New methodology measures webcam gaze tracker latency honestly

Researchers have developed a new methodology called Capture-Clock to accurately measure the latency of browser-based webcam gaze trackers. This method addresses the issue where current trackers often report inaccurate latency by timestamping gaze samples upon emission rather than capture. The new approach utilizes the browser's requestVideoFrameCallback API to recover a per-frame capture clock, enabling more honest latency measurements. An open-source TypeScript implementation is provided, demonstrated with engines like WebGazer and a FaceMesh+KRR pipeline. AI

IMPACT Improves accuracy in webcam-based gaze tracking, crucial for research and clinical applications.

RANK_REASON The cluster contains a research paper detailing a new methodology and implementation for measuring webcam gaze tracker latency. [lever_c_demoted from research: ic=1 ai=0.7]

Read on arXiv cs.CV →

• Capture-Clock Methodology
• captureTime
• FaceMesh
• knowledge representation and reasoning
• presentationTime
• requestVideoFrameCallback
• TypeScript
• Webcam Gaze
• WebGazer

• paper
• product
• infra

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