Hand labelled eye movements and targets, together with the output of three automatic classification algorithms for the GazeCom data set

Ioannis Agtzidis 67fadad43f Typo fixes 4 years ago
gaze_arff 99b62106e7 Initial commit 4 years ago
ground_truth 99b62106e7 Initial commit 4 years ago
output_berg_itti 99b62106e7 Initial commit 4 years ago
output_larsson 99b62106e7 Initial commit 4 years ago
output_sp_tool 99b62106e7 Initial commit 4 years ago
targets_arff 2a39948963 Fixed bounding box numbers 4 years ago
LICENSE 07b1fde460 Initial commit 4 years ago
README.md 67fadad43f Typo fixes 4 years ago


GazeCom labels

Here we provide labels for the GazeCom data set. The original gaze files and movie clip are available here.

The ARFF representations of the original GazeCom eye tracking files are provided in the gaze_arff folder and are organized per movie clip in the corresponding file.

The hand annotated fixations, saccades, smooth pursuit, and noise (tracking loss, blinks, physically impossible eye movements) are provided in the ground_truth folder.

We also provide the annotations from our algorithm as detected from the sp_tool, which is based on Agtzidis et al. (2016), along with annotations from Berg et al. (2009) and Larsson et al. (2015) (our re-implementation of the latter is available on the http://michaeldorr.de/smoothpursuit/ page, or via this link) in the corresponding folders starting with output_.

Finally, a collection of 45 hand annotated targets is provided in the targets_arff folder.


The implementation of our clustering-based detection algorithm together with a wide variety of evaluation metrics for eye movement classification can be found here.

Model performance comparison

A tentative evaluation table of sample-level model evaluation statistics for eye movement classification on GazeCom is available at http://michaeldorr.de/smoothpursuit/.

For a more thorough evaluation (all eye movement classes; including event-level metrics), please refer to our later papers:


Agtzidis, I., Startsev, M., & Dorr, M. (2016). Smooth pursuit detection based on multiple observers. In Proceedings of the ninth biennial acm symposium on eye tracking research & applications (pp. 303-306). ACM.

Berg, D. J., Boehnke, S. E., Marino, R. A., Munoz, D. P., & Itti, L. (2009). Free viewing of dynamic stimuli by humans and monkeys. Journal of vision, 9(5), 19-19.

Larsson, L., Nyström, M., Andersson, R., & Stridh, M. (2015). Detection of fixations and smooth pursuit movements in high-speed eye-tracking data. Biomedical Signal Processing and Control, 18, 145-152.