Research map / Video / Video segmentation and tracking
Region-Based Message Exploration over Spatio-Temporal Data Streams
Lisi Chen, Shuo Shang
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 |
|---|---|---|---|
| use learned triplet network relevancy metric (TN) instead of SVSM and SP | region relevancy · FS and TT, varying noise kappa | 10-RR and 20-RR | Improved |
| increase noise kappa from 0.05 to 0.25 (ablation) | TN · FS and TT | 10-RR: reduced by 10% | Hurt |
| increase noise kappa from 0.05 to 0.25 (ablation) | SP · FS and TT | 10-RR: reduced by 22% | Hurt |
| increase noise kappa from 0.05 to 0.25 (ablation) | SVSM · FS and TT | 10-RR: reduced by 53% | Hurt |
| increase location noise upsilon from 10km to 50km (ablation) | TN · FS and TT | 10-RR and 20-RR | Hurt |
| increase location noise upsilon from 10km to 50km (ablation) | SVSM · FS and TT | 10-RR and 20-RR | No clear effect |
| use greedy region summarization GRS instead of Max-Sum, Max-Min and Rand | region summarization · FS and TT | information coverage score | Improved |
| use GRS instead of Max-Min and Max-Sum | region summarization · FS and TT | runtime | Improved |
| increase number of representative messages (ablation) | summarization methods · FS and TT | information coverage score | No clear effect |
Closest papers by meaning
- College Towns, Vacation Spots, and Tech Hubs: Using Geo-Social Media to Model and Compare Locations (AAAI 2016 · similarity 0.85)
- Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation (AAAI 2025 · similarity 0.81)
- GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model (AAAI 2025 · similarity 0.81)
- GeoLLM: Extracting Geospatial Knowledge from Large Language Models (ICLR 2024 · similarity 0.80)
- Robust Spatio-Temporal Centralized Interaction for OOD Learning (ICML 2025 · similarity 0.79)
- Towards Effective, Efficient and Unsupervised Social Event Detection in the Hyperbolic Space (AAAI 2025 · similarity 0.79)
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.
