Research map / Graph learning / Knowledge and temporal graphs
Where Will Players Move Next? Dynamic Graphs and Hierarchical Fusion for Movement Forecasting in Badminton
Read the paperCheck 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 |
|---|---|---|---|
| Add dynamic GCN in place of static GCN (ablation) | DyMF · Badminton singles, τ=8 | MSE location: 1.1838 -> 1.0827 | Helped |
| Add player-player fusion (ablation) | DyMF · Badminton singles, τ=8 | MSE location: 1.1346 -> 1.0827 | Helped |
| Add dynamic weights for rally interactions (ablation) | DyMF · Badminton singles, τ=8 | MSE location: 1.1375 -> 1.0827 | Helped |
| Add dynamic weights for player-player styles (ablation) | DyMF · Badminton singles, τ=8 | MSE location: 1.1270 -> 1.0827 | Helped |
| Add dynamic GCN in place of static GCN (ablation) | DyMF · Badminton singles, τ=8 | CE shot type: 1.9650 -> 1.9570 | Helped |
| Add player-player fusion (ablation) | DyMF · Badminton singles, τ=8 | CE shot type: 1.9607 -> 1.9570 | Helped |
| Add dynamic weights for rally interactions (ablation) | DyMF · Badminton singles, τ=8 | CE shot type: 1.9883 -> 1.9570 | Helped |
| Add dynamic weights for player-player styles (ablation) | DyMF · Badminton singles, τ=8 | CE shot type: 1.9674 -> 1.9570 | Helped |
| Use a PM graph instead of a complete graph (ablation) | GCN · Badminton singles, τ=8 | MSE location: 3.2579 -> 1.2676 | Helped |
| Use a PM graph instead of a complete graph (ablation) | R-GCN · Badminton singles, τ=8 | MSE location: 1.1296 -> 1.2006 | Hurt |
| Use a PM graph instead of a complete graph (ablation) | DyMF · Badminton singles, τ=8 | MSE location: 1.1366 -> 1.0827 | Helped |
| Use DyMF rather than ShuttleNet | Movement forecasting models · Badminton singles, τ=2, τ=4, and τ=8 | MSE location: 1.1345 -> 1.1006; 1.1539 -> 1.1061; 1.1399 -> 1.0827 | Helped |
Closest papers by meaning
- The CoachAI Badminton Environment: A Novel Reinforcement Learning Environment with Realistic Opponents (Student Abstract) (AAAI 2024 · similarity 0.89)
- Sports-Traj: A Unified Trajectory Generation Model for Multi-Agent Movement in Sports (ICLR 2025 · similarity 0.87)
- The CoachAI Badminton Environment: Bridging the Gap between a Reinforcement Learning Environment and Real-World Badminton Games (AAAI 2024 · similarity 0.86)
- Event2Tracking: Reconstructing Multi-Agent Soccer Trajectories Using Long-Term Multimodal Context (AAAI 2025 · similarity 0.85)
- LATTE-MV: Learning to Anticipate Table Tennis Hits from Monocular Videos (CVPR 2025 · similarity 0.85)
- Chess-World-Model: A 10M-Game Benchmark for Exact State Tracking from Chess Move Sequences (NeurIPS 2026 · 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.