AI Paper Atlas

Research map / Probabilistic and scientific modeling / Molecules and proteins

Human Trajectory Prediction via Counterfactual Analysis

Guangyi Chen, Junlong Li, Jiwen Lu, Jie Zhou

ICCV 2021 · Probabilistic and scientific modeling › Molecules and proteins · approach: Multimodal trajectory prediction · 98 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 counterfactual analysis (zero-vector history intervention, subtract prediction)STGAT · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.47/0.93 -> 0.40/0.77Improved
add counterfactual analysis (zero-vector history intervention)Social-STGCNN · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.45/0.75 -> 0.43/0.66Improved
use mean feature vector instead of zero vector as counterfactual (ablation)Causal-STGAT · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.40/0.77 -> 0.44/0.84Hurt
use random uniform vector instead of zero vector as counterfactual (ablation)Causal-STGAT · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.40/0.77 -> 0.42/0.80Hurt
mean counterfactual versus no counterfactual (ablation)STGAT · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.47/0.93 -> 0.44/0.84Improved
random counterfactual versus no counterfactual (ablation)STGAT · ETH/UCY (avg of 5 scenes)ADE/FDE: 0.47/0.93 -> 0.42/0.80Improved
add causal model to Social-STGCNN with scene image featuresS-STGCNN · ETH/UCY with scene image (avg of 5 scenes)ADE/FDE: 0.57/0.91 -> 0.43/0.73Improved
add causal model to PECNetPECNet* · Stanford Drone DatasetADE/FDE: 10.27/15.99 -> 9.19/15.31Improved
add counterfactual analysisSocial-STGCNN* · ETH/UCY (UNIV scene)ADE/FDE: 0.51/0.93 -> 0.49/0.81Improved
add counterfactual analysis on ZARA2 sceneSocial-STGCNN* · ETH/UCY (ZARA2 scene)ADE/FDE: 0.31/0.47 -> 0.32/0.49Mixed
add counterfactual analysis (extra computation on part of network)Social-STGCNN · ETH/UCY inferenceinference time: 0.0116 -> 0.0124Hurt
add counterfactual analysisSTGAT · ETH/UCY inferenceparameters: 56k -> 56kNo clear effect

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