Research map / 3D vision / Human pose estimation
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge
Long Zhao, Xi Peng, Yuxiao Chen, Mubbasir Kapadia, Dimitris N. Metaxas
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 attention-map matching to final-activation matching (ablation) | CMKD on RHD with ResNet-18 · RHD evaluation | EPE (mm): 23.41 -> 22.19 | Improved |
| Add synthetic data augmentation (ablation) | CMKD on RHD with ResNet-18 and ACT+ATT · RHD evaluation | EPE (mm): 22.19 -> 20.89 | Improved |
| Use ResNet-50 instead of ResNet-18 (ablation) | CMKD on RHD with ACT+ATT and synthetic augmentation · RHD evaluation | EPE (mm): 20.89 -> 18.06 | Improved |
| Apply the source-learned ℓ2 regularizer | CMKG on STB · STB B1 evaluation | EPE (mm): 15.67 -> 8.18 | Improved |
| Apply the source-learned ℓ2 regularizer | CMKG on STB · STB B1 evaluation | AUC: 0.915 -> 0.987 | Improved |
| Use an ℓ2-regularized learned prior instead of an ℓ1-regularized learned prior (ablation) | CMKG on STB · STB B1 evaluation | EPE (mm): 8.86 -> 8.18 | Improved |
| Use the learned ℓ2 prior instead of default ℓ1 regularization (ablation) | CMKG on STB · STB B1 evaluation | EPE (mm): 11.41 -> 8.18 | Improved |
| Apply the learned regularizer | CMKG on FreiHAND G · FreiHAND G | EPE (mm): 12.37 -> 12.27 | No clear effect |
| Apply the learned regularizer | CMKG on FreiHAND H · FreiHAND H | EPE (mm): 14.49 -> 13.82 | Improved |
| Apply the learned regularizer | CMKG on FreiHAND S · FreiHAND S | EPE (mm): 15.80 -> 14.26 | Improved |
| Apply the learned regularizer | CMKG on FreiHAND A · FreiHAND A | EPE (mm): 16.18 -> 14.18 | Improved |
Closest papers by meaning
- Cross-Modal Deep Variational Hand Pose Estimation (CVPR 2018 · similarity 0.89)
- Learning Modality Knowledge Alignment for Cross-Modality Transfer (ICML 2024 · similarity 0.86)
- Keypoint Fusion for RGB-D Based 3D Hand Pose Estimation (AAAI 2024 · similarity 0.85)
- Cross-Constrained Progressive Inference for 3D Hand Pose Estimation with Dynamic Observer-Decision-Adjuster Networks (AAAI 2024 · similarity 0.85)
- C2KD: Bridging the Modality Gap for Cross-Modal Knowledge Distillation (CVPR 2024 · similarity 0.85)
- Align-KD: Distilling Cross-Modal Alignment Knowledge for Mobile Vision-Language Large Model Enhancement (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.
