Research map / Graph learning / Graph algorithms and clustering
Robust Visual Place Recognition With Graph Kernels
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 |
|---|---|---|---|
| Use neighborhood-vector graph comparison instead of word co-occurrence comparison | visual place recognition · KITTI and sFly sequences | precision-recall | Mixed |
| Use neighborhood-vector graph comparison instead of FAB-MAP | visual place recognition · KITTI and sFly sequences | precision-recall | Helped |
| Use neighborhood-vector graph comparison | visual place recognition · Narrow-Wide camera sequences | precision-recall | Helped |
| Use neighborhood-vector graph comparison | visual place recognition · Wide-Narrow camera sequences | precision-recall | Mixed |
| Use a constant estimate for the non-matching observation likelihood rather than ground-truth-based per-query normalization (ablation) | nbhdGraph · KITTI 05 | precision-recall | Helped |
| Add covisibility neighborhood structure to visual-word labels | visual place recognition · repetitive and self-similar environments | place discrimination | Helped |
| Avoid explicit posterior normalization over the map by using a constant non-match likelihood (ablation) | nbhdGraph · place recognition across tested datasets | precision-recall | No clear effect |
Closest papers by meaning
- SuperVLAD: Compact and Robust Image Descriptors for Visual Place Recognition (NeurIPS 2024 · similarity 0.87)
- R-SCoRe: Revisiting Scene Coordinate Regression for Robust Large-Scale Visual Localization (CVPR 2025 · similarity 0.86)
- Towards Implicit Aggregation: Robust Image Representation for Place Recognition in the Transformer Era (NeurIPS 2025 · similarity 0.86)
- On the Estimation of Image-matching Uncertainty in Visual Place Recognition (CVPR 2024 · similarity 0.86)
- Focus on Local: Finding Reliable Discriminative Regions for Visual Place Recognition (AAAI 2025 · similarity 0.86)
- MutualVPR: A Mutual Learning Framework for Resolving Supervision Inconsistencies via Adaptive Clustering (NeurIPS 2025 · similarity 0.86)
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.