Research map / Video / Video segmentation and tracking
FPEM: Face Prior Enhanced Facial Attractiveness Prediction for Live Videos with Face Retouching
Hui Li, Xiaoyu Ren, Hongjiu Yu, Ying Chen, Kai Li, L Wang, Xiongkuo Min, Huiyu Duan, Guangtao Zhai, Xu Liu
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 |
|---|---|---|---|
| add FaceNet facial prior via cross-attention (ablation) | PAPM · LiveBeauty | SROCC: 0.9078 -> 0.9096 | Improved |
| add multi-scale feature fusion (ablation) | PAPM · LiveBeauty | SROCC: 0.9089 -> 0.9096 | Improved |
| add facial prior and multi-scale to Swin stem (ablation) | PAPM · LiveBeauty | SROCC: 0.9045 -> 0.9096 | Improved |
| add similarity regression strategy (ablation) | MAEM · LiveBeauty | SROCC: 0.8825 -> 0.9198 | Improved |
| fine-tune CLIP with FAP training instead of zero-shot (ablation) | MAEM · LiveBeauty | SROCC: 0.3838 -> 0.9198 | Improved |
| add L1 scoring loss (ablation) | MAEM · LiveBeauty | SROCC: 0.9161 -> 0.9198 | Improved |
| add ranking loss (ablation) | MAEM · LiveBeauty | SROCC: 0.9186 -> 0.9198 | Improved |
| add ranking loss (ablation) | MAEM · LiveBeauty | PLCC: 0.8911 -> 0.8631 | Hurt |
| add two-stage training (ablation) | FPEM · LiveBeauty | SROCC: 0.9189 -> 0.9243 | Improved |
| add selective fusion module (ablation) | FPEM · LiveBeauty | SROCC: 0.9197 -> 0.9243 | Improved |
| add SFM to fuse PAPM and MAEM (ablation) | FPEM · MEBeauty (cross-dataset) | SROCC: 0.6229 -> 0.6299 | Improved |
| train on LiveBeauty and test on other datasets, FPEM vs best baseline (ablation) | FPEM · SCUT-FBP5500 (cross-dataset) | SROCC: 0.599 vs 0.553 | Improved |
Closest papers by meaning
- A Survey of Deep Facial Attribute Analysis (IJCV 2020 · similarity 0.84)
- Pre-training Strategies and Datasets for Facial Representation Learning (ECCV 2022 · similarity 0.84)
- Hierarchical Spatio-Temporal Probabilistic Graphical Model with Multiple Feature Fusion for Binary Facial Attribute Classification in Real-World Face Videos (TPAMI 2016 · similarity 0.83)
- SLIP: Spoof-Aware One-Class Face Anti-Spoofing with Language Image Pretraining (AAAI 2025 · similarity 0.82)
- Makeup Prior Models for 3D Facial Makeup Estimation and Applications (CVPR 2024 · similarity 0.82)
- ACFun: Abstract-Concrete Fusion Facial Stylization (NeurIPS 2024 · similarity 0.82)
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.
