In the process of making a movie, directors constantly care about where the spectator will look on the screen. Shot composition, framing, camera movements or editing are tools commonly used to direct attention. In order to provide a quantitative analysis of the relationship between those tools and gaze patterns, we propose a new eye-tracking database, containing gaze pattern information on movie sequences, as well as editing annotations, and we show how state-of-the-art computational saliency techniques behave on this dataset. In this work, we expose strong links between movie editing and spectators scanpaths, and open several leads on how the knowledge of editing information could improve human visual attention modeling for cinematic content.
Our dataset contains :
- Firsts and lasts frames of each stimulus used, alongside with timestamps. Clips will be shared by the corresponding author upon resonable request.
- Eye-fixation maps for each frame of each stimulus
- Saliency maps for each frame of each stimulus
- Hand-crafted annotations on the editing characteristics of each clips
- Details about each clip
Additional data, including individual fixation locations for each observer, will be shortly added to this page.
Data is available for download here (~1.7Go): ftp://ftp.irisa.fr/local/percept/datasets/saliency/video/Film_editing/eye_tracking_filmmaking.rar
If you have any questions about our work, or need supplementary material, please contact us at alexandre.bruckert@irisa.fr
This dataset is licensed under a Creative Commons Attribution 4.0 License
