Research map / 3D vision / Face and shape
4DFAB: A Large Scale 4D Database for Facial Expression Analysis and Biometric Applications
Shiyang Cheng, Irene Kotsia, Maja Pantic, Stefanos Zafeiriou
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 |
|---|---|---|---|
| Use the 4DFAB expression blendshape instead of FaceWarehouse features | Dynamic facial expression recognition · 4DFAB sessions S1–S4 | recognition rate (%): 71.02 -> 72.69; 68.03 -> 68.88; 68.35 -> 71.1; 66.81 -> 70.09 | Improved |
| Use identity-free 3DMM-exp deformation features instead of FaceWarehouse | Dynamic face recognition · 4DFAB: six basic expressions | recognition rate (%): 45.61 -> 66.22; 51.69 -> 66.55; 41.89 -> 62.84; 54.73 -> 67.23; 45.95 -> 59.46; 49.66 -> 61.15 | Improved |
| Use identity-free expression deformation rather than identity-and-expression 3DMM shape parameters | Dynamic face recognition · 4DFAB: six basic expressions | recognition rate (%): 66.22 -> 96.62; 66.55 -> 95.95; 62.84 -> 96.28; 67.23 -> 97.3; 59.46 -> 96.62; 61.15 -> 95.61 | Hurt |
| Use spontaneous smile rather than posed smile | Deformation-based face verification · 4DFAB smile verification | equal error rate (%): 22.6% -> 23.9% | No clear effect |
| Use disgust or happiness rather than the other posed expressions | Deformation-based face verification · 4DFAB posed expression verification | equal error rate (%): anger 18.2%; disgust 15.9%; fear 21.9%; happiness 17.5%; sadness 18.5%; surprise 18.8% | Mixed |
| Use the 3D mouth model parameters with an LSTM for word recognition | Dynamic speech recognition · 4DFAB sessions S1–S4 | recognition rate (%): 77.89; 75.17; 70.28; 68.47 | Improved |
Closest papers by meaning
- MimicME: A Large Scale Diverse 4D Database for Facial Expression Analysis (ECCV 2022 · similarity 0.91)
- Learning to Generate Customized Dynamic 3D Facial Expressions (ECCV 2020 · similarity 0.87)
- Face Anything: 4D Face Reconstruction from Any Image Sequence (ECCV 2026 · similarity 0.86)
- CAS(ME)3: A Third Generation Facial Spontaneous Micro-Expression Database with Depth Information and High Ecological Validity (TPAMI 2022 · similarity 0.86)
- A Comprehensive Database for Benchmarking Imaging Systems (TPAMI 2018 · similarity 0.86)
- Rethinking the Learning Paradigm for Dynamic Facial Expression Recognition (CVPR 2023 · 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.
