Colour in Context
Research group
Computer Vision Center

Learning to Rank Images using Semantic and Aesthetic Labels

Naila Murray, Luca Marchesotti, Florent Perronnin
(to appear) British machine and vision conference (BMVC) - 2012
Download the publication : murray12.pdf [333Ko]   supplementary_material.pdf [5.6Mo]  
Most works on image retrieval from text queries have addressed the problem of retrieving semantically relevant images. However, the ability to assess the aesthetic quality of an image is an increasingly important differentiating factor for search engines. In this work, given a semantic query, we are interested in retrieving images which are semantically relevant and score highly in terms of aesthetics/visual quality. We use large-margin classifiers and rankers to learn statistical models capable of ordering images based on the aesthetic and semantic information. In particular, we compare two families of approaches: while the first one attempts to learn a single ranker which takes into account both semantic and aesthetic information, the second one learns separate semantic and aesthetic models. We carry out a quantitative and qualitative evaluation on a recently-published large-scale dataset and we show that the second family of techniques significantly outperforms the first one.

Images and movies

 

BibTex references

@InProceedings\{MMP2012a,
  author       = "Naila Murray and Luca Marchesotti and Florent Perronnin",
  title        = "Learning to Rank Images using Semantic and Aesthetic Labels",
  booktitle    = "(to appear) British machine and vision conference (BMVC)",
  year         = "2012",
  abstract     = "Most works on image retrieval from text queries have addressed the problem of retrieving semantically relevant images. However, the ability to assess the aesthetic quality of an image is an increasingly important differentiating factor for search engines. In this work, given a semantic query, we are interested in retrieving images which are semantically relevant and score highly in terms of aesthetics/visual quality. We use large-margin classifiers and rankers to learn statistical models capable of ordering images based on the aesthetic and semantic information. In particular, we compare two families of approaches: while the first one attempts to learn a single ranker which takes into account both semantic and aesthetic information, the second one learns separate semantic and aesthetic models. We carry out a quantitative and qualitative evaluation on a recently-published large-scale dataset and we show that the second family of techniques significantly outperforms the first one.    ",
  url          = "http://cat.uab.cat/Public/Publications/2012/MMP2012a"
}

Other publications in the database

 © 2008 Colour in context Group | Computer Vision Center. All rights reserved | Contact webmaster |  Last updated: Monday 11 May 2009     eXTReMe Tracker