Research map / Architectures and efficiency / CNN design
Eye Tracking for Everyone
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add train augmentation (ablation) | iTracker · GazeCapture mobile phone | error (cm): 2.04 -> 1.86 | Helped |
| Add test augmentation (ablation) | iTracker · GazeCapture mobile phone | error (cm): 2.04 -> 1.84 | Helped |
| Fine-tune the model for each device and orientation | iTracker · GazeCapture tablet | error (cm): 2.83 -> 2.53 | Helped |
| Add eye-image inputs (ablation) | iTracker · GazeCapture mobile phone | error (cm): 2.11 -> 2.04 | Helped |
| Add face-image input (ablation) | iTracker · GazeCapture mobile phone | error (cm): 2.15 -> 2.04 | Helped |
| Add face-grid input (ablation) | iTracker · GazeCapture tablet | error (cm): 3.90 -> 3.32 | Helped |
| Calibrate with 4 points | iTracker · GazeCapture tablet | error (cm): 2.83 -> 4.41 | Hurt |
| Calibrate with 13 points | iTracker · GazeCapture mobile phone | error (cm): 1.77 -> 1.56 | Helped |
| Calibrate with 13 points | iTracker* · GazeCapture tablet | error (cm): 2.53 -> 2.12 | Helped |
| Use iTracker features instead of AlexNet features | SVR gaze prediction on TabletGaze · TabletGaze | error (cm): 3.09 -> 2.58 | Helped |
| Increase the number of training subjects rather than samples per subject | iTracker · GazeCapture | error | Helped |
Closest papers by meaning
- EyeGraph: Modularity-aware Spatio Temporal Graph Clustering for Continuous Event-based Eye Tracking (NeurIPS 2024 · similarity 0.86)
- Toward Semantic Gaze Target Detection (NeurIPS 2024 · similarity 0.85)
- CLIP-Gaze: Towards General Gaze Estimation via Visual-Linguistic Model (AAAI 2024 · similarity 0.84)
- EyEar: Learning Audio Synchronized Human Gaze Trajectory Based on Physics-Informed Dynamics (AAAI 2025 · similarity 0.84)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.84)
- DiffEye: Diffusion-Based Continuous Eye-Tracking Data Generation Conditioned on Natural Images (NeurIPS 2025 · similarity 0.83)
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.