AI Paper Atlas

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

AgentFormer: Agent-Aware Transformers for Socio-Temporal Multi-Agent Forecasting

Ye Yuan, Xinshuo Weng, Yanglan Ou, Kris M. Kitani

ICCV 2021 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 720 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
add agent-aware attention (vs standard scaled dot-product attention) (ablation)AgentFormer · ETH/UCY average (K=20)ADE_20/FDE_20: 0.27/0.47 -> 0.23/0.39Improved
add agent-aware attention (vs standard scaled dot-product attention) (ablation)AgentFormer · nuScenes (K=5)ADE_5/FDE_5: 2.02/4.29 -> 1.86/3.89Improved
use agent-aware attention instead of agent index encoding (ablation)AgentFormer · ETH/UCY average (K=20)ADE_20/FDE_20: 0.27/0.46 -> 0.23/0.39Improved
use agent-aware attention instead of agent index encoding (ablation)AgentFormer · nuScenes (K=10)ADE_10/FDE_10: 1.63/3.11 -> 1.45/2.86Improved
add joint latent intent modeling across agents (ablation)AgentFormer · ETH/UCY average (K=20)ADE_20/FDE_20: 0.27/0.46 -> 0.23/0.39Improved
add joint latent intent modeling across agents (ablation)AgentFormer · nuScenes (K=5)ADE_5/FDE_5: 1.95/3.98 -> 1.86/3.89Improved
add semantic map features (ablation)AgentFormer · nuScenes (K=5)ADE_5/FDE_5: 1.97/4.21 -> 1.86/3.89Improved
model time and social dimensions jointly instead of separate TF social + TF temporal (ablation)AgentFormer · ETH/UCY average (K=20)ADE_20/FDE_20: 0.26/0.47 -> 0.23/0.39Improved
model time and social dimensions jointly instead of separate TF social + TF temporal (ablation)AgentFormer · nuScenes (K=5)ADE_5/FDE_5: 1.99/4.12 -> 1.86/3.89Improved
use Transformer instead of LSTM as temporal model (GCN social) (ablation)separate social/temporal baseline · ETH/UCY average (K=20)ADE_20/FDE_20: 0.31/0.52 -> 0.28/0.50Improved
use Transformer instead of LSTM as temporal model (TF social) (ablation)separate social/temporal baseline · nuScenes (K=10)ADE_10/FDE_10: 1.69/3.31 -> 1.54/3.07Improved
add agent-aware attention (vs standard attention) (ablation)AgentFormer · nuScenes (K=10)FDE_10: 2.91 -> 2.86No clear effect

Later papers that compared with this method

9 later accepted papers report AgentFormer as a baseline in their results tables; 7 of them report a better number on most of the results they share with it.

1 more not listed.

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.

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