Progressively generating better initial guesses towards next stages for high-quality human motion prediction

T Ma, Y Nie, C Long, Q Zhang… - Proceedings of the IEEE …, 2022 - openaccess.thecvf.com
This paper presents a high-quality human motion prediction method that accurately predicts
future human poses given observed ones. Our method is based on the observation that a …

Trajectory unified transformer for pedestrian trajectory prediction

L Shi, L Wang, S Zhou, G Hua - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Pedestrian trajectory prediction is an essentially connecting link to understanding human
behavior. Recent works achieve state-of-the-art performance gained from the hand …

Eigentrajectory: Low-rank descriptors for multi-modal trajectory forecasting

I Bae, J Oh, HG Jeon - Proceedings of the IEEE/CVF …, 2023 - openaccess.thecvf.com
Capturing high-dimensional social interactions and feasible futures is essential for
predicting trajectories. To address this complex nature, several attempts have been devoted …

Sparse instance conditioned multimodal trajectory prediction

Y Dong, L Wang, S Zhou, G Hua - Proceedings of the IEEE …, 2023 - openaccess.thecvf.com
Pedestrian trajectory prediction is critical in many vision tasks but challenging due to the
multimodality of the future trajectory. Most existing methods predict multimodal trajectories …

Multi-stream representation learning for pedestrian trajectory prediction

Y Wu, L Wang, S Zhou, J Duan, G Hua… - Proceedings of the AAAI …, 2023 - ojs.aaai.org
Forecasting the future trajectory of pedestrians is an important task in computer vision with a
range of applications, from security cameras to autonomous driving. It is very challenging …

A set of control points conditioned pedestrian trajectory prediction

I Bae, HG Jeon - Proceedings of the AAAI Conference on Artificial …, 2023 - ojs.aaai.org
Predicting the trajectories of pedestrians in crowded conditions is an important task for
applications like autonomous navigation systems. Previous studies have tackled this …

Social-ssl: Self-supervised cross-sequence representation learning based on transformers for multi-agent trajectory prediction

LW Tsao, YK Wang, HS Lin, HH Shuai… - … on Computer Vision, 2022 - Springer
Earlier trajectory prediction approaches focus on ways of capturing sequential structures
among pedestrians by using recurrent networks, which is known to have some limitations in …

Multimodal trajectory prediction: A survey

R Huang, H Xue, M Pagnucco, F Salim… - arxiv preprint arxiv …, 2023 - arxiv.org
Trajectory prediction is an important task to support safe and intelligent behaviours in
autonomous systems. Many advanced approaches have been proposed over the years with …

Can Language Beat Numerical Regression? Language-Based Multimodal Trajectory Prediction

I Bae, J Lee, HG Jeon - … of the IEEE/CVF Conference on …, 2024 - openaccess.thecvf.com
Abstract Language models have demonstrated impressive ability in context understanding
and generative performance. Inspired by the recent success of language foundation models …

STGlow: A flow-based generative framework with dual-graphormer for pedestrian trajectory prediction

R Liang, Y Li, J Zhou, X Li - IEEE transactions on neural …, 2023 - ieeexplore.ieee.org
The pedestrian trajectory prediction task is an essential component of intelligent systems. Its
applications include but are not limited to autonomous driving, robot navigation, and …