Research map / Multi-agent systems and games / Human-AI and goal-conditioned
IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction
Dekai Zhu, Guangyao Zhai, Yan Di, Fabian Manhardt, Hendrik Berkemeyer, Tuan Tran, Nassir Navab, Federico Tombari, Benjamin Busam
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 IPCC-TP to AgentFormer | AgentFormer · nuScenes | minJ-FDE(5): 7.82 -> 7.49 | Improved |
| Add IPCC-TP to AutoBots | AutoBots · nuScenes | minJ-FDE(5): 6.50 -> 6.27 | Improved |
| Add IPCC-TP to AgentFormer | AgentFormer · Argoverse 2 | minJ-FDE(6): 5.88 -> 4.64 | Improved |
| Add IPCC-TP to AutoBots | AutoBots · Argoverse 2 | minJ-FDE(6): 5.76 -> 4.79 | Improved |
| Replace CUM with IPCC-TP | AutoBots · Argoverse 2 | minJ-FDE(6): 4.85 -> 4.79 | Improved |
| Replace CUM with IPCC-TP | AgentFormer · nuScenes | minJ-FDE(5): 7.75 -> 7.49 | Improved |
| Replace the Attention Block with an MLP Block (ablation) | AutoBots+IPCC-TP · Argoverse 2 | minJ-FDE(6): 4.79 -> 4.84 | Hurt |
| Set Tikhonov regularization Δreg to 1.0e-3 instead of 1.0e-4 (ablation) | AutoBots+IPCC-TP · Argoverse 2 | minJ-FDE(6): 4.79 -> 8.59 | Hurt |
| Set Tikhonov regularization Δreg to 1.0e-5 instead of 1.0e-4 (ablation) | AutoBots+IPCC-TP · Argoverse 2 | minJ-FDE(6): 4.79 -> 28.24 | Hurt |
| Remove Tikhonov regularization (ablation) | AutoBots+IPCC-TP · Argoverse 2 | training stability | Hurt |
| Evaluate AutoBots with IPCC-TP | AutoBots · INTERACTION | minJ-FDE(6): 0.97 -> 0.93 | Improved |
Earlier methods this paper compares with
Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.
- AgentFormer — AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting (ICCV 2021) · better on 4 of 4 shared results
Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.
Closest papers by meaning
- FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs (CVPR 2023 · similarity 0.87)
- M2I: From Factored Marginal Trajectory Prediction to Interactive Prediction (CVPR 2022 · similarity 0.87)
- THOMAS: Trajectory Heatmap Output with learned Multi-Agent Sampling (ICLR 2022 · similarity 0.86)
- Unlimited Neighborhood Interaction for Heterogeneous Trajectory Prediction (ICCV 2021 · similarity 0.86)
- Leveraging Future Relationship Reasoning for Vehicle Trajectory Prediction (ICLR 2023 · similarity 0.86)
- Density-Adaptive Model Based on Motif Matrix for Multi-Agent Trajectory Prediction (CVPR 2024 · similarity 0.86)
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.
