AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

EEGEyeNet: a Simultaneous Electroencephalography and Eye-tracking Dataset and Benchmark for Eye Movement Prediction

Ard Kastrati, Martyna Beata Plomecka, Damian Pascual, Lukas Wolf, Victor Gillioz, Roger Wattenhofer, Nicolas Langer

NeurIPS 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use deep learning models instead of classical MLCNN · EEGEyeNet Abs. PositionRMSE (mm): 123 -> 70.2Improved
Use CNN instead of tree-based modelsCNN · EEGEyeNet Angle/Amplitudeangle RMSE (rad): 1.09 -> 0.33Improved
Use deep models instead of tree-based models on Left-RightCNN · EEGEyeNet Left-Rightaccuracy (%): 97.9 -> 98.3Improved
Use simpler CNN rather than EEGNetCNN · EEGEyeNet Abs. PositionRMSE (mm): 81.7 -> 70.2Improved
Use tree-based models instead of linear modelsXGBoost · EEGEyeNet Angle/Amplitudeangle RMSE (rad): 1.39 -> 1.11Improved
Use RBF SVC/SVR instead of other classical modelsRBF SVC/SVR · EEGEyeNet Angle/Amplitudeamplitude RMSE (mm): 74.7 -> 75.9Hurt
Classical models on absolute position versus naive baselineKNN · EEGEyeNet Abs. PositionRMSE (mm): 123.3 -> 119.7No clear effect
Use maximal instead of minimal preprocessing (ablation)CNN · EEGEyeNet Left-Rightaccuracy (%): 98.3 -> 75.5Hurt
Use maximal instead of minimal preprocessing (ablation)PyramidalCNN · EEGEyeNet Left-Rightaccuracy (%): 98.5 -> 86.6Hurt
Use maximal instead of minimal preprocessing (ablation)XGBoost · EEGEyeNet Left-Rightaccuracy (%): 97.9 -> 68.3Hurt
Use maximal instead of minimal preprocessing (ablation)CNN · EEGEyeNet Abs. PositionRMSE (mm): 70.2 -> 134.6Hurt
Use maximal instead of minimal preprocessing (ablation)CNN · EEGEyeNet Angle/Amplitudeangle RMSE (rad): 0.33 -> 1.07Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy