AI Paper Atlas

Research map / Multi-agent systems and games / Human-AI and goal-conditioned

EqMotion: Equivariant Multi-Agent Motion Prediction With Invariant Interaction Reasoning

Chenxin Xu, Robby T. Tan, Yuhong Tan, Siheng Chen, Yu Guang Wang, Xinchao Wang, Yanfeng Wang

CVPR 2023 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 135 citations (OpenAlex)

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 changedWhereMeasuredEffect
Use EqMotion's equivariant geometric, invariant pattern, and invariant interaction reasoning modulesmotion prediction · MD17 moleculesADE/FDE: 34.2%/30.1%Improved
Use EqMotionH3.6M short-term skeleton prediction · H3.6MMPJPE: 8.6%Improved
Use EqMotionH3.6M long-term skeleton prediction · H3.6MMPJPE: 3.8%Improved
Use EqMotiondeterministic pedestrian prediction · ETH-UCYFDE: 10.4%Improved
Use EqMotion multi-predictionpedestrian prediction · ETH-UCYFDE: 7.9%Improved
Add EGFL (ablation)EqMotion · H3.6MMPJPE at 400ms: 82.4 -> 60.7Improved
Add IPFL (ablation)EqMotion with EGFL · H3.6MMPJPE at 400ms: 60.7 -> 57.0Improved
Add IRM (ablation)EqMotion with EGFL and IPFL · H3.6MMPJPE at 400ms: 57.0 -> 55.0Improved
Add inner-agent attention (ablation)EqMotion · H3.6MMPJPE at 400ms: 55.7 -> 55.0Improved
Add inter-agent aggregation (ablation)EqMotion · H3.6MMPJPE at 400ms: 58.9 -> 55.0Improved
Add equivariant nonlinear function (ablation)EqMotion · H3.6MMPJPE at 400ms: 58.6 -> 55.0Improved
Increase feature-learning depth from 1 to 4 layers (ablation)EqMotion · H3.6MMPJPE at 400ms: 58.3 -> 55.0Improved

Later papers that compared with this method

1 later accepted paper reports EqMotion as a baseline in their results tables; 1 of them report a better number on most of the results they share with it.

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

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.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy