Research map / Label-efficient and robust learning / Recognition and long-tail
Not Afraid of the Dark: NIR-VIS Face Recognition via Cross-Spectral Hallucination and Low-Rank Embedding
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 |
|---|---|---|---|
| Add hallucination and low-rank embedding | VGG-S · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 75.04 -> 95.72 | Helped |
| Add hallucination and low-rank embedding | VGG-face · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 72.54 -> 91.01 | Helped |
| Add hallucination and low-rank embedding | COTS · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 83.84 -> 96.41 | Helped |
| Add cross-spectral hallucination (ablation) | VGG-S · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 75.04 -> 80.65 | Helped |
| Add low-rank embedding (ablation) | VGG-S · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 75.04 -> 89.88 | Helped |
| Add cross-spectral hallucination (ablation) | VGG-face · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 72.54 -> 83.10 | Helped |
| Add low-rank embedding (ablation) | VGG-face · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 72.54 -> 82.26 | Helped |
| Add cross-spectral hallucination (ablation) | COTS · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 83.84 -> 93.02 | Helped |
| Add low-rank embedding (ablation) | COTS · CASIA NIR-VIS 2.0 (six-fold protocol) | rank-1 identification accuracy (%): 83.84 -> 91.83 | Helped |
| Add low-rank embedding | VGG-S · CASIA NIR-VIS 2.0 (10-fold protocol) | rank-1 identification accuracy (%): 57.53 ± 2.31 -> 82.07 ± 1.27 | Helped |
| Add low-rank embedding | VGG-face · CASIA NIR-VIS 2.0 (10-fold protocol) | rank-1 identification accuracy (%): 66.97 ± 1.62 -> 80.69 ± 1.02 | Helped |
| Add low-rank embedding | COTS · CASIA NIR-VIS 2.0 (10-fold protocol) | rank-1 identification accuracy (%): 79.29 ± 1.54 -> 89.59 ± 0.89 | Helped |
Closest papers by meaning
- Learning Invariant Deep Representation for NIR-VIS Face Recognition (AAAI 2017 · similarity 0.91)
- Physically-Based Face Rendering for NIR-VIS Face Recognition (NeurIPS 2022 · similarity 0.89)
- Hypergraph-Guided Disentangled Spectrum Transformer Networks for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.86)
- Multi-Energy Guided Image Translation with Stochastic Differential Equations for Near-Infrared Facial Expression Recognition (AAAI 2024 · similarity 0.85)
- Masked Face Recognition with Generative-to-Discriminative Representations (ICML 2024 · similarity 0.82)
- UIFace: Unleashing Inherent Model Capabilities to Enhance Intra-Class Diversity in Synthetic Face Recognition (ICLR 2025 · 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.