Research map / 3D vision / Face and shape
Deep Cross-modality Adaptation via Semantics Preserving Adversarial Learning for Sketch-based 3D Shape Retrieval
Jiaxin Chen, Yi Fang
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 cross-modality transformation network trained with adversarial learning (CMDM-AL) (ablation) | sepIAML baseline · SHREC 2013 | mAP: 0.037 -> 0.795 | Improved |
| add cross-modality transformation network trained with adversarial learning (CMDM-AL) (ablation) | sepIAML baseline · SHREC 2014 | mAP: 0.028 -> 0.782 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2013 | mAP: 0.795 -> 0.813 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2014 | mAP: 0.782 -> 0.803 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2013 | NN: 0.762 -> 0.783 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2014 | NN: 0.745 -> 0.770 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2013 | E: 0.370 -> 0.376 | Improved |
| add semantics preserving term L_SeP (ablation) | DCA (CMDM-AL) · SHREC 2014 | E: 0.392 -> 0.398 | Improved |
| use DCA instead of LWBR | DCA (CMDM-AL+SeP) · SHREC 2013 | mAP: 0.752 -> 0.813 | Improved |
| use DCA instead of LWBR | DCA (CMDM-AL+SeP) · SHREC 2014 | mAP: 0.401 -> 0.803 | Improved |
| move from SHREC 2013 to harder SHREC 2014 (171 classes) | LWBR · SHREC 2013 vs 2014 | mAP: 0.752 -> 0.401 | Hurt |
| move from SHREC 2013 to harder SHREC 2014 (171 classes) | DCA (CMDM-AL+SeP) · SHREC 2013 vs 2014 | mAP: 0.813 -> 0.803 | No clear effect |
Closest papers by meaning
- Learning Cross-Domain Neural Networks for Sketch-Based 3D Shape Retrieval (AAAI 2016 · similarity 0.89)
- Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval (CVPR 2017 · similarity 0.88)
- Deep Correlated Metric Learning for Sketch-based 3D Shape Retrieval (AAAI 2017 · similarity 0.88)
- Domain Disentangled Generative Adversarial Network for Zero-Shot Sketch-Based 3D Shape Retrieval (AAAI 2022 · similarity 0.87)
- CrossOver: 3D Scene Cross-Modal Alignment (CVPR 2025 · similarity 0.85)
- TAMM: TriAdapter Multi-Modal Learning for 3D Shape Understanding (CVPR 2024 · 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.
