Event-based Eye Tracking
AI for Streaming CVPR 2024 Challenge

Zuowen Wang1, Chang Gao2, Zongwei Wu3, Shih-Chii Liu1, Qinyu Chen1,4,
1Sensors Group, Institute of Neuroinformatics, UZH/ETH Zurich, 2EMI Lab,TU Delft, 3Computer Vision Lab, University of Wurzburg, 4LIACS, Leiden University
Presentation at CVPR AI for Streaming Workshop
Kaggle Github Data Challenge Report
Event-based eye-tracking video game demo

Let's play some video games with event-based eye-tracking!

This video was filmed at the 2023 Telluride Neuromorphic Cognition Engineering Workshop, CO, US, by Qinyu Chen and Chang Gao.

About the Challenge

Developing an event-based eye-tracking system presents significant opportunities in diverse fields, notably in consumer electronics and neuroscience. Human eyes exhibit rapid movements, occasionally surpassing speeds of 300°/s. This necessitates using event cameras capable of high-speed sampling and tracking.

In consumer electronics, particularly in augmented and virtual reality (AR/VR) applications, the primary benefits of event-based systems extend beyond their high speed. Their highly sparse input data streams can be exploited to reduce power consumption. This is a pivotal advantage in creating lighter, more efficient wearable headsets that offer prolonged usage and enhanced user comfort.

This is instrumental in augmenting the immersive experience in AR/VR and expanding the capabilities of portable technology. In neuroscience and cognitive studies, such technology is crucial for deciphering the complexities of eye movement. It facilitates a deeper comprehension of visual attention processes and aids in diagnosing and understanding neurological disorders.

This challenge aims to develop an **event-based eye-tracking system for precise tracking of rapid eye movements** to produce lighter and more comfortable devices for a better user experience. Simultaneously, it promises to provide novel insights into neuroscience and cognitive research, deepening our understanding of these domains.

The challenge will held with the 1st edition of AI for Streaming workshop, in conjunction with CVPR 2024.

News

[16/03/2024] Challenge Ends! Thanks for your interest in our challenge!

[02/05/2024] Challenge Starts!

[01/29/2024] Release Website

Contact

If you have technical questions on the challenge, please contact us at:
- Zuowen Wang (zuowen [at] ini [dot] uzh [dot] ch)
- Qinyu Chen (q.chen [at] liacs [dot] leidenuniv [dot] nl)

Winners will be invited, after being reviewed, to present during the associated CVPR workshop.
Other top-ranked teams may be invited to a tentative report for documenting the challenge.
For more details, please contact workshop organizers.

Program Committee Members (TBU):

Zuowen Wang, UZH/ETH Zurich
Chang Gao, TU Delft
Zongwei Wu, University of Wurzburg
Shih-Chii Liu, UZH/ETH Zurich
Qinyu Chen, UZH/ETH Zurich & Leiden University

Zhuyun Zhou, University of Burgundy
Remi Boutteau, University of Rouen Normandy
Dominique Ginhac, University of Burgundy
Fan Yang-Song, University of Burgundy
Guillaume Caron, CNRS-AIST JRL, IRL 3218 & UPJV
Menghan Hu, East China Normal University
Guohao Lan, TU Delft
Xucong Zhang, TU Delft
Zhuo Zou, Fudan University
Congyi Sun, Nanjing University
Shilin Fu, Dalian University of Technology
Zixiao Li, UZH/ETH Zurich
Joachim Ott, UZH/ETH Zurich

BibTeX


      @inproceedings{chen20233et,
      title={3et: Efficient event-based eye tracking using a change-based convlstm network},
      author={Chen, Qinyu and Wang, Zuowen and Liu, Shih-Chii and Gao, Chang},
      booktitle={2023 IEEE Biomedical Circuits and Systems Conference (BioCAS)},
      pages={1--5},
      year={2023},
      organization={IEEE}
    }

      @inproceedings{wang2024ais_event, 
      title={{E}vent-{B}ased {E}ye {T}racking. {AIS} 2024 {C}hallenge {S}urvey}, 
      author={Zuowen Wang and Chang Gao and Zongwei Wu and Marcos V. Conde and Radu Timofte and Shih-Chii Liu and Qinyu Chen and others}, 
      booktitle={Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops}, 
      year={2024}
    }