Jul 2026
Open-Vocabulary Gaze Object Prediction: Benchmark and Method
This work proposes a framework that leverages text-driven object discovery to localize potential gaze candidates, with a gaze-guided selection module to pinpoint the intended target from the candidate objects, and introduces Gradient-Informed Selection Tuning (GIST) to selectively update parameters most relevant to a g...
Bing-Lu Wang, Sensen Niu, Ying Chen et al.
· arXiv.org · 0 citations