Research map / Label-efficient and robust learning / Recognition and long-tail
Temporal Non-Volume Preserving Approach to Facial Age-Progression and Age-Invariant Face Recognition
Chi Nhan Duong, Kha Gia Quach, Khoa Luu, Ngan Le, Marios Savvides
Read the paperCheck 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 |
|---|---|---|---|
| add TNVP age-progressed faces on top of the Center Loss face recognition model (no retraining) | Center Loss model · MegaFace Challenge 1 (FGNET probe, 1M distractors) | rank-1 identification accuracy: 38.79% -> 47.72% | Improved |
| match TNVP age-progressed face against older face instead of the original younger face | Center Loss model · FG-NET 1052 pairs (age gap over 10 years) | face verification matching performance: improvement of 30% on matching performance over the original pair (set A) | Improved |
| use IAAP or TRBM age-progressed faces instead of TNVP for verification | Center Loss model · FG-NET 1052 pairs (age gap over 10 years) | face verification matching performance: slightly increase the rates | No clear effect |
Closest papers by meaning
- Longitudinal Face Modeling via Temporal Deep Restricted Boltzmann Machines (CVPR 2016 · similarity 0.93)
- Towards Age-Invariant Face Recognition (TPAMI 2020 · similarity 0.92)
- Learning Continuous Face Age Progression: A Pyramid of GANs (TPAMI 2019 · similarity 0.91)
- Look across Elapse: Disentangled Representation Learning and Photorealistic Cross-Age Face Synthesis for Age-Invariant Face Recognition (AAAI 2019 · similarity 0.91)
- Recurrent Face Aging (CVPR 2016 · similarity 0.90)
- From Cradle to Cane: A Two-Pass Framework for High-Fidelity Lifespan Face Aging (NeurIPS 2025 · similarity 0.90)
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.
