Research map / Label-efficient and robust learning / Semi-supervised learning
Gait Recognition via Semi-supervised Disentangled Representation Learning to Identity and Covariate Features
Xiang Li, Yasushi Makihara, Chi Xu, Yasushi Yagi, Mingwu Ren
Check 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 reconstruction loss Lreconst to the contrastive-loss training objective (ablation) | ICDNet verification · OU-LP-Bag cooperative | EER: 0.98 -> 0.89 | Improved |
| Add reconstruction loss Lreconst to the triplet-loss training objective (ablation) | ICDNet identification · OU-LP-Bag cooperative | Rank-1: 84.02 -> 86.37 | Improved |
| Add identity similarity loss Lsim to triplet and reconstruction losses (ablation) | ICDNet identification · OU-LP-Bag cooperative | Rank-1: 86.37 -> 87.04 | Improved |
| Fine-tune an OU-LP-Bag-pretrained model rather than train from scratch | ICDNet · CASIA-B protocol 1 | Rank-1 mean: 85.0 -> 97.7 | Improved |
Closest papers by meaning
- On Learning Disentangled Representations for Gait Recognition (TPAMI 2020 · similarity 0.91)
- Gait Recognition via Disentangled Representation Learning (CVPR 2019 · similarity 0.91)
- Cross-Covariate Gait Recognition: A Benchmark (AAAI 2024 · similarity 0.87)
- BiggerGait: Unlocking Gait Recognition with Layer-wise Representations from Large Vision Models (NeurIPS 2025 · similarity 0.86)
- Exploring More from Multiple Gait Modalities for Human Identification (AAAI 2025 · similarity 0.86)
- RA-GAR: A Richly Annotated Benchmark for Gait Attribute Recognition (AAAI 2025 · 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.
