New Promptable Gaze Estimation Method Introduced with GazeAnywhere Model

Researchers have introduced a new approach called Promptable Gaze Target Estimation (PGE) for analyzing human gaze in images. This method uses natural language or visual prompts to identify specific subjects for gaze analysis, integrating subject localization with gaze estimation. A new dataset, Gaze-Co, and a model named GazeAnywhere have been developed to support this task, with GazeAnywhere achieving state-of-the-art performance on PGE benchmarks. AI

IMPACT This new approach could enhance the flexibility and scalability of gaze analysis in various applications, from human-computer interaction to clinical studies.

RANK_REASON The cluster describes a new research paper introducing a novel task, dataset, and model for gaze target estimation. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv cs.AI →

• alphaXiv
• arXiv
• CatalyzeX
• DagsHub
• GazeAnywhere
• Gotit.pub
• Hugging Face
• Promptable Gaze Target Estimation
• ScienceCast

• paper
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →