Reproduce “Event-Based Eye Tracking. AIS 2024 Challenge Survey” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Zuowen Wang, Chang Gao, Zongwei Wu, Marcos V. Conde, Radu Timofte, Shih-Chii Liu, Qinyu Chen, Zheng-jun Zha and 31 more
The authors survey methods for tracking pupil centers from real event-camera recordings in a challenge evaluating accuracy and practical efficiency. Event cameras capture asynchronous brightness changes, and submissions use varied temporal and model approaches. USTCEventGroup ranked first with 99.58% p10 accuracy, meaning predictions within 10 pixels, on the private test split; this does not establish real-time speed or deployment readiness.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.