mlsanityData to 7 Oct 2026

Convolutions for Spatial Interaction Modeling

arXiv 2104.07182 ↗First posted 15 Apr 2021cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

In many different fields interactions between objects play a critical role in determining their behavior. Graph neural networks (GNNs) have emerged as a powerful tool for modeling interactions, although often at the cost of adding considerable complexity and latency. In this paper, we consider the problem of spatial interaction modeling in the context of predicting the motion of actors around autonomous vehicles, and investigate alternatives to GNNs. We revisit 2D convolutions and show that they can demonstrate comparable performance to graph networks in modeling spatial interactions with lower latency, thus providing an effective and efficient alternative in time-critical systems. Moreover, we propose a novel interaction loss to further improve the interaction modeling of the considered methods.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 34 of its 42 references that are in the map. First posted on arXiv 15 Apr 2021.

Builds on

34 of 42 references.

References · 34

  1. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  2. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  3. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  4. 2017Inductive Representation Learning on Large Graphscited by 6,284
  5. 2016Feature Pyramid Networks for Object Detectioncited by 5,021
  6. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  7. 2017Neural Message Passing for Quantum Chemistrycited by 3,460
  8. 2017Non-local Neural Networkscited by 2,290
  9. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  10. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  11. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  12. 2020On the Bottleneck of Graph Neural Networks and its Practical Implicationscited by 624
22 more
  1. 2017Learning Combinatorial Optimization Algorithms over Graphscited by 557
  2. 2020VectorNet: Encoding HD Maps and Agent Dynamics from Vectorized Representationcited by 528
  3. 2016Interaction Networks for Learning about Objects, Relations and Physicscited by 503
  4. 2020Inductive Representation Learning on Temporal Graphscited by 454
  5. 2018Neural Relational Inference for Interacting Systemscited by 339
  6. 2018Multimodal Trajectory Predictions for Autonomous Driving using Deep Convolutional Networkscited by 289
  7. 2018Graph networks as learnable physics engines for inference and controlcited by 242
  8. 2020Fast and Furious: Real Time End-to-End 3D Detection, Tracking and Motion Forecasting with a Single Convolutional Netcited by 228
  9. 2018Convolutional Social Pooling for Vehicle Trajectory Predictioncited by 221
  10. 2019PRECOG: PREdiction Conditioned On Goals in Visual Multi-Agent Settingscited by 178
  11. 2017Arbitrary-Oriented Scene Text Detection via Rotation Proposalscited by 176
  12. 2021IntentNet: Learning to Predict Intention from Raw Sensor Datacited by 158
  13. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  14. 2017Knowledge Transfer for Out-of-Knowledge-Base Entities: A Graph Neural Network Approachcited by 102
  15. 2020Amortized Causal Discovery: Learning to Infer Causal Graphs from Time-Series Datacited by 99
  16. 2019Learning representations of irregular particle-detector geometry with distance-weighted graph networkscited by 43
  17. 2019Graph Neural Networks for Modelling Traffic Participant Interactioncited by 42
  18. 2020GRIP: A Graph Neural Network Accelerator Architecturecited by 37
  19. 2017CAR-Net: Clairvoyant Attentive Recurrent Networkcited by 34
  20. 2020MultiXNet: Multiclass Multistage Multimodal Motion Predictioncited by 31
  21. 2018The Trajectron: Probabilistic Multi-Agent Trajectory Modeling With Dynamic Spatiotemporal Graphscited by 3
  22. 2020Temporally-Continuous Probabilistic Prediction using Polynomial Trajectory Parameterizationcited by 3

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 0; 2024: 0; 2025: 1.

2 papers.

  1. 2022Transferable and Adaptable Driving Behavior Predictioncited by 20
  2. 2025DG-STMTL: A Novel Graph Convolutional Network for Multi-Task Spatio-Temporal Traffic Forecastingcited by 0