24 videos (5 classes: Abnormal, Surveillance, Crowd, Moving, Noise) / 10 observers per video. No specific task was asked to the viewers. The eye-tracker raw data sampled at the frame rate of each video are provided.
The dataset can be downloaded from the webpage: Link: http://www.tcts.fpms.ac.be/attention/ Direct link to the ZIP file: Link: http://www.tcts.fpms.ac.be/attention/data/documents/data/ACCV2012_database.zip
The original link was: http://www.tcts.fpms.ac.be/attention/
References and Citation
If you use the database, please cite this reference [RMC12].
RMC12: N. Riche, M. Mancas, D. Ćulibrk, V. Ćrnojevic, B. Gosselin, T. Dutoit, Dynamic saliency models and human attention: a comparative study on videos, Proceedings of the 11th Asian Conference on Computer Vision (ACCV), Daejeon, Korea, November 5-9.