Research map / Architectures and efficiency / CNN design
Direct Shape Regression Networks for End-to-End Face Alignment
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 DSRN instead of DRA-TSR | Face alignment · AFLW | NME: 2.17 -> 1.86 | Helped |
| Use DSRN instead of DRA-TSR | Face alignment · 300W common subset | NME: 4.36 -> 4.12 | Helped |
| Use DSRN instead of DRA-TSR | Face alignment · 300W challenging subset | NME: 7.56 -> 9.68 | Hurt |
| Use DSRN instead of DRA-TSR | Face alignment · 300W full test set | NME: 4.99 -> 5.21 | Hurt |
| Use DSRN instead of CFSS | Face alignment · CelebA | NME: 3.95 -> 3.08 | Helped |
| Use DSRN instead of TCDCN | Face alignment · MAFL | NME: 7.95 -> 3.15 | Helped |
| Use DSRN instead of TSTN | Video-based face alignment · 300VW Test 1 | NME: 5.36 -> 5.33 | Helped |
| Use DSRN instead of TSTN | Video-based face alignment · 300VW Test 2 | NME: 4.51 -> 4.92 | Hurt |
| Use DSRN instead of TSTN | Video-based face alignment · 300VW Test 3 | NME: 12.84 -> 8.85 | Helped |
Closest papers by meaning
- Self-Reinforced Cascaded Regression for Face Alignment (AAAI 2018 · similarity 0.89)
- Mnemonic Descent Method: A Recurrent Process Applied for End-To-End Face Alignment (CVPR 2016 · similarity 0.89)
- Brute-Force Facial Landmark Analysis With a 140,000-Way Classifier (AAAI 2018 · similarity 0.88)
- Occlusion-Free Face Alignment: Deep Regression Networks Coupled With De-Corrupt AutoEncoders (CVPR 2016 · similarity 0.88)
- A Deep Regression Architecture With Two-Stage Re-Initialization for High Performance Facial Landmark Detection (CVPR 2017 · similarity 0.87)
- DSFNet: Dual Space Fusion Network for Occlusion-Robust 3D Dense Face Alignment (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.