Multimedia Quality Modeling

Submission deadline: 1 October 2015
Publication: July–September 2016

Multimedia quality models aim at evaluating the quality of multimedia (image, audio, and video) items in various applications, including multimedia search and recommendation and multimedia transmission. The quality criteria deployed in such models are typically related to human perception (audio or visual distortions, for example) or to aesthetic appeal related to a given multimedia item. For example, a photo management system that can rank photos based on perceptual quality criteria (such as the resolution or presence of visible distortions), or the criteria related to aesthetics could help users select not only topically relevant photos but also those most appealing and representative for their albums. Furthermore, being able to assess the acceptable quality of an audiovisual signal can guide cost-effective optimization of signal processing (compression, cropping, retargeting) and transmission.

Extensive research efforts have been dedicated to designing multimedia quality models, but effective tools for quality prediction are still in their infancy. The largest potential for growth has been recognized along the following lines: emphasizing the role of multimedia content semantics as a parameter in assessing the quality of multimedia items, better exploiting cross-media analysis for quality assessment, and handling the instability of the biologically/psychologically inspired multimedia features in reflecting human perception.
This special issue targets the researchers and practitioners from both the industry and academia. It solicits original contributions reflecting the most recent progress on data-driven models for image, video, and audio quality prediction and on discovering new types of visual/acoustic cues in computational quality models. The topics of interest include, but are not limited to, the following:

  • new data-driven computational models for media quality evaluation;
  • aesthetic models for multimedia applications;
  • quality-driven video and image summarization;
  • semantic models for multimedia quality prediction;
  • multimodal quality models for event and abnormality detection;
  • visual quality prediction for photo and video management systems;
  • human interactive learning for multimedia quality prediction;
  • data-driven quality models for large-scale multimedia retrieval;
  • advanced descriptors for evaluating multimedia quality; and
  • datasets, benchmarks, and validation of multimedia quality of experience.

Submission Information

Submissions should no more than 6,500 words, including all text, the abstract, keywords, bibliography, biographies, and table text. The word count should include 200 words for each table and figure. For general author guidelines, see

To submit your article directly to our online peer-review system, go directly to Manuscript Central (

Guest Editors