Leveraging future relationship reasoning for vehicle trajectory prediction
Understanding the interaction between multiple agents is crucial for realistic vehicle
trajectory prediction. Existing methods have attempted to infer the interaction from the …
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 …
extending neural networks to arbitrary irregular domains. The principle of these networks …
Dynamic neural relational inference
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 …
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
Online transient analysis plays an increasingly important role in dynamic power grids as the
renewable generation continues growing. Traditional numerical methods for transient …
renewable generation continues growing. Traditional numerical methods for transient …
Multi-agent trajectory prediction with fuzzy query attention
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 …
numerous domains such as traffic prediction, pedestrian tracking and path planning. We …
Dynamic neural relational inference for forecasting trajectories
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 …
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 …
generalizing convolutional operations to arbitrary non-regular domains. In particular, GCNs …
Iterative structural inference of directed graphs
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' …
Graphs (iSIDG), to infer the existence of directed interactions from observational agents' …
Memory-augmented dynamic neural relational inference
Dynamic interacting systems are prevalent in vision tasks. These interactions are usually
difficult to observe and measure directly, and yet understanding latent interactions is …
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 …
many cases, only the state sequences of individual agents are observed, while the …