AI Paper Atlas

Research map / Graph learning / Knowledge and temporal graphs

STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction

Yingfan Huang, Huikun Bi, Zhaoxin Li, Tianlu Mao, Zhaoqi Wang

ICCV 2019 · Graph learning › Knowledge and temporal graphs · approach: Spatio-temporal graph traffic forecasting · 716 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
replace SGAN pooling with a graph attention network (GAT) (ablation)SGAT vs SGAN-20VP-20 · ETH/UCY average, Tpred=8ADE: 0.41 -> 0.36Improved
replace SGAN pooling with a graph attention network (GAT) (ablation)SGAT vs SGAN-20VP-20 · ETH/UCY average, Tpred=12ADE: 0.61 -> 0.47Improved
replace SGAN pooling with a graph attention network (GAT) (ablation)SGAT vs SGAN-20VP-20 · ETH/UCY average, Tpred=12FDE: 1.21 -> 0.92Improved
add G-LSTM to model temporal correlations of interactions (ablation)STGAT-20V-20 over SGAT · ETH/UCY average, Tpred=8ADE: 0.36 -> 0.31Improved
add G-LSTM to model temporal correlations of interactions (ablation)STGAT-20V-20 over SGAT · ETH/UCY average, Tpred=12ADE: 0.47 -> 0.43Improved
add G-LSTM to model temporal correlations of interactions (ablation)STGAT-20V-20 over SGAT · ETH/UCY average, Tpred=12FDE: 0.92 -> 0.83Improved
add variety loss (k=20 outputs instead of 1) (ablation)STGAT · ETH/UCY average (Tpred=8, 12)ADE: reduced by 22.6% and 16.3%Improved
add variety loss (k=20 outputs instead of 1) (ablation)STGAT · ETH/UCY average (Tpred=8, 12)FDE: reduced by 27.4%, 26.5%Improved
add G-LSTM (ablation)STGAT over SGAT · CUDA memory in training (MB)memory: 1133 -> 7503Hurt
add G-LSTM (ablation)STGAT over SGAT · Inference time (seconds, avg)time: 11.565 -> 11.680No clear effect
replace SGAN pooling with GAT (ablation)SGAT over SGAN-P · Inference time (seconds, avg)time: 8.579 -> 11.565Hurt

Later papers that compared with this method

1 later accepted paper reports STGAT 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