Paper Info
Title
Memory-augmented Dynamic Neural Relational Inference.
Abstract
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 tasks on dynamic systems like forecasting. Neural relational inference (NRI) techniques are thus introduced to explicitly estimate interpretable relations between the entities in the system for trajectory prediction. However, NRI assumes static relations; thus, dynamic neural relational inference (DNRI) was proposed to handle dynamic relations using LSTM. Unfortunately, the older information will be washed away when the LSTM updates the latent variable as a whole, which is why DNRI struggles with modeling long-term dependences and forecasting long sequences. This motivates us to propose a memory-augmented dynamic neural relational inference method, which maintains two associative memory pools: one for the interactive relations and the other for the individual entities. The two memory pools help retain useful relation features and node features for the estimation in the future steps. Our model dynamically estimates the relations by learning better embeddings and utilizing the long-range information stored in the memory. With the novel memory modules and customized structures, our memory-augmented DNRI can update and access the memory adaptively as required. The memory pools also serve as global latent variables across time to maintain detailed long-term temporal relations readily available for other components to use. Experiments on synthetic and real-world datasets show the effectiveness of the proposed method on modeling dynamic relations and forecasting complex trajectories.
Year
DOI
Venue
2021
10.1109/ICCV48922.2021.01163
ICCV
DocType
Citations 
PageRank 
Conference
0
0.34
References 
Authors
0
4
Name
Order
Citations
PageRank
Dong Gong100.68
Frederic Z. Zhang200.34
Qinfeng Shi3156474.85
Anton van den Hengel43710174.30