I need to train a neural net classifier for different types of eye movements, and there seems very little data available on this.

1 Answer 1


quick web search gives handful of resources


This was the first data set with held-out human eye movements, and is used as a benchmark test set. eyetracker: ETL 400 ISCAN (240Hz)


This dataset contains two sets of images: train and test. Train images (100 from each category) and fixations of 18 observers are shared but 6 observers are held-out. Test images are available but fixations of all 24 observers are held out. eyetracker: EyeLink1000 (1000Hz)

http://gazecapture.csail.mit.edu and https://github.com/CSAILVision/GazeCapture

In the dataset, we include data for 1474 unique subjects. Each numbered directory represents a recording session from one of those subjects. Numbers were assigned sequentially, although some numbers are missing for various reasons (e.g., test recordings, duplicate subjects, or incomplete uploads).


We collected eye tracking data for the complete trainval set of ten objects classes (cat, dog, bicycle, motorbike, boat, aeroplane, horse, cow, sofa, diningtable) from Pascal VOC 2012 [2] (6,270 images in total). Each image is annotated with the eye movement record of five participants, whose task was to identify which object class was present in the image.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.