TrajFormer: Efficient trajectory classification with transformers

Y Liang, K Ouyang, Y Wang, X Liu, H Chen… - Proceedings of the 31st …, 2022 - dl.acm.org
Transformers have been an efficient alternative to recurrent neural networks in many
sequential learning tasks. When adapting transformers to modeling trajectories, we …

Addressing some limitations of transformers with feedback memory

A Fan, T Lavril, E Grave, A Joulin… - arXiv preprint arXiv …, 2020 - arxiv.org
Transformers have been successfully applied to sequential, auto-regressive tasks despite
being feedforward networks. Unlike recurrent neural networks, Transformers use attention to …

Self-supervised contrastive representation learning for large-scale trajectories

S Li, W Chen, B Yan, Z Li, S Zhu, Y Yu - Future Generation Computer …, 2023 - Elsevier
Trajectory representation learning aims to embed trajectory sequences into fixed-length
vector representations while preserving their original spatio-temporal feature proximity …

Self-supervised trajectory representation learning with temporal regularities and travel semantics

J Jiang, D Pan, H Ren, X Jiang, C Li… - 2023 IEEE 39th …, 2023 - ieeexplore.ieee.org
Trajectory Representation Learning (TRL) is a powerful tool for spatial-temporal data
analysis and management. TRL aims to convert complicated raw trajectories into low …

Shifted chunk transformer for spatio-temporal representational learning

X Zha, W Zhu, L Xun, S Yang… - Advances in Neural …, 2021 - proceedings.neurips.cc
Spatio-temporal representational learning has been widely adopted in various fields such as
action recognition, video object segmentation, and action anticipation. Previous spatio …

Trembr: Exploring road networks for trajectory representation learning

TY Fu, WC Lee - ACM Transactions on Intelligent Systems and …, 2020 - dl.acm.org
In this article, we propose a novel representation learning framework, namely TRajectory
EMBedding via Road networks (Trembr), to learn trajectory embeddings (low-dimensional …

Teri: An effective framework for trajectory recovery with irregular time intervals

Y Chen, G Cong, C Anda - Proceedings of the VLDB Endowment, 2023 - dl.acm.org
The proliferation of trajectory data has facilitated various applications in urban spaces, such
as travel time estimation, traffic monitoring, and flow prediction. These applications require a …

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 …

Pre-Training General Trajectory Embeddings With Maximum Multi-View Entropy Coding

Y Lin, H Wan, S Guo, J Hu… - IEEE Transactions on …, 2023 - ieeexplore.ieee.org
Spatio-temporal trajectories provide valuable information about movement and travel
behavior, enabling various downstream tasks that in turn power real-world applications …

Working memory graphs

R Loynd, R Fernandez, A Celikyilmaz… - International …, 2020 - proceedings.mlr.press
Transformers have increasingly outperformed gated RNNs in obtaining new state-of-the-art
results on supervised tasks involving text sequences. Inspired by this trend, we study the …