AI Paper Atlas

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

Where Will They Go? Predicting Fine-Grained Adversarial Multi-Agent Motion using Conditional Variational Autoencoders

Panna Felsen, Patrick Lucey, Sujoy Ganguly

ECCV 2018 · Multi-agent systems and games › Human-AI and goal-conditioned · approach: Interactive multi-agent trajectory prediction · 71 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 role alignment to VAE (ablation)VAE · Offense, 4 savg distance error (ft): 7.10 -> 6.85Improved
add history, context and team conditionals to random-aligned VAE (ablation)CVAE · Offense, 4 savg distance error (ft): 7.10 -> 6.76Improved
add a single conditional (history, context, team or player) with random alignment (ablation)CVAE · Offense, 4 savg distance error (ft): 7.10 -> 6.90No clear effect
add role alignment to the CVAE with history, context and team (ablation)CVAE · Offense, 4 savg distance error (ft): 6.76 -> 5.80Improved
use role alignment instead of canonical position alignment (ablation)CVAE history+context+team · Offense, 4 savg distance error (ft): 6.09 -> 5.80Improved
add team identity conditional under role alignment (ablation)CVAE role · Offense, 4 savg distance error (ft): 5.81 -> 5.80No clear effect
use player identity instead of team identity under role alignment (ablation)CVAE role · Offense, 4 savg distance error (ft): 5.80 -> 5.96Hurt
add history and context conditionals to random-aligned CVAE with player identity (ablation)CVAE random · Offense, 4 savg distance error (ft): 7.02 -> 6.64Improved
replace Social LSTM with CVAE-role-teammix 5v5 prediction · Basketball 4 s horizonavg distance error (ft): 17.95 -> 5.74Improved
increase observed history length (1 s to 4 s) (ablation)CVAE-role-team · Basketball offenseavg distance error (ft): 4 s history barely optimalImproved
increase prediction horizon from 1 s to 8 s (ablation)CVAE-role-team offense · Basketball offenseavg distance error (ft): 2.35 -> 8.07Hurt
increase predicted players from 1v1 to 5v5 (ablation)CVAE-role-team · Basketball mixture 4 savg distance error (ft): 4.19 -> 5.74Hurt

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