# Event-based Eye Tracking - AIS2024 CVPR Workshop — Data

来源：https://www.kaggle.com/competitions/event-based-eye-tracking-ais2024/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

## Dataset Description
There are 13 subjects in total, each having 2-6 recording sessions. The subjects are required to perform 5 classes of activities: random, saccades, read text, smooth pursuit, and blinks. Figure 2 visualizes one real recording sample by making the raw events into event frames. The total data volume is approximately 1 GB in the compressed .h5 form. Depending on your method, you may have very different data representations and processing pipelines based on the raw events. We provide an event [voxel-grid-based](https://tonic.readthedocs.io/en/latest/auto_examples/representations/plot_tovoxelgrid.html#sphx-glr-auto-examples-representations-plot-tovoxelgrid-py) data loading pipeline in the GitHub repository. It will automatically slice the raw event recordings into subsequences. For more details please refer to the GitHub repository.

#### Labeling
The ground truth is labeled at 100Hz and consists of two parts for each label (x, y, close) with 

* labeling of the pupil center coordinates (x,y).
* a binary value 'close' indicating whether the eye blinks or not (0 for opening, 1 for closing). 

Labels (x,y, close) for the train split are provided at a frequency of 100Hz. The user is free to decide if they would like to downsample this frequency and whether to use the close label or not. In the training sample pipeline we provided, the labels are downsampled to 20Hz and we do not use the close label by default. For the test set, we will evaluate the prediction at **20Hz** only. If you would like to alter the data loading pipeline, please be aware of this downsampling.

#### Dataset splitting
We use 12 recordings for testing (test_files.txt) and the remaining recordings are for the user to train (dataset/train_files.txt ) and validate (dataset/val_files.txt) their methods. The users are free to re-divide the training and validation sets in train_files.txt and val_files.txt.