Research map / Vision-language and multimodal / Human and embodied modeling
SceneSketcher: Fine-Grained Image Retrieval with Scene Sketches
Fang Liu, Changqing Zou, Xiaoming Deng, Ran Zuo, Yu-Kun Lai, Cuixia Ma, Yong-Jin Liu, Hongan Wang
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 category labels to visual node features (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 24.29 -> 30.48 | Improved |
| add visual features to category label nodes (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 29.52 -> 30.48 | Improved |
| add spatial position information to node features (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 30.48 -> 31.91 | Improved |
| add spatial position information to node features (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@10 (%): 83.81 -> 86.19 | Improved |
| add category-wise IoU to graph triplet loss (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 13.33 -> 31.91 | Improved |
| add category-wise IoU to graph triplet loss (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@10 (%): 47.62 -> 86.19 | Improved |
| add the scene sketch graph to category-wise IoU ranking (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 28.10 -> 31.91 | Improved |
| use category-wise IoU instead of IoUcategory (no graph) (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 23.82 -> 28.10 | Improved |
| use category-wise IoU instead of global IoU (no graph) (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 5.24 -> 28.10 | Improved |
| use category-wise IoU instead of IoUcategory with graph features (ablation) | SceneSketcher · Our scene sketch database (210 test) | Recall@1 (%): 24.76 -> 31.91 | Improved |
| add category-wise IoU and full node features on extended database (ablation) | SceneSketcher · Extended database (5210 test) | Recall@1 (%): 2.38 -> 12.38 | Improved |
| add spatial position information on extended database (ablation) | SceneSketcher · Extended database (5210 test) | Recall@1 (%): 11.43 -> 12.38 | Improved |
Closest papers by meaning
- Scene-Level Sketch-Based Image Retrieval with Minimal Pairwise Supervision (AAAI 2023 · similarity 0.94)
- Generalising Fine-Grained Sketch-Based Image Retrieval (CVPR 2019 · similarity 0.91)
- Sketch Me That Shoe (CVPR 2016 · similarity 0.90)
- You'll Never Walk Alone: A Sketch and Text Duet for Fine-Grained Image Retrieval (CVPR 2024 · similarity 0.89)
- ARNet: Self-Supervised FG-SBIR with Unified Sample Feature Alignment and Multi-Scale Token Recycling (AAAI 2025 · similarity 0.88)
- Composite Sketch+Text Queries for Retrieving Objects with Elusive Names and Complex Interactions (AAAI 2024 · similarity 0.87)
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.
