Research map / Multi-agent systems and games / Human-AI and goal-conditioned
Resonance: Learning to Predict Social-Aware Pedestrian Trajectories as Co-Vibrations
Conghao Wong, Ziqian Zou, Beihao Xia
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 self-bias vibration on top of linear base plus re-bias (ablation) | Re · ETH-UCY avg (ablation) | minADE: 0.434 -> 0.210 | Improved |
| add resonance-bias to linear base plus self-bias (ablation) | Re · ETH-UCY avg (ablation) | minADE: 0.210 -> 0.176 | Improved |
| add resonance-bias to linear base plus self-bias (ablation) | Re · SDD | minADE: 6.93 -> 6.27 | Improved |
| add linear base to self-bias plus re-bias (ablation) | Re · ETH-UCY avg (ablation) | minADE: 0.182 -> 0.176 | Improved |
| add linear base to self-bias plus re-bias (ablation) | Re · NBA | minADE: 1.14 -> 1.17 | Hurt |
| add self-bias to linear base plus re-bias on top of re-bias only model (ablation) | Re · ETH-UCY avg (ablation) | minADE: 0.188 -> 0.176 | Mixed |
| use resonance gathering instead of SocialCircle for social vibration (ablation) | Re · ETH-UCY avg (ablation) | minADE: 0.184 -> 0.176 | Improved |
| use resonance gathering instead of SocialCircle for social vibration (ablation) | Re · SDD | minADE: 6.39 -> 6.27 | Improved |
| use resonance gathering instead of SocialCircle under same conditions without linear base (ablation) | Re · NBA | minADE: 1.18 -> 1.14 | Improved |
| Re vs SocialCircle+ | Re · ETH-UCY eth | minADE: 0.25 -> 0.23 | Improved |
| Re vs SocialCircle+ | Re · SDD | minADE: 6.44 -> 6.27 | Improved |
| Re vs SocialCircle+ | Re · NBA (tf=5) | minFDE: 0.86 -> 0.78 | Improved |
Closest papers by meaning
- SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latents (AAAI 2024 · similarity 0.88)
- SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.87)
- EigenTrajectory: Low-Rank Descriptors for Multi-Modal Trajectory Forecasting (ICCV 2023 · similarity 0.87)
- SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction (CVPR 2025 · similarity 0.87)
- Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion (CVPR 2022 · similarity 0.86)
- Higher-order Relational Reasoning for Pedestrian 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.
