Conference paper Open Access

Unsupervised Video Summarization via Attention-Driven Adversarial Learning

Apostolidis, Evlampios; Adamantidou, Eleni; Metsai, Alexandros; Mezaris, Vasileios; Patras, Ioannis


JSON-LD (schema.org) Export

{
  "description": "<p>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 rst 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&#39;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 architecture (SUM-GAN-VAAE), and ii) by replacing the VAE with a deterministic attention auto-encoder (SUM-GAN-AAE). Experimental evaluation on two datasets (SumMe and TVSum) documents the contribution of the attention auto-encoder to faster and more stable training of the model, resulting in a signicant performance improvement with respect to the original model and demonstrating the competitiveness of the proposed SUM-GAN-AAE against the state of the art.&nbsp;Software is publicly available at: https://github.com/e-apostolidis/SUM-GAN-AAE</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "CERTH & QMUL", 
      "@type": "Person", 
      "name": "Apostolidis, Evlampios"
    }, 
    {
      "affiliation": "CERTH", 
      "@type": "Person", 
      "name": "Adamantidou, Eleni"
    }, 
    {
      "affiliation": "CERTH", 
      "@type": "Person", 
      "name": "Metsai, Alexandros"
    }, 
    {
      "affiliation": "CERTH", 
      "@type": "Person", 
      "name": "Mezaris, Vasileios"
    }, 
    {
      "affiliation": "QMUL", 
      "@type": "Person", 
      "name": "Patras, Ioannis"
    }
  ], 
  "headline": "Unsupervised Video Summarization via Attention-Driven Adversarial Learning", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2020-01-06", 
  "url": "https://zenodo.org/record/3605501", 
  "@type": "ScholarlyArticle", 
  "keywords": [
    "Video summarization", 
    "Unsupervised learning", 
    "Attention mechanism", 
    "Adversarial learning"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1007/978-3-030-37731-1_40", 
  "@id": "https://doi.org/10.1007/978-3-030-37731-1_40", 
  "workFeatured": {
    "alternateName": "MMM 2020", 
    "location": "Daejeon, Korea", 
    "@type": "Event", 
    "name": "26th Int. Conf. on Multimedia Modeling"
  }, 
  "name": "Unsupervised Video Summarization via Attention-Driven Adversarial Learning"
}
530
182
views
downloads
Views 530
Downloads 182
Data volume 178.1 MB
Unique views 516
Unique downloads 171

Share

Cite as