Research map / Video / Video segmentation and tracking
Learning Discriminative Aggregation Network for Video-Based Face Recognition
Yongming Rao, Ji Lin, Jiwen Lu, Jie Zhou
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 DAN aggregation before feature extraction | CNN dense features · YTF | verification accuracy (%): 93.16 -> 94.28 | Improved |
| add DAN aggregation before feature extraction | CNN dense features · PaSC control | verification rate at FAR 0.01 (%): 90.78 -> 92.06 | Improved |
| add DAN aggregation before feature extraction | CNN dense features · PaSC handheld | verification rate at FAR 0.01 (%): 78.67 -> 80.33 | Improved |
| add DAN aggregation before feature extraction | CNN dense features · YTC | classification accuracy (%): 96.79 -> 97.32 | Improved |
| use DAN aggregation instead of random sampling of 10 frames (ablation) | Random + CNN · YTF | verification accuracy (%): 92.80 -> 94.28 | Improved |
| use DAN aggregation instead of hierarchical pooling into 10 frames (ablation) | Hierarchical Pooling · YTF | verification accuracy (%): 93.15 -> 94.28 | Improved |
| use DAN aggregation instead of random sampling (ablation) | Random + CNN · PaSC control | verification rate at FAR 0.01 (%): 89.12 -> 92.06 | Improved |
| use DAN aggregation instead of hierarchical pooling (ablation) | Hierarchical Pooling · PaSC handheld | verification rate at FAR 0.01 (%): 78.23 -> 80.33 | Improved |
| use DAN aggregation instead of random sampling (ablation) | Random + CNN · YTC | classification accuracy (%): 96.63 -> 97.32 | Improved |
| aggregate 200 frames to 10 images with DAN instead of dense extraction | CNN dense features · YTF | runtime (ms): 819.7 -> 126.1 | Improved |
Closest papers by meaning
- Neural Aggregation Network for Video Face Recognition (CVPR 2017 · similarity 0.91)
- Learning Discriminative Aggregation Network for Video-Based Face Recognition and Person Re-identification (IJCV 2018 · similarity 0.88)
- Unsupervised Domain Adaptation for Face Recognition in Unlabeled Videos (ICCV 2017 · similarity 0.87)
- FaceCoresetNet: Differentiable Coresets for Face Set Recognition (AAAI 2024 · similarity 0.84)
- Video Based Face Recognition by Using Discriminatively Learned Convex Models (IJCV 2020 · similarity 0.84)
- Deep Layer Aggregation (CVPR 2018 · 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.
