Conference proceedings
Open access

The Quest for Visual Interest

Publication date2015

In this paper, we report on identifying the underlying factors that contribute to the visual interest in digital photos. A set of 1005 digital photos covering different topics and of different qualities was collected from Flickr. Images were annotated by a pool of diverse participants on a crowdsourcing platform. 12 bipolar ratings were collected for each photo on 7-point semantic differential scale, including dimensions related to interest, emotions and image quality. Every image received 20 annotations from unique participants. The most important appraisals and visual attributes for visual interest in photos was identified. We found that intrinsic pleasantness, arousal, visual quality and coping potential are the most important factors contributing to visual interest in digital photos. We developed a system that automatically detects the important visual attributes from low level visual features and demonstrated their significance in predicting interest at individual level.

  • Interest
  • Emotion
  • Appraisal
  • Crowdsourcing
  • Computer vision
  • Swiss National Science Foundation - Ambizione-Soleymani
Citation (ISO format)
SOLEYMANI, Mohammad. The Quest for Visual Interest. [s.l.] : [s.n.], 2015.
Main files (1)
Proceedings (Accepted version)
  • PID : unige:76717

Technical informations

Creation09/20/2015 3:45:00 PM
First validation09/20/2015 3:45:00 PM
Update time03/14/2023 11:46:31 PM
Status update03/14/2023 11:46:31 PM
Last indexation01/16/2024 7:21:08 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack