mlsanityData to 7 Oct 2026

Track to Detect and Segment: An Online Multi-Object Tracker

arXiv 2103.08808 ↗First posted 16 Mar 2021cs.CVcited by 156

Not on the map. Why?

Abstract (arXiv)

Most online multi-object trackers perform object detection stand-alone in a neural net without any input from tracking. In this paper, we present a new online joint detection and tracking model, TraDeS (TRAck to DEtect and Segment), exploiting tracking clues to assist detection end-to-end. TraDeS infers object tracking offset by a cost volume, which is used to propagate previous object features for improving current object detection and segmentation. Effectiveness and superiority of TraDeS are shown on 4 datasets, including MOT (2D tracking), nuScenes (3D tracking), MOTS and Youtube-VIS (instance segmentation tracking). Project page: https://jialianwu.com/projects/TraDeS.html.

Key facts. Cited by 156 papers in the map (data through 7 Oct 2026). Builds on 53 of its 67 references that are in the map. First posted on arXiv 16 Mar 2021.

Builds on

53 of 67 references.

References · 53

  1. 2014Microsoft COCO: Common Objects in Contextcited by 17,498
  2. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  3. 2017Mask R-CNNcited by 7,259
  4. 2019nuScenes: A multimodal dataset for autonomous drivingcited by 4,485
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2018PointPillars: Fast Encoders for Object Detection from Point Cloudscited by 1,707
  7. 2017Deformable Convolutional Networkscited by 1,481
  8. 2019Objects as Pointscited by 1,172
  9. 2017PWC-Net: CNNs for Optical Flow Using Pyramid, Warping, and Cost Volumecited by 966
  10. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  11. 2016Simple Online and Realtime Trackingcited by 862
  12. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
38 more
  1. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  2. 2020FairMOT: On the Fairness of Detection and Re-Identification in Multiple Object Trackingcited by 489
  3. 2020Tracking Objects as Pointscited by 483
  4. 2017Deep Layer Aggregationcited by 436
  5. 2019Video Instance Segmentationcited by 391
  6. 2019Tracking without bells and whistlescited by 382
  7. 2020TransTrack: Multiple Object Tracking with Transformercited by 370
  8. 2020Conditional Convolutions for Instance Segmentationcited by 314
  9. 2019Towards Real-Time Multi-Object Trackingcited by 311
  10. 2019MOTS: Multi-Object Tracking and Segmentationcited by 222
  11. 2019Disentangling Monocular 3D Object Detectioncited by 215
  12. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  13. 2016Joint Detection and Identification Feature Learning for Person Searchcited by 190
  14. 2019FEELVOS: Fast End-to-End Embedding Learning for Video Object Segmentationcited by 178
  15. 2019Cost Volume Pyramid Based Depth Inference for Multi-View Stereocited by 154
  16. 2017Detect to Track and Track to Detectcited by 131
  17. 2019DPSNet: End-to-end Deep Plane Sweep Stereocited by 115
  18. 2020Chained-Tracker: Chaining Paired Attentive Regression Results for End-to-End Joint Multiple-Object Detection and Trackingcited by 115
  19. 2020GNN3DMOT: Graph Neural Network for 3D Multi-Object Tracking with Multi-Feature Learningcited by 113
  20. 2020SipMask: Spatial Information Preservation for Fast Image and Video Instance Segmentationcited by 108
  21. 2018Efficient Video Object Segmentation via Network Modulationcited by 98
  22. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  23. 2019Online Multi-Object Tracking with Dual Matching Attention Networkscited by 77
  24. 2016POI: Multiple Object Tracking with High Performance Detection and Appearance Featurecited by 74
  25. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
  26. 2020TubeTK: Adopting Tubes to Track Multi-Object in a One-Step Training Modelcited by 70
  27. 2020RetinaTrack: Online Single Stage Joint Detection and Trackingcited by 67
  28. 2017Accurate Optical Flow via Direct Cost Volume Processingcited by 66
  29. 2019Learning Spatial Fusion for Single-Shot Object Detectioncited by 59
  30. 2018Object Detection in Video with Spatiotemporal Sampling Networkscited by 57
  31. 2020Combining detection and tracking for human pose estimation in videoscited by 49
  32. 2017Recurrent Autoregressive Networks for Online Multi-Object Trackingcited by 48
  33. 2017Deep Network Flow for Multi-Object Trackingcited by 45
  34. 2018Person Search via A Mask-Guided Two-Stream CNN Modelcited by 44
  35. 2019Learning Temporal Pose Estimation from Sparsely-Labeled Videoscited by 39
  36. 2020Segment as Points for Efficient Online Multi-Object Tracking and Segmentationcited by 36
  37. 2016Full Flow: Optical Flow Estimation By Global Optimization over Regular Gridscited by 34
  38. 2020A Unified Object Motion and Affinity Model for Online Multi-Object Trackingcited by 33

50 most cited of 53 All 53 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 12; 2022: 44; 2023: 40; 2024: 33; 2025: 10; 2026: 17.

156 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2021MOTR: End-to-End Multiple-Object Tracking with Transformercited by 379
  3. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  4. 2022BoT-SORT: Robust Associations Multi-Pedestrian Trackingcited by 313
  5. 2021DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motioncited by 213
  6. 2022StrongSORT: Make DeepSORT Great Againcited by 213
  7. 2022MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectorscited by 148
  8. 2021A Survey on Deep Learning Technique for Video Segmentationcited by 132
  9. 2023Deep OC-SORT: Multi-Pedestrian Tracking by Adaptive Re-Identificationcited by 130
  10. 2023SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenescited by 130
  11. 2022MeMOT: Multi-Object Tracking with Memorycited by 113
  12. 2022Global Tracking Transformerscited by 110
38 more
  1. 2022Towards Grand Unification of Object Trackingcited by 93
  2. 2023MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Trackingcited by 86
  3. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  4. 2021Do Different Tracking Tasks Require Different Appearance Models?cited by 62
  5. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  6. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  7. 2024DiffMOT: A Real-time Diffusion-based Multiple Object Tracker with Non-linear Predictioncited by 59
  8. 2024Multiple Object Tracking as ID Predictioncited by 58
  9. 2023SparseTrack: Multi-Object Tracking by Performing Scene Decomposition based on Pseudo-Depthcited by 48
  10. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
  11. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  12. 2022Efficient Video Instance Segmentation via Tracklet Query and Proposalcited by 33
  13. 2022Towards Discriminative Representation: Multi-view Trajectory Contrastive Learning for Online Multi-object Trackingcited by 33
  14. 2022SMILEtrack: SiMIlarity LEarning for Occlusion-Aware Multiple Object Trackingcited by 29
  15. 2022Quo Vadis: Is Trajectory Forecasting the Key Towards Long-Term Multi-Object Tracking?cited by 28
  16. 2021One More Check: Making "Fake Background" Be Tracked Againcited by 25
  17. 2023Focus On Details: Online Multi-object Tracking with Diverse Fine-grained Representationcited by 25
  18. 2023Type-to-Track: Retrieve Any Object via Prompt-based Trackingcited by 24
  19. 2021Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformerscited by 21
  20. 2023TOPIC: A Parallel Association Paradigm for Multi-Object Tracking under Complex Motions and Diverse Scenescited by 21
  21. 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
  22. 2023Mask-Free Video Instance Segmentationcited by 20
  23. 2023Bridging the Gap Between End-to-end and Non-End-to-end Multi-Object Trackingcited by 20
  24. 2023MotionTrack: Learning Motion Predictor for Multiple Object Trackingcited by 20
  25. 2024Samba: Synchronized Set-of-Sequences Modeling for Multiple Object Trackingcited by 20
  26. 2023OmniTracker: Unifying Object Tracking by Tracking-with-Detectioncited by 19
  27. 2022Region Aware Video Object Segmentation with Deep Motion Modelingcited by 18
  28. 2023TCOVIS: Temporally Consistent Online Video Instance Segmentationcited by 18
  29. 2024MambaTrack: A Simple Baseline for Multiple Object Tracking with State Space Modelcited by 18
  30. 2023DIVOTrack: A Novel Dataset and Baseline Method for Cross-View Multi-Object Tracking in DIVerse Open Scenescited by 17
  31. 2025SAM2MOT: A Novel Paradigm of Multi-Object Tracking by Segmentationcited by 17
  32. 2022Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimationcited by 16
  33. 2022Generalizing Multiple Object Tracking to Unseen Domains by Introducing Natural Language Representationcited by 16
  34. 2022Detection Recovery in Online Multi-Object Tracking with Sparse Graph Trackercited by 15
  35. 2023Living Scenes: Multi-object Relocalization and Reconstruction in Changing 3D Environmentscited by 15
  36. 2024RingMo-Aerial: An Aerial Remote Sensing Foundation Model With Affine Transformation Contrastive Learningcited by 15
  37. 2022STC: Spatio-Temporal Contrastive Learning for Video Instance Segmentationcited by 13
  38. 2023TrackFlow: Multi-Object Tracking with Normalizing Flowscited by 13

50 most cited of 156 All 156 (JSON)