This eye tracking video database has been created to allow the comparison of Deep learning model against other saliency models. It can be used to validate visual attention models. This dataset includes 132 videos, we have selected a representative subset of videos using multiple known video datasets (CITIUS, CRCNS, DIEM, AE-UCFS, ASCMN, GC, Holly2Train, Holly2Test) acquired with different eye trackers. Most of them are too focused in a unique topic, so we have selected some representative videos for different categories. The videos can be classified in four categories, syntetic, urban, natural and indoors. The videos have been selected in order to minimize the influence of the top-down efects.
If you only want to download the videos you can do it by clicking on the download icons of the previous section. If you have a fast enough internet connection and you prefer to download a stand alone file, with all the information and folder structure included inside, you can download by clicking on this link: