Research map / Graph learning / Graph algorithms and clustering
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
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 |
|---|---|---|---|
| Jointly learn features and discover relations from a small initial graph | GSFA on Hopkins 155 · Hopkins 155 | clustering error: GSFA: 10.02% -> ReD-SFA: 2.19% | Helped |
| Initialize relations with k-NN instead of ε-ball (ablation) | ReD-SFA on Hopkins 155 · Hopkins 155 | clustering error | Hurt |
| Add the Boosting-like rounds to discover relations across clusters (ablation) | ReD-SFA · Hopkins 155 18th set | relation recall: 2.09% -> 67.31% | Helped |
| Use CNI prior to restrict relation discovery to coherent neighbors (ablation) | ReD-SFA on CUHK Crowd Dataset · CUHK Crowd Dataset | NMI | Helped |
| Use ReD-SFA rather than CF for crowd grouping | Crowd detection · CUHK Crowd Dataset | NMI | Helped |
| Use ReD-SFA rather than CT for crowd grouping | Crowd detection · CUHK Crowd Dataset | NMI: 0.48 vs 0.45 | Hurt |
| Use ReD-SFA rather than DTW-based spectral clustering | Time-series clustering · CC 6 classes | clustering error: 24.7% -> 22.8% | Helped |
| Use ReD-SFA rather than DTW-based spectral clustering | Time-series clustering · CC 5 classes | clustering error: 4% vs 6.6% | Hurt |
| Use ReD-SFA rather than subspace clustering methods | Time-series clustering · CC 2 classes | clustering error: LRR: 41.5%; SSC: 1.5%; ReD-SFA: 0% | Helped |
Closest papers by meaning
- Learned Trajectory Embedding for Subspace Clustering (CVPR 2024 · similarity 0.83)
- SC-FAGC: Size Constrained Fast Anchor-based Graph Clustering (ICML 2026 · similarity 0.82)
- MC-GTA: Metric-Constrained Model-Based Clustering using Goodness-of-fit Tests with Autocorrelations (ICML 2024 · similarity 0.82)
- Scalable Attributed-Graph Subspace Clustering (AAAI 2023 · similarity 0.82)
- Optimal Graph Clustering without Edge Density Signals (NeurIPS 2025 · similarity 0.81)
- Graph Minimum Factor Distance and Its Application to Large-Scale Graph Data Clustering (ICML 2025 · similarity 0.81)
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.