream
  • Results
    • Demos
    • Deliverables
    • Publications and Conference Papers
    • Presentations
    • ReTV Webinar
  • DataTV Community
  • Zenodo
  • Contact
Jan 14

ReTV award-winning paper at the MMM2020

  • January 14, 2020
  • About
  • Latest Posts
Konstantinos Apostolidis
Konstantinos Apostolidis
Research Assistant at CERTH
Konstantinos Apostolidis
Latest posts by Konstantinos Apostolidis (see all)
  • Summarizing videos on the Web - April 16, 2020
  • ReTV award-winning paper at the MMM2020 - January 14, 2020
  • The SUM-GAN-sl method for video summarization - October 22, 2019

On January 8th, ReTV’s partners CERTH presented the ReTV-supported paper on “Unsupervised Video Summarization via Attention-Driven Adversarial Learning” at the 26th International Conference on Multimedia Modeling in Daejeon, Korea.

Authored by E. Apostolidis, E. Adamantidou, A. Metsai, V. Mezaris & I. Patras, the paper has been awarded the “Best Paper Award ” by the organizing committee of the conference.

Unsupervised Video Summarization via Attention-Driven Adversarial Learning – SUM-GAN-AAE model

The paper presents a new video summarization approach that integrates an attention mechanism to identify the significant parts of the video, and is trained unsupervisingly via generative adversarial learning. 

Are you interested in knowing more? You can read the full-text paper here, access the presentation slides here and the related software used in the paper: here.

  • Facebook
  • Twitter
  • LinkedIn
  • E-Mail

Comments are closed.

CONTACT:
Project Coordinator
Lyndon Nixon
MODUL Technology
info(Replace this parenthesis with the @ sign)retv-project.eu

Follow us

  • Facebook
  • LinkedIn
  • Twitter

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No. 780656.
The European Commission does not guarantee the accuracy of the information and accepts no responsibility or liability whatsoever with regard to the information on this website.

  • About
    ▼
    • Project Overview
    • Partners
    • Related Projects
  • News
    ▼
    • Blog
    • Events
  • Use Cases
    ▼
    • Topics Compass: News Discourse Monitoring
    • Content Wizard: Content Adaptation and Publication Online
    • 4U2: Personalised, AI-driven Content
    • Content sWitch: Personalised TV Stream
  • Results
    ▼
    • Demos
    • Deliverables
    • Publications and Conference Papers
    • Presentations
    • ReTV Webinar
  • DataTV Community
  • Zenodo
  • Contact