mlsanityData to 14 Oct 2026

Spatio-Temporal Scene-Graph Embedding for Autonomous Vehicle Collision Prediction

arXiv 2111.06123 ↗First posted 11 Nov 2021cs.CVcited by 29

Not on the map. Why?

Abstract (arXiv)

In autonomous vehicles (AVs), early warning systems rely on collision prediction to ensure occupant safety. However, state-of-the-art methods using deep convolutional networks either fail at modeling collisions or are too expensive/slow, making them less suitable for deployment on AV edge hardware. To address these limitations, we propose sg2vec, a spatio-temporal scene-graph embedding methodology that uses Graph Neural Network (GNN) and Long Short-Term Memory (LSTM) layers to predict future collisions via visual scene perception. We demonstrate that sg2vec predicts collisions 8.11% more accurately and 39.07% earlier than the state-of-the-art method on synthesized datasets, and 29.47% more accurately on a challenging real-world collision dataset. We also show that sg2vec is better than the state-of-the-art at transferring knowledge from synthetic datasets to real-world driving datasets. Finally, we demonstrate that sg2vec performs inference 9.3x faster with an 88.0% smaller model, 32.4% less power, and 92.8% less energy than the state-of-the-art method on the industry-standard Nvidia DRIVE PX 2 platform, making it more suitable for implementation on the edge.

Key facts. Cited by 29 papers in the map (data through 14 Oct 2026). Builds on 16 of its 44 references that are in the map. First posted on arXiv 11 Nov 2021.

Builds on

16 of 44 references.

References · 16

  1. 2017Mask R-CNNcited by 7,277
  2. 2017CARLA: An Open Urban Driving Simulatorcited by 2,449
  3. 2017Modeling Relational Data with Graph Convolutional Networkscited by 1,694
  4. 2018Relational inductive biases, deep learning, and graph networkscited by 1,360
  5. 2017Scene Graph Generation by Iterative Message Passingcited by 462
  6. 2019Self-Attention Graph Poolingcited by 421
  7. 2018Graph R-CNN for Scene Graph Generationcited by 298
  8. 2017On a Formal Model of Safe and Scalable Self-driving Carscited by 131
  9. 2018Toward Driving Scene Understanding: A Dataset for Learning Driver Behavior and Causal Reasoningcited by 102
  10. 2020Scene-Graph Augmented Data-Driven Risk Assessment of Autonomous Vehicle Decisionscited by 34
  11. 2020When, Where, and What? A New Dataset for Anomaly Detection in Driving Videoscited by 27
  12. 2019Learning 3D-aware Egocentric Spatial-Temporal Interaction via Graph Convolutional Networkscited by 22
4 more
  1. 2017Deep Predictive Models for Collision Risk Assessment in Autonomous Drivingcited by 15
  2. 2020Understanding Dynamic Scenes using Graph Convolution Networkscited by 10
  3. 2020Towards Accurate Vehicle Behaviour Classification With Multi-Relational Graph Convolutional Networkscited by 8
  4. 2020Opportunistic Intermittent Control with Safety Guarantees for Autonomous Systemscited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2022: 3; 2023: 9; 2024: 5; 2025: 9; 2026: 3.

29 papers.

Sort:

By area:

  1. 2023Graph-based Topology Reasoning for Driving Scenescited by 54
  2. 2024Advancing Video Anomaly Detection: A Concise Review and a New Datasetcited by 49
  3. 2024Abductive Ego-View Accident Video Understanding for Safe Driving Perceptioncited by 43
  4. 2023Vision-Based Traffic Accident Detection and Anticipation: A Surveycited by 31
  5. 2022Behavioral Intention Prediction in Driving Scenes: A Surveycited by 30
  6. 2025Nexar Dashcam Collision Prediction Dataset and Challengecited by 21
  7. 2023RS2G: Data-Driven Scene-Graph Extraction and Embedding for Robust Autonomous Perception and Scenario Understandingcited by 17
  8. 2022Cognitive Accident Prediction in Driving Scenes: A Multimodality Benchmarkcited by 16
  9. 2022Spatial-Temporal-Aware Safe Multi-Agent Reinforcement Learning of Connected Autonomous Vehicles in Challenging Scenarioscited by 13
  10. 2023Survey on video anomaly detection in dynamic scenes with moving camerascited by 10
  11. 2024Enhancing Vision-Language Models with Scene Graphs for Traffic Accident Understandingcited by 10
  12. 2023Explainable Action Prediction through Self-Supervision on Scene Graphscited by 9
17 more
  1. 2023MaGNAS: A Mapping-Aware Graph Neural Architecture Search Framework for Heterogeneous MPSoC Deploymentcited by 9
  2. 2025World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Drivingcited by 8
  3. 2025GraphPilot: Grounded Scene Graph Conditioning for Language-Based Autonomous Drivingcited by 7
  4. 2025AI2-Active Safety: AI-enabled Interaction-aware Active Safety Analysis with Vehicle Dynamicscited by 6
  5. 2025BADAS: Context Aware Collision Prediction Using Real-World Dashcam Datacited by 4
  6. 2023Interpretable End-to-End Driving Model for Implicit Scene Understandingcited by 2
  7. 2025Deep Learning Advances in Vision-Based Traffic Accident Anticipation: A Comprehensive Review of Methods, Datasets, and Future Directionscited by 1
  8. 2025What Demands Attention in Urban Street Scenes? From Scene Understanding towards Road Safety: A Survey of Vision-driven Datasets and Studiescited by 1
  9. 2025STAGNet: A Spatio-Temporal Graph and LSTM Framework for Accident Anticipationcited by 1
  10. 2026VAGNet: Vision-based Accident Anticipation with Global Featurescited by 1
  11. 2023Recent Advances in Graph-based Machine Learning for Applications in Smart Urban Transportation Systemscited by 0
  12. 2023STDG: Semi-Teacher-Student Training Paradigram for Depth-guided One-stage Scene Graph Generationcited by 0
  13. 2024Collision Probability Distribution Estimation via Temporal Difference Learningcited by 0
  14. 2024A transition towards virtual representations of visual scenescited by 0
  15. 2025MsFIN: Multi-scale Feature Interaction Network for Traffic Accident Anticipationcited by 0
  16. 2026FLaRA: Predicting Future Latent Representations for Accident Anticipationcited by 0
  17. 2026hia-gat: A Heterogeneous Interaction-Aware Graph Attention Network For Frame-Level Traffic Conflict Risk Prediction On Freewayscited by 0