Proceedings chapter
Open access

Analyzing and Predicting GIF Interestingness

Presented at Amsterdam, The Netherlands, October 15 - 19, 2016
Publication date2016

Animated GIFs have regained huge popularity. They are used in instant messaging, online journalism, social media, among others. In this paper, we present an in-depth study on the interestingness of GIFs. We create and annotate a dataset with a set of affective labels, which allows us to investigate the sources of interest. We show that GIFs of pets are considered more interesting that GIFs of people. Furthermore, we study the connection of interest to other features and factors such as popularity. Finally, we build a predictive model and show that it can estimate GIF interestingness with high accuracy. Our model outperforms the existing methods on GIF popularity, as well as a model based on still image interestingness, by a large margin. We envision that the insights and method developed can be used for automatic recognition and generation of interesting GIFs.

  • GIF
  • Emotion
  • Interest
  • Computer vision
Citation (ISO format)
GYGLI, Michael, SOLEYMANI, Mohammad. Analyzing and Predicting GIF Interestingness. In: MM ’16 Proceedings of the 2016 ACM on Multimedia Conference. Amsterdam, The Netherlands. [s.l.] : [s.n.], 2016. doi: 10.1145/2964284.2967195
Main files (1)
Proceedings chapter (Published version)

Technical informations

Creation03/09/2017 2:15:00 PM
First validation03/09/2017 2:15:00 PM
Update time03/15/2023 1:26:53 AM
Status update03/15/2023 1:26:53 AM
Last indexation01/16/2024 11:27:37 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack