Research map / Learning theory and algorithms / Matrix and tensor methods
A Functional Regression Approach to Facial Landmark Tracking
Enrique Sánchez, Georgios Tzimiropoulos, Brais Martínez, Fernando De la Torre, Michel Valstar
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 incremental learning (iCCR) to CCR (ablation) | CCR · 300-VW Category 3 | AUC: 0.4410 -> 0.5141 | Improved |
| add incremental learning (iCCR) to CCR (ablation) | CCR · 300-VW Category 1 | AUC: 0.5657 -> 0.5978 | Improved |
| add incremental learning (iCCR) to CCR (ablation) | CCR · 300-VW Category 2 | AUC: 0.5539 -> 0.5918 | Improved |
| add incremental learning to CCR (ablation) | CCR · 300-VW | reinitialised frames (%): 0.51 -> 0.34 | Improved |
| use CCR instead of sampling-based SDM | SDM · 300-VW Category 3 | AUC: 0.4380 -> 0.4410 | No clear effect |
| use CCR instead of sampling-based SDM | SDM · 300-VW Category 1 | AUC: 0.5617 -> 0.5657 | No clear effect |
| model correlated shape variables with full covariance (cor-CCR vs uncor-CCR) (ablation) | CCR · 300-VW hardest subset, 49 points | cumulative error distribution | Improved |
| vary forgetting factor of iCCR (ablation) | iCCR · 300-VW Category 3 | CED / AUC | No clear effect |
| use iCCR instead of Yang et al. | Yang et al. · 300-VW Category 3 | AUC: 0.4996 -> 0.5141 | Improved |
| use iCCR instead of Xiao et al. | Xiao et al. · 300-VW Category 2 | AUC: 0.6093 -> 0.5918 | Hurt |
Closest papers by meaning
- Cascaded Continuous Regression for Real-Time Incremental Face Tracking (ECCV 2016 · similarity 0.95)
- Synergy Between Face Alignment and Tracking via Discriminative Global Consensus Optimization (ICCV 2017 · similarity 0.88)
- Dynamic Attention-Controlled Cascaded Shape Regression Exploiting Training Data Augmentation and Fuzzy-Set Sample Weighting (CVPR 2017 · similarity 0.88)
- Self-Reinforced Cascaded Regression for Face Alignment (AAAI 2018 · similarity 0.88)
- Face Landmark Fitting via Optimized Part Mixtures and Cascaded Deformable Model (TPAMI 2016 · similarity 0.87)
- Generalizable Face Landmarking Guided by Conditional Face Warping (CVPR 2024 · similarity 0.84)
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.
