Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
WebEyeTrack: Scalable Eye-Tracking for the Browser via On-Device Few-Shot Personalization
Eduardo Davalos, Yike Zhang, Namrata Srivastava, Yashvitha Thatigotla, Ashwin Tudur Sadashiva, Jorge Salas, Sun-Joo Cho, Amanda Goodwin, Gautam Biswas
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| use BlazeGaze instead of the previous fastest model Mnist | gaze estimator · Inference speed (CPU) | FPS: 319.0 -> 1137.0 | Improved |
| use BlazeGaze instead of AFF-Net | gaze estimator · MPIIFaceGaze | PoG error (cm): 4.21 -> 4.56 | Hurt |
| use BlazeGaze instead of AFF-Net | gaze estimator · GazeCapture | PoG error (cm): 2.30 -> 2.32 | Hurt |
| use BlazeGaze instead of AFF-Net | gaze estimator · EyeDiap | PoG error (cm): 9.25 -> 7.53 | Improved |
| use BlazeGaze instead of EFE | gaze estimator · MPIIFaceGaze | PoG error (cm): 3.89 -> 4.56 | Hurt |
| use BlazeGaze instead of iTracker | gaze estimator · MPIIFaceGaze | PoG error (cm): 7.67 -> 4.56 | Improved |
| use BlazeGaze instead of AFF-Net for model size | gaze estimator · Parameter count | parameters (M): 1.94 -> 0.16 | Improved |
| use WebEyeTrack instead of WebGazer (error growth over session) | browser eye-tracker · Eye of the Typer (initial to final Dot Test) | PoG error (cm): 11.62 -> 8.72 | Improved |
Closest papers by meaning
- Towards End-to-end Video-based Eye-Tracking (ECCV 2020 · similarity 0.89)
- Eye Tracking for Everyone (CVPR 2016 · similarity 0.88)
- Towards High Performance Low Complexity Calibration in Appearance Based Gaze Estimation (TPAMI 2022 · similarity 0.87)
- EV-Eye: Rethinking High-frequency Eye Tracking through the Lenses of Event Cameras (NeurIPS 2023 · similarity 0.86)
- CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model (AAAI 2024 · similarity 0.85)
- UVAGaze: Unsupervised 1-to-2 Views Adaptation for Gaze Estimation (AAAI 2024 · similarity 0.85)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
