Research map / Architectures and efficiency / CNN design
Mixed Effects Neural Networks (MeNets) With Applications to Gaze Estimation
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 subject-specific mixed effects to the gaze estimator | ResNet gaze estimation · MPIIGaze | mean angular error: 6.04 ± 0.64 -> 4.90 ± 0.59 | Helped |
| add subject-specific mixed effects to the gaze estimator | gaze estimation · RealVideo | mean angular error: 6.98 ± 1.63 -> 6.72 ± 1.15 | Helped |
| add subject-specific mixed effects to the gaze estimator | gaze estimation · UT Multiview | mean angular error: 5.86 ± 1.10 -> 5.50 ± 1.03 | Helped |
| add subject-specific mixed effects to the gaze estimator | gaze estimation · Cross-dataset: UT Multiview train, MPIIGaze test | mean angular error: 9.84 ± 1.73 -> 9.51 ± 0.75 | Helped |
| use predicted random effects at test time (ablation) | MeNet with ResNet · MPIIGaze within-subject evaluation | mean angular error: 3.9 -> 2.66 | Helped |
| train with subject-specific random effects, even when not using them at test time (ablation) | ResNet gaze estimation · MPIIGaze within-subject evaluation | mean angular error: 3.9 -> 3.9 | Helped |
| add subject-specific mixed effects | ResNet gaze estimation · Across-subjects gaze estimation | mean angular error: 6.0 -> 4.34 | Helped |
| add MPIIGaze training data | MeNet gaze estimation · Real-video gaze estimation | mean angular error: 6.11° | Helped |
| use 200 calibration samples per subject | MeNet · MPIIGaze personalized gaze estimation | mean angular error: 3.8 degrees | Helped |
| model dataset-specific random effects | ResNet gaze estimation · Mixed-dataset evaluation | mean angular error: 16.36 degrees -> 11.2 degrees | Helped |
| add dataset-specific random effects (ablation) | MeNet · Mixed-dataset evaluation | mean angular error: 11.7 error -> 11.2 degrees | Helped |
Closest papers by meaning
- Test-Time Personalization with Meta Prompt for Gaze Estimation (AAAI 2024 · similarity 0.81)
- Gaze from Origin: Learning for Generalized Gaze Estimation by Embedding the Gaze Frontalization Process (AAAI 2024 · similarity 0.81)
- Enhancing 3D Gaze Estimation in the Wild using Weak Supervision with Gaze Following Labels (CVPR 2025 · similarity 0.81)
- From Feature to Gaze: A Generalizable Replacement of Linear Layer for Gaze Estimation (CVPR 2024 · similarity 0.81)
- Gaze Label Alignment: Alleviating Domain Shift for Gaze Estimation (AAAI 2025 · similarity 0.81)
- Sharingan: A Transformer Architecture for Multi-Person Gaze Following (CVPR 2024 · similarity 0.81)
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.