mlsanityData to 14 Oct 2026

S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations

arXiv 2306.17602 ↗First posted 30 Jun 2023cs.CV cs.AI cs.ROcited by 12

Not on the map. Why?

Abstract (arXiv)

Following the tracking-by-attention paradigm, this paper introduces an object-centric, transformer-based framework for tracking in 3D. Traditional model-based tracking approaches incorporate the geometric effect of object- and ego motion between frames with a geometric motion model. Inspired by this, we propose S.T.A.R.-Track, which uses a novel latent motion model (LMM) to additionally adjust object queries to account for changes in viewing direction and lighting conditions directly in the latent space, while still modeling the geometric motion explicitly. Combined with a novel learnable track embedding that aids in modeling the existence probability of tracks, this results in a generic tracking framework that can be integrated with any query-based detector. Extensive experiments on the nuScenes benchmark demonstrate the benefits of our approach, showing state-of-the-art performance for DETR3D-based trackers while drastically reducing the number of identity switches of tracks at the same time.

Key facts. Cited by 12 papers in the map (data through 14 Oct 2026). Builds on 39 of its 53 references that are in the map. First posted on arXiv 30 Jun 2023.

Builds on

39 of 53 references.

References · 39

  1. 2017Attention Is All You Needcited by 60,361
  2. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  3. 2014Microsoft COCO: Common Objects in Contextcited by 17,608
  4. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,639
  5. 2020End-to-End Object Detection with Transformerscited by 7,414
  6. 2016Feature Pyramid Networks for Object Detectioncited by 5,036
  7. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,523
  8. 2020Deformable DETR: Deformable Transformers for End-to-End Object Detectioncited by 3,422
  9. 2022BEVFormer: Learning Bird's-Eye-View Representation from Multi-Camera Images via Spatiotemporal Transformerscited by 1,218
  10. 2018On the Continuity of Rotation Representations in Neural Networkscited by 1,214
  11. 2020Center-based 3D Object Detection and Trackingcited by 1,144
  12. 2016HyperNetworkscited by 1,027
27 more
  1. 2022BEVFusion: Multi-Task Multi-Sensor Fusion with Unified Bird's-Eye View Representationcited by 850
  2. 2021DETR3D: 3D Object Detection from Multi-view Images via 3D-to-2D Queriescited by 658
  3. 2022PETR: Position Embedding Transformation for Multi-View 3D Object Detectioncited by 552
  4. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 518
  5. 2022TransFusion: Robust LiDAR-Camera Fusion for 3D Object Detection with Transformerscited by 466
  6. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 381
  7. 2020TransTrack: Multiple Object Tracking with Transformercited by 371
  8. 2022PETRv2: A Unified Framework for 3D Perception from Multi-Camera Imagescited by 352
  9. 2023Exploring Object-Centric Temporal Modeling for Efficient Multi-View 3D Object Detectioncited by 315
  10. 2020Quasi-Dense Similarity Learning for Multiple Object Trackingcited by 220
  11. 2022Unifying Voxel-based Representation with Transformer for 3D Object Detectioncited by 202
  12. 2014Multiple Object Tracking: A Literature Reviewcited by 166
  13. 2019An Energy and GPU-Computation Efficient Backbone Network for Real-Time Object Detectioncited by 163
  14. 2022DETRs with Hybrid Matchingcited by 150
  15. 2019Self-Driving Cars: A Surveycited by 148
  16. 2022ViP3D: End-to-end Visual Trajectory Prediction via 3D Agent Queriescited by 117
  17. 2019Deep Learning in Video Multi-Object Tracking: A Surveycited by 107
  18. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 103
  19. 2022MUTR3D: A Multi-camera Tracking Framework via 3D-to-2D Queriescited by 91
  20. 2018Features for Multi-Target Multi-Camera Tracking and Re-Identificationcited by 88
  21. 2023Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Trackingcited by 54
  22. 2022DiffStack: A Differentiable and Modular Control Stack for Autonomous Vehiclescited by 37
  23. 2022CC-3DT: Panoramic 3D Object Tracking via Cross-Camera Fusioncited by 31
  24. 2022Group DETR v2: Strong Object Detector with Encoder-Decoder Pretrainingcited by 25
  25. 2022Focal-PETR: Embracing Foreground for Efficient Multi-Camera 3D Object Detectioncited by 19
  26. 2022Transformers for Multi-Object Tracking on Point Cloudscited by 14
  27. 2022Li3DeTr: A LiDAR based 3D Detection Transformercited by 11

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2024: 3; 2025: 5; 2026: 4.

12 papers.

  1. 2024ADA-Track++: End-to-End Multi-Camera 3D Multi-Object Tracking with Alternating Detection and Associationcited by 33
  2. 2024DualAD: Disentangling the Dynamic and Static World for End-to-End Drivingcited by 17
  3. 2025CoopTrack: Exploring End-to-End Learning for Efficient Cooperative Sequential Perceptioncited by 12
  4. 2025TQD-Track: Temporal Query Denoising for 3D Multi-Object Trackingcited by 4
  5. 2025Inverse++: Vision-Centric 3D Semantic Occupancy Prediction Assisted with 3D Object Detectioncited by 4
  6. 2025Rethinking the Spatio-Temporal Alignment of End-to-End 3D Perceptioncited by 3
  7. 2024SynCL: A Synergistic Training Strategy with Instance-Aware Contrastive Learning for End-to-End Multi-Camera 3D Trackingcited by 2
  8. 2026Offline-Poly: A Polyhedral Framework For Offline 3D Multi-Object Trackingcited by 2
  9. 2026SCATR: Mitigating New Instance Suppression in LiDAR-based Tracking-by-Attention via Second Chance Assignment and Track Query Dropoutcited by 2
  10. 2025To New Beginnings: A Survey of Unified Perception in Autonomous Vehicle Softwarecited by 1
  11. 2026Fusion-Poly: A Polyhedral Framework Based on Spatial-Temporal Fusion for 3D Multi-Object Trackingcited by 1
  12. 2026GraphBEV++: Multi-Modal Feature Alignment for Autonomous Drivingcited by 0