AI RESEARCH

Enhancing Gaze Reasoning in Vision Foundation Models for Gaze Following

arXiv CS.CV

ArXi:2605.22607v1 Announce Type: new Gaze following requires both scene understanding and gaze reasoning to localize the gaze target of an in-scene person. Recently, vision foundation models (VFMs) have nstrated strong performance on this task, enabling simpler architectures while outperforming prior methods. However, we observe a key limitation of VFM-based approaches: while VFMs substantially improve scene understanding, they contribute little to gaze reasoning.