Research map / Label-efficient and robust learning / Recognition and long-tail
Survey on the Analysis and Modeling of Visual Kinship: A Decade in the Making
Joseph P. Robinson, Ming Shao, Yun Fu
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 top challenge entry vuvko instead of ArcFace baseline | kin verification · RFIW 2020 T1 (FIW) | average accuracy: 0.64 -> 0.78 | Improved |
| use top challenge entry ustc-nelslip instead of Sphereface baseline | tri-subject verification · RFIW 2020 T2 (FIW) | average accuracy: 0.68 -> 0.79 | Improved |
| use top entry vuvko instead of Sphereface baseline | search and retrieval · RFIW 2020 T3 (FIW) | mAP: 0.02 -> 0.18 | Improved |
| use top entry vuvko instead of Sphereface baseline | search and retrieval · RFIW 2020 T3 (FIW) | Rank@5: 0.10 -> 0.60 | Improved |
| deep KVRL-fcDBN instead of metric learning MSIDA+WCCN | kinship verification · KinWild I | average accuracy: 87.7 -> 96.1 | Improved |
| deep KVRL-fcDBN instead of metric learning MSIDA+WCCN | kinship verification · KinWild II | average accuracy: 87.0 -> 96.2 | Improved |
| use BCE loss instead of Focal loss (ablation) | ResNet50/SENet50 kin verification · RFIW 2020 Track I | accuracy | Improved |
| use SENet backbone instead of ResNet50 (ablation) | kin verification entry · RFIW 2020 validation vs test | accuracy | Mixed |
| use Euclidean distance instead of cosine similarity | kin verification entry · RFIW 2020 | accuracy | No clear effect |
Closest papers by meaning
- Visual Kinship Recognition of Families in the Wild (TPAMI 2018 · similarity 0.91)
- Facial Kinship Verification: A Comprehensive Review and Outlook (IJCV 2022 · similarity 0.90)
- Meta-Mining Discriminative Samples for Kinship Verification (CVPR 2021 · similarity 0.88)
- SapiensID: Foundation for Human Recognition (CVPR 2025 · similarity 0.82)
- Learning from Synchronization: Self-Supervised Uncalibrated Multi-View Person Association in Challenging Scenes (CVPR 2025 · similarity 0.82)
- PairDETR : Joint Detection and Association of Human Bodies and Faces (CVPR 2024 · similarity 0.81)
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.
