Research map / Video / Video segmentation and tracking
Joint Registration and Representation Learning for Unconstrained Face Identification
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 |
|---|---|---|---|
| jointly learn face registration and representation, then use Bayesian decision-level fusion of intact template media | VGG-16 face identification system · IJB-A | TPIR@Rank=1: 92.8 ± 1.0 -> 96.4 ± 0.8 | Helped |
| jointly learn face registration and representation, then use Bayesian decision-level fusion of intact template media | VGG-16 face identification system · IJB-A | TPIR@Rank=10: 98.6 ± 0.3 -> 100.0 ± 0.0 | Helped |
| jointly learn face registration and representation, then use Bayesian decision-level fusion of intact template media | VGG-16 face identification system · IJB-A | TPIR@FPIR=0.01: 77.4 ± 4.9 -> 88.6 ± 4.1 | Helped |
| jointly learn face registration and representation, then use Bayesian decision-level fusion of intact template media | VGG-16 face identification system · IJB-A | TPIR@FPIR=0.1: 88.2 ± 1.6 -> 96.0 ± 1.0 | Helped |
| use learned face features and the proposed template identification scheme | face identification · YTC | rank-1 identification rate | Helped |
| use learned face features and the proposed template identification scheme | face identification · COX | rank-1 identification rate | Helped |
| replace Bayesian decision fusion with a simple mean of decision values (ablation) | the proposed IJB-A template identification method · IJB-A | rank-1 identification rate: 94.2 ± 0.9 versus 96.4 ± 0.8 | Hurt |
| use the proposed learned features in place of the image-set methods' original features | existing image-set classification methods · YTC and COX | rank-1 identification rate | Helped |
Closest papers by meaning
- Disentangling 3D Pose in a Dendritic CNN for Unconstrained 2D Face Alignment (CVPR 2018 · similarity 0.84)
- Vec2Face: Scaling Face Dataset Generation with Loosely Constrained Vectors (ICLR 2025 · similarity 0.84)
- LAFS: Landmark-based Facial Self-supervised Learning for Face Recognition (CVPR 2024 · similarity 0.83)
- FaithfulFaces: Pose-Faithful Facial Identity Preservation for Text-to-Video Generation (NeurIPS 2026 · similarity 0.83)
- HyperFace: Generating Synthetic Face Recognition Datasets by Exploring Face Embedding Hypersphere (ICLR 2025 · similarity 0.83)
- GIF: Generative Inspiration for Face Recognition at Scale (CVPR 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.