Leveraging future relationship reasoning for vehicle trajectory prediction

D Park, H Ryu, Y Yang, J Cho, J Kim… - arxiv preprint arxiv …, 2023 - arxiv.org
Understanding the interaction between multiple agents is crucial for realistic vehicle
trajectory prediction. Existing methods have attempted to infer the interaction from the …

Learning laplacians in chebyshev graph convolutional networks

H Sahbi - Proceedings of the IEEE/CVF International …, 2021 - openaccess.thecvf.com
Spectral graph convolutional networks (GCNs) are particular deep models which aim at
extending neural networks to arbitrary irregular domains. The principle of these networks …

Dynamic neural relational inference

C Graber, AG Schwing - … of the IEEE/CVF conference on …, 2020 - openaccess.thecvf.com
Understanding interactions between entities, eg, joints of the human body, team sports
players, etc., is crucial for tasks like forecasting. However, interactions between entities are …

Structure-informed graph learning of networked dependencies for online prediction of power system transient dynamics

T Zhao, M Yue, J Wang - IEEE Transactions on Power Systems, 2022 - ieeexplore.ieee.org
Online transient analysis plays an increasingly important role in dynamic power grids as the
renewable generation continues growing. Traditional numerical methods for transient …

Multi-agent trajectory prediction with fuzzy query attention

N Kamra, H Zhu, DK Trivedi… - Advances in Neural …, 2020 - proceedings.neurips.cc
Trajectory prediction for scenes with multiple agents and entities is a challenging problem in
numerous domains such as traffic prediction, pedestrian tracking and path planning. We …

Dynamic neural relational inference for forecasting trajectories

C Graber, A Schwing - … of the IEEE/CVF Conference on …, 2020 - openaccess.thecvf.com
Understanding interactions between entities, eg, joints of the human body, team sports
players, etc., is crucial for tasks like forecasting. However, interactions between entities are …

Learning connectivity with graph convolutional networks

H Sahbi - 2020 25th International Conference on Pattern …, 2021 - ieeexplore.ieee.org
Learning graph convolutional networks (GCNs) is an emerging field which aims at
generalizing convolutional operations to arbitrary non-regular domains. In particular, GCNs …

Iterative structural inference of directed graphs

A Wang, J Pang - Advances in Neural Information …, 2022 - proceedings.neurips.cc
In this paper, we propose a variational model, iterative Structural Inference of Directed
Graphs (iSIDG), to infer the existence of directed interactions from observational agents' …

Memory-augmented dynamic neural relational inference

D Gong, FZ Zhang, JQ Shi… - Proceedings of the …, 2021 - openaccess.thecvf.com
Dynamic interacting systems are prevalent in vision tasks. These interactions are usually
difficult to observe and measure directly, and yet understanding latent interactions is …

Neural relational inference with efficient message passing mechanisms

S Chen, J Wang, G Li - Proceedings of the AAAI Conference on Artificial …, 2021 - ojs.aaai.org
Many complex processes can be viewed as dynamical systems of interacting agents. In
many cases, only the state sequences of individual agents are observed, while the …