Research map / Probabilistic and scientific modeling / Molecules and proteins
Socialality Anchors: Towards Group-Bounded Trajectory Prediction
Ziqian Zou, Conghao Wong, Qinmu Peng, Xinge You
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 |
|---|---|---|---|
| inject Gaussian noise (sigma 0.1) into neighbor short-term previews (ablation) | Socialality · ETH-UCY zara1 | ADE/FDE: +0.43% / +0.06% | No clear effect |
| inject Gaussian noise (sigma 2.0) into neighbor previews (ablation) | Socialality · ETH-UCY zara1 | ADE/FDE: +30.05% / +29.31% | Hurt |
| swap all neighbors' previews (ablation) | Socialality · ETH-UCY zara1 | ADE/FDE: +49.78% / +55.06% | Hurt |
| flip all neighbors' previews (ablation) | Socialality · ETH-UCY zara1 | ADE/FDE: +49.92% / +46.88% | Hurt |
| swap 20% of neighbor previews (ablation) | Socialality · ETH-UCY zara1 | group consistency: 89.98% -> 41.61% | Hurt |
| replace fixed 180 degree FOV with adaptive FOV (ablation) | Socialality · SDD | ADE/FDE: 6.283/10.121 -> 6.330/10.195 | No clear effect |
| replace fixed FOV with adaptive FOV (ablation) | Socialality · NBA (t_p=10) | ADE/FDE: 1.212/1.641 -> 1.198/1.614 | Improved |
| use team ownership as group priors (ablation) | Socialality · NBA (t_p=5) | ADE/FDE: 0.624/0.875 -> 0.605/0.829 | Improved |
| add environmental virtual agents with stride 5 (ablation) | Socialality · ETH-UCY zara1 | ADE: 0.168 -> 0.170 | Hurt |
| add environmental virtual agents with stride 5 (ablation) | Socialality · SDD | ADE/FDE: 6.283/10.121 -> 6.274/10.074 | Improved |
| use stride 1 (dense virtual agents) instead of 5 (ablation) | sa-map · ETH-UCY zara1 | ADE: 0.170 -> 0.183 | Hurt |
| replace MSN with Transformer backbone (ablation) | Socialality · ETH-UCY eth | ADE/FDE: 0.233/0.369 -> 0.272/0.454 | Hurt |
Closest papers by meaning
- Social-Mamba: Socially-Aware Trajectory Forecasting with State-Space Models (ECCV 2026 · similarity 0.86)
- SocialCVAE: Predicting Pedestrian Trajectory via Interaction Conditioned Latents (AAAI 2024 · similarity 0.84)
- Social-Transmotion: Promptable Human Trajectory Prediction (ICLR 2024 · similarity 0.84)
- SocialMOIF: Multi-Order Intention Fusion for Pedestrian Trajectory Prediction (CVPR 2025 · similarity 0.84)
- SocialCircle: Learning the Angle-based Social Interaction Representation for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.83)
- Higher-order Relational Reasoning for Pedestrian Trajectory Prediction (CVPR 2024 · similarity 0.82)
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.
