Research map / Detection and segmentation / CNN features
Remote Photoplethysmography Correspondence Feature for 3D Mask Face Presentation Attack Detection
Si-Qi Liu, Xiangyuan Lan, Pong C. Yuen
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 noise-aware robust learning (global noise regularizer) (ablation) | CFrPPG · Replay Attack Dataset | HTER test (%): 10.2 -> 6.11 | Improved |
| add noise-aware robust learning (global noise regularizer) (ablation) | CFrPPG · Replay Attack Dataset | EER (%): 10.2 -> 6.17 | Improved |
| add noise-aware robust learning (global noise regularizer) (ablation) | CFrPPG · Replay Attack Dataset | FFR@FLR=0.01 (%): 29.9 -> 17.8 | Improved |
| use correspondence feature instead of max spectrum amplitude (CFrPPG-NAR vs LrPPG) | LrPPG · Replay Attack Dataset | HTER test (%): 19.3 -> 10.2 | Improved |
| use CFrPPG instead of LrPPG | LrPPG · HKBU-MARsV2 (intra-dataset) | HTER test (%): 8.67 -> 4.42 | Improved |
| use CFrPPG instead of LrPPG | LrPPG · Combined 3DMAD+HKBU-MARsV2 (intra-dataset) | HTER test (%): 9.16 -> 6.62 | Improved |
| use CFrPPG instead of LrPPG | LrPPG · 3DMAD (intra-dataset) | HTER test (%): 8.57 -> 6.82 | Improved |
| use CFrPPG instead of LrPPG | LrPPG · 3DMAD -> HKBU-MARsV2 (cross-dataset) | HTER (%): 16.8 -> 2.51 | Improved |
| use CFrPPG instead of LrPPG | LrPPG · HKBU-MARsV2 -> 3DMAD (cross-dataset) | HTER (%): 17.4 -> 2.55 | Improved |
| use rPPG-based CFrPPG instead of appearance-based MS-LBP | MS-LBP · HKBU-MARsV2 (intra-dataset) | HTER test (%): 24.0 -> 4.42 | Improved |
| use rPPG-based CFrPPG instead of appearance-based MS-LBP | MS-LBP · 3DMAD (intra-dataset) | HTER test (%): 4.22 -> 6.82 | Hurt |
| use CFrPPG instead of appearance-based CNN | CNN · 3DMAD -> HKBU-MARsV2 (cross-dataset) | HTER (%): 50.0 -> 2.51 | Improved |
Closest papers by meaning
- Learning Motion-Robust Remote Photoplethysmography through Arbitrary Resolution Videos (AAAI 2023 · similarity 0.90)
- Oulu Remote-photoplethysmography Physical Domain Attacks Database (ORPDAD) (ECCV 2024 · similarity 0.89)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.89)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.87)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.86)
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.86)
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.
