Research map / 3D vision / Human pose estimation
Fashion Landmark Detection in the Wild
Ziwei Liu, Sijie Yan, Ping Luo, Xiaogang Wang, Xiaoou Tang
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 visibility prediction (ablation) | DFA stage-1 · FLD | NE average: .153 -> .102 | Improved |
| add soft pseudo-labels (T=20) vs none (ablation) | DFA stage-1 · FLD | NE average: .102 -> .084 | Improved |
| use soft (T=20) instead of hard (T=1) pseudo-labels (ablation) | DFA stage-1 · FLD | NE average: .091 -> .084 | Improved |
| add offset pseudo-labels (ablation) | DFA stage-2 · FLD | NE average: .078 -> .074 | Improved |
| use offset instead of absolute-position pseudo-labels (ablation) | DFA stage-2 · FLD | NE average: .076 -> .074 | Improved |
| add auto-routing vs plain two-branch averaging (ablation) | DFA stage-3 · FLD | NE average: .072 -> .070 | Improved |
| add two-branch averaging (ablation) | DFA stage-3 · FLD | NE average: .073 -> .072 | No clear effect |
| add contextual-offset pseudo-labels (ablation) | DFA stage-3 · FLD | NE average: .070 -> .068 | Improved |
| add auto-routing (ablation) | DFA stage-3 · FLD L. Zoom-in subset | NE: .148 -> .146 | Improved |
| add pseudo-labels in stage 1 (ablation) | DFA stage-1 · FLD L. Zoom-in subset | NE: .193 -> .156 | Improved |
| add pseudo-labels to IDPR (ablation) | IDPR · LSP | mean strict PCP: 75.0 -> 77.0 | Improved |
| add auto-routing to IDPR with pseudo-labels (ablation) | IDPR · LSP | mean strict PCP: 77.0 -> 78.6 | Improved |
Closest papers by meaning
- Attentive Fashion Grammar Network for Fashion Landmark Detection and Clothing Category Classification (CVPR 2018 · similarity 0.91)
- Layout-Graph Reasoning for Fashion Landmark Detection (CVPR 2019 · similarity 0.91)
- DeepFashion2: A Versatile Benchmark for Detection, Pose Estimation, Segmentation and Re-Identification of Clothing Images (CVPR 2019 · similarity 0.88)
- Texture and Shape Biased Two-Stream Networks for Clothing Classification and Attribute Recognition (CVPR 2020 · similarity 0.88)
- TailorNet: Predicting Clothing in 3D as a Function of Human Pose, Shape and Garment Style (CVPR 2020 · similarity 0.88)
- FashionTailor: Controllable Clothing Editing for Human Images with Appearance Preserving (AAAI 2025 · similarity 0.85)
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.
