Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper addresses the issue of inaccurate latency reporting in browser-based webcam gaze trackers by introducing a novel methodology that utilizes the browser's requestVideoFrameCallback API to measure gaze inference latency more accurately. The authors demonstrate how to recover a per-frame capture clock, allowing for precise source-frame pairing and establishing verifiable lower bounds on latency for gaze tracking engines. Their open-source TypeScript implementation, tested on WebGazer and a new FaceMesh+KRR pipeline, provides a significant improvement in the reliability of gaze tracking metrics for both research and clinical applications.
Browser gaze trackers may report zero latency, but this new methodology reveals the true delays, providing crucial insights for real-world applications.
Browser-based webcam gaze trackers are increasingly used for crowd-scale data collection and in clinical settings where lab eye trackers are impractical, but the reported latency numbers may not represent real world functionality. The common practice of timestamping each gaze sample when it is emitted, rather than when its source frame was captured, makes the measured inference latency read about $0\,$ms no matter how slow the engine really is. We show how to measure it honestly, recovering a per-frame capture clock from the browser's \texttt{re\-quest\-Video\-Frame\-Call\-back} (rVFC) API (\texttt{captureTime} where the browser exposes it for local camera streams, else \texttt{presentationTime}, in which case every recovered latency is a verifiable lower bound): exact source-frame pairing through a per-frame queue for engines that expose their inference pipeline, and a further lower bound for engines that do not, such as WebGazer. We release an open TypeScript implementation and benchmark harness, demonstrated on two interchangeable engines: WebGazer and a new FaceMesh+KRR pipeline.