Research map / Learning theory and algorithms / Combinatorial and search optimization
Pairwise Matching Through Max-Weight Bipartite Belief Propagation
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 Hungarian-BP instead of DD | Feature matching · Chinese Character1 | accuracy: 0.9119 -> 0.9159 | Helped |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character2 | accuracy: 0.9140 -> 0.9188 | Helped |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character3 | accuracy: 0.8778 -> 0.8778 | No clear effect |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character4 | accuracy: 0.9961 -> 0.9961 | No clear effect |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character1 | time: 2.2333 -> 0.0948 | Helped |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character2 | time: 0.9873 -> 0.0914 | Helped |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character3 | time: 5.1402 -> 0.4438 | Helped |
| Use Hungarian-BP instead of DD | Feature matching · Chinese Character4 | time: 0.8655 -> 0.0625 | Helped |
| Use Hungarian-BP instead of FGM | Real-world car image matching · Car | accuracy: 0.9077 -> 0.9218 | Helped |
| Use Hungarian-BP instead of FGM | Real-world car image matching · Car | objective: 0.9991 -> 0.9952 | Hurt |
| Use Hungarian-BP instead of DD | Real-world motorbike image matching · Motor | accuracy: 0.9610 -> 0.9713 | Helped |
| Use Hungarian-BP instead of DD | Real-world motorbike image matching · Motor | objective: 0.9993 -> 1.0000 | Helped |
Closest papers by meaning
- Reinforced Feature Points: Optimizing Feature Detection and Description for a High-Level Task (CVPR 2020 · similarity 0.87)
- MATCHA: Towards Matching Anything (CVPR 2025 · similarity 0.86)
- Unifying Feature and Cost Aggregation with Transformers for Semantic and Visual Correspondence (ICLR 2024 · similarity 0.85)
- OmniGlue: Generalizable Feature Matching with Foundation Model Guidance (CVPR 2024 · similarity 0.85)
- The Balanced-Pairwise-Affinities Feature Transform (ICML 2024 · similarity 0.85)
- Reconstruct and Match: Out-of-Distribution Robustness via Topological Homogeneity (NeurIPS 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.