Research map / Label-efficient and robust learning / Recognition and long-tail
Face Behind Makeup
Shuyang Wang, Yun Fu
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 locality-constrained low-rank dictionary learning instead of SVM for makeup detection | makeup detector · SMU Eye | detection accuracy (%): 80.90 -> 84.36 | Improved |
| use locality-constrained low-rank dictionary learning instead of SVM for makeup detection | makeup detector · YMU | detection accuracy (%): 87.08 -> 91.59 | Improved |
| apply LC-CDL makeup removal as preprocessing before face verification | SVM face verification · SMU | verification rate (%): 79.18 -> 87.73 | Improved |
| use LC-CDL instead of SCDL for makeup removal preprocessing | face verification · SMU | verification rate (%): 84.85 -> 87.73 | Improved |
| use LC-CDL instead of CDFL/SCDL for makeup removal | makeup removal · VMU and SMU | SSIM | Improved |
Closest papers by meaning
- Toward Tiny and High-quality Facial Makeup with Data Amplify Learning (ECCV 2024 · similarity 0.84)
- Makeup Prior Models for 3D Facial Makeup Estimation and Applications (CVPR 2024 · similarity 0.83)
- DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protection (CVPR 2024 · similarity 0.81)
- Content-Style Decoupling for Unsupervised Makeup Transfer without Generating Pseudo Ground Truth (CVPR 2024 · similarity 0.81)
- SHMT: Self-supervised Hierarchical Makeup Transfer via Latent Diffusion Models (NeurIPS 2024 · similarity 0.81)
- Disguise without Disruption: Utility-Preserving Face De-identification (AAAI 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.
