Research map / 3D vision / Face and shape
Deep Sketch-Shape Hashing With Segmented 3D Stochastic Viewing
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 |
|---|---|---|---|
| Replace aligned horizontal rendering with segmented stochastic view sampling (ablation) | DSSH · PART-SHREC’14 | mAP: 0.777 -> 0.806 | Helped |
| Use segmented stochastic views instead of horizontal views for randomly rotated shapes (ablation) | DSSH · PART-SHREC’14 | mAP: 0.749 -> 0.806 | Helped |
| Add the view attention network (ablation) | DSSH · PART-SHREC’14 | mAP: 0.799 -> 0.806 | Helped |
| Increase code length from 16 to 512 bits (ablation) | DSSH · SHREC’13 | mAP: 0.825 -> 0.858 | Helped |
| Increase code length from 16 to 512 bits (ablation) | DSSH · SHREC’14 | mAP: 0.773 -> 0.826 | Helped |
| Increase code length from 16 to 512 bits (ablation) | DSSH · PART-SHREC’14 | mAP: 0.759 -> 0.806 | Helped |
| Use DSSH binary codes instead of Semantic’s non-hashing representation | Sketch-based 3D shape retrieval · SHREC’13 | mAP: 0.843 -> 0.858 | Helped |
| Use DSSH binary codes instead of DCA’s representation | Sketch-based 3D shape retrieval · SHREC’14 | mAP: 0.803 -> 0.826 | Helped |
| Use DSSH binary codes instead of Semantic’s representation | Sketch-based 3D shape retrieval · PART-SHREC’14 | mAP: 0.676 -> 0.806 | Helped |
Closest papers by meaning
- Learning Barycentric Representations of 3D Shapes for Sketch-Based 3D Shape Retrieval (CVPR 2017 · similarity 0.90)
- Deep Correlated Metric Learning for Sketch-based 3D Shape Retrieval (AAAI 2017 · similarity 0.89)
- Deep Sketch Hashing: Fast Free-Hand Sketch-Based Image Retrieval (CVPR 2017 · similarity 0.89)
- SketchMate: Deep Hashing for Million-Scale Human Sketch Retrieval (CVPR 2018 · similarity 0.87)
- How to Handle Sketch-Abstraction in Sketch-Based Image Retrieval? (CVPR 2024 · similarity 0.85)
- OnlineAnySeg: Online Zero-Shot 3D Segmentation by Visual Foundation Model Guided 2D Mask Merging (CVPR 2025 · similarity 0.84)
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.