mlsanityData to 7 Oct 2026

RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understanding

arXiv 2304.08600 ↗First posted 17 Apr 2023cs.CV cs.LGcited by 17

Not on the map. Why?

Abstract (arXiv)

Effectively capturing intricate interactions among road users is of critical importance to achieving safe navigation for autonomous vehicles. While graph learning (GL) has emerged as a promising approach to tackle this challenge, existing GL models rely on predefined domain-specific graph extraction rules that often fail in real-world drastically changing scenarios. Additionally, these graph extraction rules severely impede the capability of existing GL methods to generalize knowledge across domains. To address this issue, we propose RoadScene2Graph (RS2G), an innovative autonomous scenario understanding framework with a novel data-driven graph extraction and modeling approach that dynamically captures the diverse relations among road users. Our evaluations demonstrate that on average RS2G outperforms the state-of-the-art (SOTA) rule-based graph extraction method by 4.47% and the SOTA deep learning model by 22.19% in subjective risk assessment. More importantly, RS2G delivers notably better performance in transferring knowledge gained from simulation environments to unseen real-world scenarios.

Key facts. Cited by 17 papers in the map (data through 7 Oct 2026). Builds on 43 of its 70 references that are in the map. First posted on arXiv 17 Apr 2023.

Builds on

43 of 70 references.

References · 43

  1. 2017Attention Is All You Needcited by 59,932
  2. 2016Semi-Supervised Classification with Graph Convolutional Networkscited by 11,282
  3. 2018How Powerful are Graph Neural Networks?cited by 4,355
  4. 2017CARLA: An Open Urban Driving Simulatorcited by 2,431
  5. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,684
  6. 2018Relational inductive biases, deep learning, and graph networkscited by 1,341
  7. 2019A Comprehensive Survey on Transfer Learningcited by 1,154
  8. 2022Planning-oriented Autonomous Drivingcited by 1,068
  9. 2019Graph Transformer Networkscited by 520
  10. 2019Self-Attention Graph Poolingcited by 421
  11. 2019Exploring the Limitations of Behavior Cloning for Autonomous Drivingcited by 343
  12. 2018Graph R-CNN for Scene Graph Generationcited by 296
31 more
  1. 2022Safety-Enhanced Autonomous Driving Using Interpretable Sensor Fusion Transformercited by 211
  2. 2018Event-based Vision meets Deep Learning on Steering Prediction for Self-driving Carscited by 197
  3. 2021Multimodal Trajectory Prediction Conditioned on Lane-Graph Traversalscited by 112
  4. 2019Gaussian YOLOv3: An Accurate and Fast Object Detector Using Localization Uncertainty for Autonomous Drivingcited by 105
  5. 2019Spatially-Aware Graph Neural Networks for Relational Behavior Forecasting from Sensor Datacited by 104
  6. 2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102
  7. 2018Uncertainty-aware Short-term Motion Prediction of Traffic Actors for Autonomous Drivingcited by 90
  8. 2022On Adversarial Robustness of Trajectory Prediction for Autonomous Vehiclescited by 89
  9. 2020A Causal View on Robustness of Neural Networkscited by 53
  10. 2021Measuring Robustness in Deep Learning Based Compressive Sensingcited by 53
  11. 2023Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Drivingcited by 37
  12. 2020Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisionscited by 34
  13. 2020Shared Cross-Modal Trajectory Prediction for Autonomous Drivingcited by 31
  14. 2021Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Predictioncited by 29
  15. 2020When, Where, and What? A New Dataset for Anomaly Detection in Driving Videoscited by 27
  16. 2019Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networkscited by 22
  17. 2020Universal-RCNN: Universal Object Detector via Transferable Graph R-CNNcited by 18
  18. 2020RTS3D: Real-time Stereo 3D Detection from 4D Feature-Consistency Embedding Space for Autonomous Drivingcited by 16
  19. 2017Deep Predictive Models for Collision Risk Assessment in Autonomous Drivingcited by 15
  20. 2021roadscene2vec: A Tool for Extracting and Embedding Road Scene-Graphscited by 15
  21. 2022EcoFusion: Energy-Aware Adaptive Sensor Fusion for Efficient Autonomous Vehicle Perceptioncited by 13
  22. 2020Road Scene Graph: A Semantic Graph-Based Scene Representation Dataset for Intelligent Vehiclescited by 12
  23. 2020Understanding Dynamic Scenes using Graph Convolution Networkscited by 10
  24. 2019Pykg2vec: A Python Library for Knowledge Graph Embeddingcited by 9
  25. 2023Explainable Action Prediction through Self-Supervision on Scene Graphscited by 9
  26. 2020Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networkscited by 8
  27. 2021SAGE: A Split-Architecture Methodology for Efficient End-to-End Autonomous Vehicle Controlcited by 8
  28. 2023Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Drivingcited by 8
  29. 2019Risky Action Recognition in Lane Change Video Clips using Deep Spatiotemporal Networks with Segmentation Mask Transfercited by 6
  30. 2021Improving Generalization of Transfer Learning Across Domains Using Spatio-Temporal Features in Autonomous Drivingcited by 5
  31. 2020Vehicle Trajectory Prediction by Transfer Learning of Semi-Supervised Modelscited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 2; 2025: 10; 2026: 5.

17 papers.

Sort:

By area:

  1. 2025Universal Scene Graph Generationcited by 11
  2. 2025Learning 4D Panoptic Scene Graph Generation from Rich 2D Visual Scenecited by 6
  3. 2025Hyperdimensional Uncertainty Quantification for Multimodal Uncertainty Fusion in Autonomous Vehicles Perceptioncited by 6
  4. 2025GraphPilot: Grounded Scene Graph Conditioning for Language-Based Autonomous Drivingcited by 6
  5. 2025Spatial Retrieval Augmented Autonomous Drivingcited by 5
  6. 2024SMORE: Similarity-based Hyperdimensional Domain Adaptation for Multi-Sensor Time Series Classificationcited by 3
  7. 2025Driving-RAG: Driving Scenarios Embedding, Search, and RAG Applicationscited by 3
  8. 2025Robo-SGG: Exploiting Layout-Oriented Normalization and Restitution Can Improve Robust Scene Graph Generationcited by 3
  9. 2025Simplifying Traffic Anomaly Detection with Video Foundation Modelscited by 3
  10. 2026DRIVESPATIAL: A Benchmark for Spatiotemporal Intelligence in VLMs for Autonomous Drivingcited by 2
  11. 2024Transformer-Based Contrastive Meta-Learning For Low-Resource Generalizable Activity Recognitioncited by 1
  12. 2025UNO: Unifying One-stage Video Scene Graph Generation via Object-Centric Visual Representation Learningcited by 1
5 more
  1. 2025Measuring What Matters: Scenario-Driven Evaluation for Trajectory Predictors in Autonomous Drivingcited by 0
  2. 2026CURVE: Learning Causality-Inspired Invariant Representations for Robust Scene Understanding via Uncertainty-Guided Regularizationcited by 0
  3. 2026Modeling Scientific Experiment Scenes: Dataset and Modelcited by 0
  4. 2026CRUISE: Vision-Language Model-Guided Uncertainty-Aware Cross-Modal Sensor Fusion for Robust Autonomous Drivingcited by 0
  5. 2026Combining Hierarchical Cognitive Process with Process Supervision for Interpretable Scene Safety Understandingcited by 0