Research map / Detection and segmentation / CNN features
Face Detection with End-to-End Integration of a ConvNet and a 3D Model
Yunzhu Li, Benyuan Sun, Tianfu Wu, Yizhou Wang
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 3D mean face model transformation to generate proposals instead of anchor boxes | Ours-Conv3D · FDDB (proposals) | recall (%): 93.67% recall with 34.4 proposals per image | Improved |
| use 3D model based part structure (continuous scores) instead of other published detectors | Ours-Conv3D · FDDB continuous scores | recall at 2000 false positives | Improved |
| compare against DP2MFD on discrete scores | Ours-Conv3D · FDDB discrete scores | recall at 2000 false positives | No clear effect |
| faceness score as sum of log probabilities of 10 key-points (double counting for low-resolution faces) (ablation) | Ours-Conv3D · FDDB | detection performance | Hurt |
| ignore invisible facial parts in faceness score (ablation) | Ours-Conv3D · FDDB and AFW | detection performance | Hurt |
Closest papers by meaning
- Hybrid Deep Learning for Face Verification (TPAMI 2016 · similarity 0.86)
- Unconstrained Still/Video-Based Face Verification with Deep Convolutional Neural Networks (IJCV 2017 · similarity 0.86)
- Learning From Millions of 3D Scans for Large-Scale 3D Face Recognition (CVPR 2018 · similarity 0.85)
- RefineFace: Refinement Neural Network for High Performance Face Detection (TPAMI 2020 · similarity 0.85)
- Supervised Transformer Network for Efficient Face Detection (ECCV 2016 · similarity 0.85)
- BFBox: Searching Face-Appropriate Backbone and Feature Pyramid Network for Face Detector (CVPR 2020 · 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.
