STGAT: Modeling Spatial-Temporal Interactions for Human Trajectory Prediction

Huikun Bi · Zhaoxin Li · Tianlu Mao · Zhaoqi Wang

691 citations0/0 files storedIEEE/CVF International Conference on Computer Vision (ICCV)

No readable copy stored yet — this record is metadata only.

No open-access location is known for this record yet.

Literature note Cite in a project Citation map

Evacuation and Crowd Dynamics Robotic Path Planning Algorithms Autonomous Vehicle Technology and Safety

Abstract

Human trajectory prediction is challenging and critical in various applications (e.g., autonomous vehicles and social robots). Because of the continuity and foresight of the pedestrian movements, the moving pedestrians in crowded spaces will consider both spatial and temporal interactions to avoid future collisions. However, most of the existing methods ignore the temporal correlations of interactions with other pedestrians involved in a scene. In this work, we propose a Spatial-Temporal Graph Attention network (STGAT), based on a sequence-to-sequence architecture to predict future trajectories of pedestrians. Besides the spatial interactions captured by the graph attention mechanism at each time-step, we adopt an extra LSTM to encode the temporal correlations of interactions. Through comparisons with state-of-the-art methods, our model achieves superior performance on two publicly available crowd datasets (ETH and UCY) and produces more "socially" plausible trajectories for pedestrians.

Paper brief

Loading…

Cite this work

Citation unavailable for this work.

BibTeX RIS CSL-JSON

No public copy is stored for this record, so only the metadata is cited.

Citations in this library

Citation map →

Stored only when both papers are in the corpus — 691 citations exist upstream.

References

1995Social force model for pedestrian dynamics 2007Crowds by Example 2006Continuum crowds 2018Social Attention: Modeling Attention in Human Crowds 2005Discrete choice models of pedestrian walking behavior 2018Soft + Hardwired attention: An LSTM framework for human trajectory prediction and abnormal event detection

Cited by

2020Spatio-Temporal Graph Transformer Networks for Pedestrian Trajectory Prediction 2021Human Trajectory Forecasting in Crowds: A Deep Learning Perspective 2020Recursive Social Behavior Graph for Trajectory Prediction 2021AST-GNN: An attention-based spatio-temporal graph neural network for Interaction-aware pedestrian trajectory prediction 2022Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-Based Approaches 2021Pedestrian trajectory prediction with convolutional neural networks

Explore the map →

Papers that cite the same references — the relational fallback while embeddings are still backfilling.

Imported from OpenAlex (CC0) — nothing here is generated.