Conference paper Open Access

Image Aesthetics Assessment using Fully Convolutional Neural Networks

Apostolidis, Konstantinos; Mezaris, Vasileios


JSON-LD (schema.org) Export

{
  "inLanguage": {
    "alternateName": "eng", 
    "@type": "Language", 
    "name": "English"
  }, 
  "description": "<p>This paper presents a new method for assessing the aesthetic quality of images. Based on the findings of previous works on this topic, we propose a method that addresses the shortcomings of existing ones, by: a) Making possible to feed higher-resolution images in the network, by introducing a fully convolutional neural network as the classier. b) Maintaining the original aspect ratio of images in the input of the network, to avoid distortions caused by re-scaling. And c) combining local and global features from the image for making the assessment of its aesthetic quality. The proposed method is shown to achieve state of the art results on a standard large-scale benchmark dataset.</p>", 
  "license": "https://creativecommons.org/licenses/by/4.0/legalcode", 
  "creator": [
    {
      "affiliation": "Information Technologies Institute / Centre for Research & Technology - Hellas", 
      "@type": "Person", 
      "name": "Apostolidis, Konstantinos"
    }, 
    {
      "affiliation": "Information Technologies Institute / Centre for Research & Technology - Hellas", 
      "@type": "Person", 
      "name": "Mezaris, Vasileios"
    }
  ], 
  "headline": "Image Aesthetics Assessment using Fully Convolutional Neural Networks", 
  "image": "https://zenodo.org/static/img/logos/zenodo-gradient-round.svg", 
  "datePublished": "2019-01-10", 
  "url": "https://zenodo.org/record/2539133", 
  "@type": "ScholarlyArticle", 
  "keywords": [
    "Image Aesthetics", 
    "Deep Learning", 
    "Fully Convolutional Neural Networks"
  ], 
  "@context": "https://schema.org/", 
  "identifier": "https://doi.org/10.1007/978-3-030-05710-7_30", 
  "@id": "https://doi.org/10.1007/978-3-030-05710-7_30", 
  "workFeatured": {
    "url": "http://mmm2019.iti.gr/", 
    "alternateName": "MMM 2019", 
    "location": "Thessaloniki, Greece", 
    "@type": "Event", 
    "name": "25th International Conference on Multimedia Modeling"
  }, 
  "name": "Image Aesthetics Assessment using Fully Convolutional Neural Networks"
}
193
147
views
downloads
Views 193
Downloads 147
Data volume 150.1 MB
Unique views 182
Unique downloads 135

Share

Cite as