Datasets › IJB-B
IJB-B (IARPA Janus Benchmark-B)
The IJB-B dataset is a template-based face dataset that contains 1845 subjects with 11,754 images, 55,025 frames and 7,011 videos where a template consists of a varying number of still images and video frames from different sources. These images and videos are collected from the Internet and are totally unconstrained, with large variations in pose, illumination, image quality etc. In addition, the dataset comes with protocols for 1-to-1 template-based face verification, 1-to-N template-based open-set face identification, and 1-to-N open-set video face identification.
Source: An Automatic System for Unconstrained Video-Based Face Recognition Image Source: https://www.vislab.ucr.edu/Biometrics2017/program_slides/Noblis_CVPRW_IJBB.pdf
Benchmarks archive 2025-07-28
All 5 leaderboards whose dataset resolves to this page shown (sort by any header). "First row" is the archive's own first row at snapshot, in the archive's row order; nothing here re-ranks and metric direction is not asserted.
| First row (archive order) | Paper | Code | ||||
|---|---|---|---|---|---|---|
| Face Verification | IJB-B | QMagFace TAR @ FAR=0.01 97.72% | QMagFace: Simple and Accurate Quality-Aware Face Recognition | pterhoer/QMagFace | 12 | Compare |
| Face Recognition | IJB-B | ArcFace+CSFM Rank-1 0.9496 | Controllable and Guided Face Synthesis for Unconstrained... | Faceplugin-ltd/FaceRecognition-Android +2 | 4 | Compare |
| Lightweight Face Recognition | IJB-B | EdgeFace - S (g=0.5) TAR @ FAR=0.01 0.9358 | EdgeFace: Efficient Face Recognition Model for Edge Devices | otroshi/edgeface +2 | 3 | Compare |
| Face Identification | IJB-B | FPN Accuracy 91.1% | FacePoseNet: Making a Case for Landmark-Free Face Alignment | fengju514/Expression-Net +4 | 1 | Compare |
| Quantization | IJB-B | TAR @ FAR=1e-4 95.13 | QuantFace: Towards Lightweight Face Recognition by... | fdbtrs/QuantFace | 1 | Compare |
Papers archive 2025-07-28
13 shown of 13 papers with a leaderboard row on this dataset's benchmarks, newest first. The archive's own "papers using this dataset" list was never published, so this is the benchmark-backed subset; the archive's count for this dataset is 163. The Syntology column is from Syntology's graph (read 2026-09-24), stated per sample; it is not part of any archive number.
Dataset loaders archive 2025-07-28
No loader listed in the archive.
Tasks archive 2025-07-28
License archive 2025-07-28
Modalities archive 2025-07-28
Languages archive 2025-07-28
No language tagged.
Variants archive 2025-07-28
- IJB-B
1 variant name, as the archive lists them.
Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections