Research map / 3D vision / Human pose estimation
Thin-Slicing for Pose: Learning to Understand Pose Without Explicit Pose Estimation
Check 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 |
|---|---|---|---|
| Add full-body and upper-body pose embeddings to VGG(img,box) features | VGG(img,box) · VOC2012 Action test | mean AP (%): 82.2 -> 84.2 | Helped |
| Add full-body and upper-body pose embeddings to VGG(img,box) features | VGG(img,box) · VOC2012 Action trainval | mean AP (%): 80.4 -> 82.5 | Helped |
| Add pose embedding features to VGG features | VGG · PPMI | classification accuracy (%): 88.5 -> 90.8 | Helped |
| Combine full-body and upper-body pose embeddings rather than using full-body alone (ablation) | PosE · VOC2012 Action trainval | mean AP (%): 48.9 -> 53.6 | Helped |
| Combine full-body and upper-body pose embeddings rather than using upper-body alone (ablation) | PosE · VOC2012 Action trainval | mean AP (%): 43.1 -> 53.6 | Helped |
| Use VGG(img) features instead of VGG(img,box) features alongside pose embeddings (ablation) | VGG + PosE(full,upper) · VOC2012 Action trainval | mean AP (%): 82.5 -> 79.2 | Hurt |
| Add full-body and upper-body pose embeddings to VGG(img) features | VGG(img) · VOC2012 Action trainval | mean AP (%): 73.8 -> 79.2 | Helped |
Closest papers by meaning
- Thin-Slicing Network: A Deep Structured Model for Pose Estimation in Videos (CVPR 2017 · similarity 0.90)
- Learning Temporal Pose Estimation from Sparsely-Labeled Videos (NeurIPS 2019 · similarity 0.87)
- Deep High-Resolution Representation Learning for Human Pose Estimation (CVPR 2019 · similarity 0.87)
- Dual Pose-invariant Embeddings: Learning Category and Object-specific Discriminative Representations for Recognition and Retrieval (CVPR 2024 · similarity 0.86)
- Optimizing Human Pose Estimation Through Focused Human and Joint Regions (AAAI 2025 · similarity 0.85)
- PoseBH: Prototypical Multi-Dataset Training Beyond Human Pose Estimation (CVPR 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.