paper-with-me

홈 › Papers

Dynamic Neural Relational Inference

2020-06-01 · CVPR 2020 6 · Colin Graber, Alexander G. Schwing

Understanding interactions between entities, e.g., joints of the human body, team sports players, etc., is crucial for tasks like forecasting. However, interactions between entities are commonly not observed and often hard to quantify. To address this challenge, recently, `Neural Relational Inference' was introduced. It predicts static relations between entities in a system and provides an interpretable representation of the underlying system dynamics that are used for better trajectory forecasting. However, generally, relations between entities change as time progresses. Hence, static relations improperly model the data. In response to this, we develop Dynamic Neural Relational Inference (dNRI), which incorporates insights from sequential latent variable models to predict separate relation graphs for every time-step. We demonstrate on several real-world datasets that modeling dynamic relations improves forecasting of complex trajectories.

📄 PDF Abstract BibTeX

Code (1)

cgraber/cvpr_dNRI 공식 구현 pytorch

Tasks

Trajectory Forecasting

Similar Papers 제목 키워드 기반

Dynamic Relational Inference in Multi-Agent Trajectories

2020-07-16 · Ruichao Xiao, Manish Kumar Singh, Rose Yu

Inferring interactions from multi-agent trajectories has broad applications in physics, vision and robotics. Neural relational inference (NRI) is a deep generative model that can reason about relations in complex dynamic…

RDI-Net: Relational Dynamic Inference Networks

2021-01-01 · ICCV 2021 10 · Huanyu Wang, Songyuan Li, Shihao Su, Zequn Qin 외

Dynamic inference networks, aimed at promoting computational efficiency, go along an adaptive executing path for a given sample. Prevalent methods typically assign a router for each convolutional block and sequential…

Computational EfficiencyRelation

Diffusion model for relational inference

2024-01-30 · Shuhan Zheng, Ziqiang Li, Kantaro Fujiwara, Gouhei Tanaka

Dynamical behaviors of complex interacting systems, including brain activities, financial price movements, and physical collective phenomena, are associated with underlying interactions between the system's components. T…

ImputationmodelTime Series

Memory-Augmented Dynamic Neural Relational Inference

2021-01-01 · ICCV 2021 10 · Dong Gong, Frederic Z. Zhang, Javen Qinfeng Shi, Anton Van Den Hengel

Dynamic interacting systems are prevalent in vision tasks. These interactions are usually difficult to observe and measure directly, and yet understanding latent interactions is essential for performing inference tas…

Trajectory Prediction

A Graph Dynamics Prior for Relational Inference

2023-06-09 · Liming Pan, Cheng Shi, Ivan Dokmanić

Relational inference aims to identify interactions between parts of a dynamical system from the observed dynamics. Current state-of-the-art methods fit the dynamics with a graph neural network (GNN) on a learnable graph.…

Graph LearningGraph Neural Network