Research map / Graph learning / Knowledge and temporal graphs
Long-Term Loop Closure Detection through Visual-Spatial Information Preserving Multi-Order Graph Matching
Peng Gao, Hao Zhang
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 |
|---|---|---|---|
| address landmark scale changes with size-based weights (ablation) | multi-order graph matching · CMU-VL | area under precision-recall curve: 0.5661 -> 0.7452 | Improved |
| add visual appearance cues to second and third-order spatial cues (ablation) | multi-order graph matching · CMU-VL | area under precision-recall curve: 0.7448 -> 0.7452 | Improved |
| add spatial relationships to visual appearance (ablation) | multi-order graph matching · CMU-VL | area under precision-recall curve: 0.5350 -> 0.7452 | Improved |
| add third-order spatial cues to second-order (ablation) | multi-order graph matching · CMU-VL | area under precision-recall curve: 0.7179 -> 0.7448 | Improved |
| use graph matching with visual-spatial info instead of vector matching (HALI) | landmark-based place matching · St Lucia | area under precision-recall curve: 0.5206 -> 0.7207 | Improved |
| use graph matching with spatial plus visual info instead of spatial-only BCAGM | graph matching · CMU-VL | area under precision-recall curve: 0.4878 -> 0.7452 | Improved |
Closest papers by meaning
- Learning Integrated Holism-Landmark Representations for Long-Term Loop Closure Detection (AAAI 2018 · similarity 0.90)
- Visual Place Recognition via Robust ℓ2-Norm Distance Based Holism and Landmark Integration (AAAI 2019 · similarity 0.85)
- Change-Robust Online Topological Memory for Long-Term Relocalization and Semantic Navigation (NeurIPS 2026 · similarity 0.85)
- Semantic Match Consistency for Long-Term Visual Localization (ECCV 2018 · similarity 0.84)
- STRNet: Visual Navigation with Spatio-Temporal Representation through Dynamic Graph Aggregation (CVPR 2026 · similarity 0.84)
- Loopy-SLAM: Dense Neural SLAM with Loop Closures (CVPR 2024 · 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.
