Skip to main content

🏢 Georgia Institute of Technology

Gaze-LLE: Gaze Target Estimation via Large-Scale Learned Encoders
·6779 words·32 mins· loading · loading
AI Generated 🤗 Daily Papers Computer Vision Video Understanding 🏢 Georgia Institute of Technology
Gaze-LLE achieves state-of-the-art gaze estimation by using a frozen DINOv2 encoder and a lightweight decoder, simplifying architecture and improving efficiency.