publication . Part of book or chapter of book . Conference object . 2020

Unsupervised Video Summarization via Attention-Driven Adversarial Learning

Evlampios E. Apostolidis; Eleni Adamantidou; Alexandros I. Metsai; Vasileios Mezaris; Ioannis Patras;
Open Access
  • Published: 06 Jan 2020
  • Publisher: Springer International Publishing
This 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. Starting from the SUM-GAN model, we first develop an improved version of it (called SUM-GAN-sl) that has a significantly reduced number of learned parameters, performs incremental training of the model’s components, and applies a stepwise label-based strategy for updating the adversarial part. Subsequently, we introduce an attention mechanism to SUM-GAN-sl in two ways: (i) by integrating an attention layer within the variational auto-encoder (VAE) of the a...
Persistent Identifiers
free text keywords: Video summarization, Unsupervised learning, Attention mechanism, Adversarial learning, Performance improvement, Computer science, Generative grammar, Architecture, Unsupervised learning, Machine learning, computer.software_genre, computer, Software, business.industry, business, Automatic summarization, Artificial intelligence, Adversarial system
Funded by
Enhancing and Re-Purposing TV Content for Trans-Vector Engagement
  • Funder: European Commission (EC)
  • Project Code: 780656
  • Funding stream: H2020 | RIA
Download fromView all 2 versions
Conference object . 2020
Provider: ZENODO
Part of book or chapter of book
Provider: UnpayWall
Part of book or chapter of book . 2019
Provider: Crossref
Any information missing or wrong?Report an Issue