Conference paper Open Access

Unsupervised Video Summarization via Attention-Driven Adversarial Learning

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


Citation Style Language JSON Export

{
  "DOI": "10.1007/978-3-030-37731-1_40", 
  "title": "Unsupervised Video Summarization via Attention-Driven Adversarial Learning", 
  "issued": {
    "date-parts": [
      [
        2020, 
        1, 
        6
      ]
    ]
  }, 
  "abstract": "<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>", 
  "author": [
    {
      "family": "Apostolidis, Evlampios"
    }, 
    {
      "family": "Adamantidou, Eleni"
    }, 
    {
      "family": "Metsai, Alexandros"
    }, 
    {
      "family": "Mezaris, Vasileios"
    }, 
    {
      "family": "Patras, Ioannis"
    }
  ], 
  "id": "3605501", 
  "event-place": "Daejeon, Korea", 
  "type": "paper-conference", 
  "event": "26th Int. Conf. on Multimedia Modeling (MMM 2020)"
}
529
182
views
downloads
Views 529
Downloads 182
Data volume 178.1 MB
Unique views 515
Unique downloads 171

Share

Cite as