GazeCLIP: Towards Enhancing Gaze Estimation via Text Guidance

arXiv:2401.00260v3 Announce Type: replace
Abstract: Over the past decade, visual gaze estimation has garnered increasing attention within the research community, owing to its wide-ranging application scenarios. While existing estimation approaches have achieved remarkable success in enhancing prediction accuracy, they primarily infer gaze from single-image signals, neglecting the potential benefits of the currently dominant text guidance. Notably, visual-language collaboration has been extensively explored across various visual tasks, such as image synthesis and manipulation, leveraging the remarkable transferability of large-scale Contrastive Language-Image …

abstract accuracy application arxiv attention benefits community cs.cv guidance image prediction research research community success text type via visual while