Research map / Label-efficient and robust learning / Recognition and long-tail
Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture
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 |
|---|---|---|---|
| Use the viewpoint-invariant hierarchical GlomFace architecture instead of the listed baselines | face alignment · Masked 300W Challenging | NME: 9.59 -> 8.81 | Helped |
| Use the viewpoint-invariant hierarchical GlomFace architecture instead of the listed baselines | face alignment · Masked 300W Full | NME: 6.46 -> 5.98 | Helped |
| Use GlomFace instead of SDL | face alignment · WFLW Occlusion | NME: 4.98 -> 5.14 | Hurt |
| Use GlomFace instead of ADNet | face alignment · 300W Challenging | NMEocular: 4.58 -> 4.87 | Hurt |
| Use GlomFace instead of ADNet | face alignment · 300W Full | NMEocular: 2.93 -> 3.20 | Hurt |
| Use GlomFace instead of ADNet | face alignment · COFW29 | NMEpupil: 4.68 -> 4.37 | Helped |
| Use GlomFace instead of SDL | face alignment · COFW68 | NMEocular: 4.22 -> 4.21 | Helped |
| Use GlomFace instead of hourglass-based boundary estimation | 68-landmark prediction · computational cost | FLOPS: 18.85G -> 13.48G | Helped |
Closest papers by meaning
- Robust Facial Landmark Detection via Occlusion-Adaptive Deep Networks (CVPR 2019 · similarity 0.88)
- Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders (CVPR 2016 · similarity 0.88)
- DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment (CVPR 2023 · similarity 0.86)
- Look at Boundary: A Boundary-Aware Face Alignment Algorithm (CVPR 2018 · similarity 0.86)
- LUVLi Face Alignment: Estimating Landmarks' Location, Uncertainty, and Visibility Likelihood (CVPR 2020 · similarity 0.85)
- TopoFR: A Closer Look at Topology Alignment on Face Recognition (NeurIPS 2024 · 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.