D Park, J Jeong, KJ Yoon - Proceedings of the AAAI Conference on …, 2024 - ojs.aaai.org
Multi-agent trajectory prediction is crucial for various practical applications, spurring the construction of many large-scale trajectory datasets, including vehicles and pedestrians …
R Li, C Li, D Ren, G Chen, Y Yuan… - Advances in Neural …, 2024 - proceedings.neurips.cc
The objective of pedestrian trajectory prediction is to estimate the future paths of pedestrians by leveraging historical observations, which plays a vital role in ensuring the safety of self …
Trajectory computing is a pivotal domain encompassing trajectory data management and mining, garnering widespread attention due to its crucial role in various practical …
V Iakovlev, C Yildiz, M Heinonen… - arXiv preprint arXiv …, 2022 - arxiv.org
Training dynamic models, such as neural ODEs, on long trajectories is a hard problem that requires using various tricks, such as trajectory splitting, to make model training work in …
A Graser, A Jalali, J Lampert, A Weißenfeld… - EDBT/ICDT …, 2023 - ceur-ws.org
Trajectory data combines the complexities of time series, spatial data, and (sometimes irrational) movement behavior. As data availability and computing power have increased, so …
M Lechner, R Hasani - arXiv preprint arXiv:2006.04418, 2020 - arxiv.org
Recurrent neural networks (RNNs) with continuous-time hidden states are a natural fit for modeling irregularly-sampled time series. These models, however, face difficulties when the …
Y Rubanova, RTQ Chen… - Advances in neural …, 2019 - proceedings.neurips.cc
Time series with non-uniform intervals occur in many applications, and are difficult to model using standard recurrent neural networks (RNNs). We generalize RNNs to have continuous …
Z Ma, H Zhang, J Liu - arXiv preprint arXiv:2206.03010, 2022 - arxiv.org
Spatiotemporal predictive learning, which predicts future frames through historical prior knowledge with the aid of deep learning, is widely used in many fields. Previous work …
Neural Ordinary Differential Equations (NODEs) use a neural network to model the instantaneous rate of change in the state of a system. However, despite their apparent …