Research map / Learning theory and algorithms / Matrix and tensor methods
Low-Rank Laplacian-Uniform Mixed Model for Robust Face Recognition
Jiayu Dong, Huicheng Zheng, Lina Lian
Check 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 LR-LUM instead of the strongest listed baseline | Face recognition on LFW · LFW clean | accuracy (%): 81.4 -> 83.5 | Improved |
| Use LR-LUM instead of the strongest listed baseline | Face recognition on LFW · LFW 20% OC | accuracy (%): 74.7 -> 77.6 | Improved |
| Use LR-LUM instead of the strongest listed baseline | Face recognition on LFW · LFW 40% OC | accuracy (%): 45.7 -> 60.8 | Improved |
| Use LR-LUM rather than the compared methods | Face recognition with one training sample · EYB, clean images | accuracy | Improved |
| Use LR-LUM rather than the compared methods | Face recognition · AR real sunglasses disguise | accuracy: over 3%; over 5%; over 4% | Improved |
| Use LR-LUM rather than the compared methods | Face recognition · AR real scarf disguise | accuracy: over 10%; over 7%; over 5% | Improved |
| Use LR-LUM rather than the compared methods | Face recognition under mixed noise · AR with disguise and pixel corruption | accuracy | Improved |
| Use LR-LUM rather than the compared methods | Face recognition with multiple training samples · EYB block occlusion | accuracy | Mixed |
| Combine a robust nuclear-norm penalty for structured errors with LUM-weighted sparsity for random errors | LR-LUM · EYB, AR, and LFW under varied noise | accuracy | Improved |
Closest papers by meaning
- Enhanced Group Sparse Regularized Nonconvex Regression for Face Recognition (TPAMI 2020 · similarity 0.86)
- Nuclear Norm Based Matrix Regression with Applications to Face Recognition with Occlusion and Illumination Changes (TPAMI 2016 · similarity 0.85)
- Rethinking Robust Representation Learning under Fine-Grained Noisy Faces (ECCV 2022 · similarity 0.85)
- Noise-Robust Face Recognition via Non-target Similarity Distribution Guided Sample Selection (ECCV 2026 · similarity 0.85)
- Towards Certifiably Robust Face Recognition (ECCV 2024 · similarity 0.84)
- RepFace: Refining Closed-Set Noise with Progressive Label Correction for Face Recognition (AAAI 2025 · 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.
