Jul 2026
Open-Vocabulary Gaze Object Prediction: Benchmark and Method
Gaze Object Prediction (GOP) aims to localize and recognize the objects humans attend to, a task crucial for understanding human-centric interactions. However, existing methods are typically trained under a closed-vocabulary paradigm with a fixed label space and evaluated on scene-specific datasets, limiting their appl...
Binglu Wang, Sensen Niu, Ying Chen et al.
· arXiv.org · 0 citations