AI Paper Atlas

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

MTR++: Multi-Agent Motion Prediction With Symmetric Scene Modeling and Guided Intention Querying

Shaoshuai Shi, Li Jiang, Dengxin Dai, Bernt Schiele

TPAMI 2024 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 241 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 learnable intention query instead of latent anchor embedding (ablation)MTR · WOMD val ablationmAP: +5.53%Improved
use learnable intention query instead of dense goals (ablation)MTR · WOMD val ablationmAP: +4.67%Improved
add iterative trajectory refinement (ablation)MTR · WOMD val ablationmAP, Miss Rate: 0.3379 -> 0.3539; miss rate 1.48% lowerImproved
use k-means intention points instead of uniform grids (ablation)MTR · WOMD val ablationmAP: 0.3205 -> 0.3539Improved
use local instead of global self-attention (256 polylines) (ablation)MTR encoder · WOMD val ablationmAP: 0.3450 -> 0.3522Improved
use local attention with more polylines (768 vs global OOM) (ablation)MTR encoder · WOMD val ablationmAP: OOM -> 0.3539Improved
add symmetric scene context encoder (ablation)MTR · WOMD val ablationinference latency, 32 agents: 193ms -> 98ms; 15.6GB -> 4.7GBImproved
add symmetric scene context encoder (ablation)MTR · WOMD val ablationmAP: 0.3539 -> 0.3505No clear effect
add mutually-guided intention querying (ablation)MTR+ · WOMD val ablationmAP: +2.49%; 0.3505 -> 0.3754Improved
add intention query interaction within and across agents (ablation)MTR++ · WOMD val ablationmAP: 0.3484 -> 0.3754Improved
use query-centric positional encoding instead of none (ablation)MTR++ · WOMD val ablationmAP: 0.3513 -> 0.3754Improved
use query-centric instead of global positional encoding (ablation)MTR++ · WOMD val ablationmAP: 0.3463 -> 0.3754Improved

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