Research map / Video / Video segmentation and tracking
Modelling of Bi-Directional Spatio-Temporal Dependence and Users’ Dynamic Preferences for Missing POI Check-In Identification
Dongbo Xi, Fuzhen Zhuang, Yanchi Liu, Jingjing Gu, Hui Xiong, Qing He
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 |
|---|---|---|---|
| add backward sequence to forward-only model (Bi vs F-STDDP) (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@1: 0.1586 -> 0.1743 | Improved |
| add forward sequence to backward-only model (ablation) | Bi-STDDP · NYC missing POI check-in identification | MAP: 0.2405 -> 0.2533 | Improved |
| add backward sequence to forward-only model (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@10: 0.4050 -> 0.4176 | Improved |
| add target temporal pattern for dynamic preferences (Bi-B vs Bi-A) (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@1: 0.1435 -> 0.1650 | Improved |
| add spatio-temporal dependence relationships (Bi-STDDP vs Bi-B) (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@1: 0.1650 -> 0.1743 | Improved |
| add spatio-temporal dependence relationships (ablation) | Bi-STDDP · NYC missing POI check-in identification | MAP: 0.2457 -> 0.2533 | Improved |
| forward-only STDDP vs best baseline ST-RNN | Bi-STDDP · NYC missing POI check-in identification | MAP: 0.2250 -> 0.2405 | Improved |
| Bi-STDDP vs best baseline ST-RNN on NYC | Bi-STDDP · NYC missing POI check-in identification | Recall@1: 0.1302 -> 0.1743 | Improved |
| Bi-STDDP vs ST-RNN on TKY | Bi-STDDP · TKY missing POI check-in identification | MAP: 0.2543 -> 0.2991 | Improved |
| Bi-STDDP vs ST-RNN on Gowalla | Bi-STDDP · Gowalla missing POI check-in identification | MAP: 0.1189 -> 0.1653 | Improved |
| increase embedding dimension beyond 16 (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@K | No clear effect |
| increase hidden units beyond 32 (ablation) | Bi-STDDP · NYC missing POI check-in identification | Recall@K | No clear effect |
Closest papers by meaning
- GeoMamba: Towards Multi-granular POI Recommendation with Geographical State Space Model (AAAI 2025 · similarity 0.89)
- Integrating Personalized Spatio-Temporal Clustering for Next POI Recommendation (AAAI 2025 · similarity 0.87)
- Learning Time Slot Preferences via Mobility Tree for Next POI Recommendation (AAAI 2024 · similarity 0.86)
- Taming the Long Tail in Human Mobility Prediction (NeurIPS 2024 · similarity 0.86)
- SPOT-Trip: Dual-Preference Driven Out-of-Town Trip Recommendation (NeurIPS 2025 · similarity 0.86)
- TAU: Trajectory Data Augmentation with Uncertainty for Next POI Recommendation (AAAI 2024 · similarity 0.85)
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.
