mlsanityData to 7 Oct 2026

Exploiting Temporal Relations on Radar Perception for Autonomous Driving

arXiv 2204.01184 ↗First posted 3 Apr 2022cs.CVcited by 22

Not on the map. Why?

Abstract (arXiv)

We consider the object recognition problem in autonomous driving using automotive radar sensors. Comparing to Lidar sensors, radar is cost-effective and robust in all-weather conditions for perception in autonomous driving. However, radar signals suffer from low angular resolution and precision in recognizing surrounding objects. To enhance the capacity of automotive radar, in this work, we exploit the temporal information from successive ego-centric bird-eye-view radar image frames for radar object recognition. We leverage the consistency of an object's existence and attributes (size, orientation, etc.), and propose a temporal relational layer to explicitly model the relations between objects within successive radar images. In both object detection and multiple object tracking, we show the superiority of our method compared to several baseline approaches.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Builds on 29 of its 48 references that are in the map. First posted on arXiv 3 Apr 2022.

Builds on

29 of 48 references.

References · 29

  1. 2017Attention Is All You Needcited by 59,932
  2. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  3. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  4. 2019EfficientNet: Rethinking Model Scaling for Convolutional Neural Networkscited by 6,415
  5. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  6. 2019Objects as Pointscited by 1,172
  7. 2020Center-based 3D Object Detection and Trackingcited by 1,143
  8. 2017Focal Loss for Dense Object Detectioncited by 749
  9. 2017DOTA: A Large-scale Dataset for Object Detection in Aerial Imagescited by 622
  10. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  11. 2017Rethinking Spatiotemporal Feature Learning: Speed-Accuracy Trade-offs in Video Classificationcited by 521
  12. 2020Tracking Objects as Pointscited by 483
17 more
  1. 2021Attention is Not All You Need: Pure Attention Loses Rank Doubly Exponentially with Depthcited by 411
  2. 2019A Survey of Autonomous Driving: Common Practices and Emerging Technologiescited by 373
  3. 2018Long-Term Feature Banks for Detailed Video Understandingcited by 239
  4. 2016Deep Feature Flow for Video Recognitioncited by 186
  5. 2017Flow-Guided Feature Aggregation for Video Object Detectioncited by 177
  6. 2019The Oxford Radar RobotCar Dataset: A Radar Extension to the Oxford RobotCar Datasetcited by 133
  7. 2017Detect to Track and Track to Detectcited by 131
  8. 2021SelfDoc: Self-Supervised Document Representation Learningcited by 117
  9. 2020RADIATE: A Radar Dataset for Automotive Perception in Bad Weathercited by 98
  10. 2020Oriented Object Detection in Aerial Images with Box Boundary-Aware Vectorscited by 63
  11. 2021RadarScenes: A Real-World Radar Point Cloud Data Set for Automotive Applicationscited by 61
  12. 2020CARRADA Dataset: Camera and Automotive Radar with Range-Angle-Doppler Annotationscited by 60
  13. 2020RadarNet: Exploiting Radar for Robust Perception of Dynamic Objectscited by 48
  14. 2017Deep Network Flow for Multi-Object Trackingcited by 45
  15. 2019Context R-CNN: Long Term Temporal Context for Per-Camera Object Detectioncited by 45
  16. 2021Rethinking of Radar's Role: A Camera-Radar Dataset and Systematic Annotator via Coordinate Alignmentcited by 23
  17. 2019Graph Neural Based End-to-end Data Association Framework for Online Multiple-Object Trackingcited by 15

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 7; 2024: 7; 2025: 2; 2026: 3.

22 papers.

Sort:

  1. 2022Simple-BEV: What Really Matters for Multi-Sensor BEV Perception?cited by 128
  2. 2024RCBEVDet: Radar-camera Fusion in Bird's Eye View for 3D Object Detectioncited by 82
  3. 2023Radar-Camera Fusion for Object Detection and Semantic Segmentation in Autonomous Driving: A Comprehensive Reviewcited by 57
  4. 2023SMURF: Spatial Multi-Representation Fusion for 3D Object Detection with 4D Imaging Radarcited by 48
  5. 2023ProxyFormer: Proxy Alignment Assisted Point Cloud Completion with Missing Part Sensitive Transformercited by 43
  6. 2023Less is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentationcited by 33
  7. 2022RaLiBEV: Radar and LiDAR BEV Fusion Learning for Anchor Box Free Object Detection Systemscited by 23
  8. 2024DART: Implicit Doppler Tomography for Radar Novel View Synthesiscited by 19
  9. 2023ADCNet: Learning from Raw Radar Data via Distillationcited by 14
  10. 2024RCBEVDet++: Toward High-accuracy Radar-Camera Fusion 3D Perception Networkcited by 11
  11. 2024MMVR: Millimeter-wave Multi-View Radar Dataset and Benchmark for Indoor Perceptioncited by 10
  12. 2022A recurrent CNN for online object detection on raw radar framescited by 9
10 more
  1. 2024RETR: Multi-View Radar Detection Transformer for Indoor Perceptioncited by 6
  2. 2024SparseRadNet: Sparse Perception Neural Network on Subsampled Radar Datacited by 5
  3. 2024SIRA: Scalable Inter-frame Relation and Association for Radar Perceptioncited by 4
  4. 2025AttentiveGRU: Recurrent Spatio-Temporal Modeling for Advanced Radar-Based BEV Object Detectioncited by 3
  5. 2023Radar-Lidar Fusion for Object Detection by Designing Effective Convolution Networkscited by 0
  6. 2023Towards Transferable Multi-modal Perception Representation Learning for Autonomy: NeRF-Supervised Masked AutoEncodercited by 0
  7. 2025Graph Query Networks for Object Detection with Automotive Radarcited by 0
  8. 2026RAVEN: Radar Adaptive Vision Encoders for Efficient Chirp-wise Object Detection and Segmentationcited by 0
  9. 2026ATN3D: Density-Aware LiDAR-Radar Early 3D Object Detection Under Extreme Sparsitycited by 0
  10. 2026Do Spinning Radar Doppler Velocity Measurements Improve Vehicle Detection and Tracking?cited by 0