Research map / Graph learning / Graph algorithms and clustering
Kinematic Structure Correspondences via Hypergraph Matching
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 weight normalisation for the multi-order similarity terms (ablation) | Proposed F + RRWHM · Real kinematic structure dataset | accuracy: 88.23(±13.07) -> 92.99 (± 10.41) | Helped |
| combine structural topology, kinematic correlation, and combinatorial motion terms instead of relying on topology alone (ablation) | Proposed hypergraph matching · Synthetic kinematic structures, 2D and 3D | accuracy | Helped |
| use only the first-order structural topology term (ablation) | Proposed hypergraph matching · Synthetic symmetry tests, 2D and 3D | accuracy | Hurt |
| use only the second-order kinematic correlation term (ablation) | Proposed hypergraph matching · Synthetic kinematic structures, 2D and 3D | accuracy | Mixed |
| use only the third-order combinatorial motion term (ablation) | Proposed hypergraph matching · Synthetic kinematic structures, 2D and 3D | accuracy | Mixed |
| set the local degree-difference constraint θ to at least 3 (ablation) | Proposed topology similarity · Real kinematic structure dataset | accuracy | Hurt |
| set the global degree-difference constraint τ to 2 or lower (ablation) | Proposed topology similarity · Real kinematic structure dataset | accuracy | Hurt |
| increase the global degree-difference constraint τ above 3 (ablation) | Proposed topology similarity · Real kinematic structure dataset | accuracy | No clear effect |
Closest papers by meaning
- SAMoR: Motion Modelling for Articulated Objects of Any Skeleton and Topology (NeurIPS 2026 · similarity 0.85)
- Articulation in Prime: Primitive-Based Articulated Object Understanding from a Single Casual Video (NeurIPS 2026 · similarity 0.84)
- Hypergraph Learning for Unsupervised Graph Alignment via Optimal Transport (AAAI 2025 · similarity 0.84)
- Multi-Shape Matching with Cycle Consistency Basis via Functional Maps (AAAI 2025 · similarity 0.83)
- RUBIK: A Structured Benchmark for Image Matching across Geometric Challenges (CVPR 2025 · similarity 0.83)
- HIG: Hierarchical Interlacement Graph Approach to Scene Graph Generation in Video Understanding (CVPR 2024 · similarity 0.83)
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.