| Dual-Agent GANs for Photorealistic and Identity Preserving Profile Face Synthesis | | 97.60% | | | Dual-Agent GANs | 2017-12-01 |
| Probabilistic Face Embeddings | ✓ Link | 97.5% | 95.25 | | PFEfuse + match | 2019-04-21 |
| GhostVLAD for set-based face recognition | ✓ Link | 97.2% | | | SE-GV-4-g1 | 2018-10-23 |
| L2-constrained Softmax Loss for Discriminative Face Verification | ✓ Link | 97% | | | L2-constrained softmax loss | 2017-03-28 |
| VGGFace2: A dataset for recognising faces across pose and age | ✓ Link | 96.8% | 92.1 | 0.99 | VGGFace2_ft | 2017-10-23 |
| Inclusive normalization of face images to passport format | | 94.60% | | | StyleFNM | 2023-12-22 |
| Pose-Robust Face Recognition via Deep Residual Equivariant Mapping | ✓ Link | 94.40% | | | Deep Residual Equivariant Mapping | 2018-03-02 |
| Neural Aggregation Network for Video Face Recognition | | 94.10% | | | NAN | 2016-03-17 |
| Template Adaptation for Face Verification and Identification | | 93.90% | | | Template adaptation | 2016-03-12 |
| An All-In-One Convolutional Neural Network for Face Analysis | ✓ Link | 92.20% | | | All-in-one CNN | 2016-11-03 |
| FacePoseNet: Making a Case for Landmark-Free Face Alignment | ✓ Link | 90.1% | | | FPN | 2017-08-24 |
| Triplet Probabilistic Embedding for Face Verification and Clustering | ✓ Link | 90% | | | Triplet probabilistic embedding | 2016-04-19 |
| Do We Really Need to Collect Millions of Faces for Effective Face Recognition? | | 88.60% | | | Synthesis as data augmentation | 2016-03-23 |
| Unconstrained Face Verification using Deep CNN Features | | 83.80% | | | DCNN | 2015-08-07 |
| Face Recognition Using Deep Multi-Pose Representations | | 78.70% | | | Deep multi-pose representations | 2016-03-23 |
| Face Search at Scale: 80 Million Gallery | | 73.30% | | | Deep CNN + COTS matcher | 2015-07-26 |
| Semi-supervised Adversarial Learning to Generate Photorealistic Face Images of New Identities from 3D Morphable Model | ✓ Link | 53.507% | 18.768 | | VGG + GANFaces | 2018-04-10 |