Papers › RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments

RT-BENE: A Dataset and Baselines for Real-Time Blink Estimation in Natural Environments

27 Oct 2019IEEE International Conference on Computer Vision Workshops 2019 10archive 2025-07-28

Kévin Cortacero, Tobias Fischer, Yiannis Demiris

In recent years gaze estimation methods have made substantial progress, driven by the numerous application areas including human-robot interaction, visual attention estimation and foveated rendering for virtual reality headsets. However, many gaze estimation methods typically assume that the subject's eyes are open; for closed eyes, these methods provide irregular gaze estimates. Here, we address this assumption by first introducing a new open-sourced dataset with annotations of the eye-openness of more than 200,000 eye images, including more than 10,000 images where the eyes are closed. We further present baseline methods that allow for blink detection using convolutional neural networks. In extensive experiments, we show that the proposed baselines perform favourably in terms of precision and recall. We further incorporate our proposed RT-BENE baselines in the recently presented RT-GENE gaze estimation framework where it provides a real-time inference of the openness of the eyes. We argue that our work will benefit both gaze estimation and blink estimation methods, and we take steps towards unifying these methods.

PaperPDFCode

Code

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Blink estimationGaze Estimation

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Blink estimation Eyeblink8 DenseNet 121 Ensemble F1 0.976 #1 of 1 Archive leaderboard report
Blink estimation RT-BENE DenseNet 121 Ensemble F1 0.721 #1 of 1 Archive leaderboard report
Blink estimation Researcher's Night DenseNet 121 Ensemble F1 0.913 #1 of 1 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections