mlsanityData to 7 Oct 2026

Online Multi-Target Tracking Using Recurrent Neural Networks

arXiv 1604.03635 ↗First posted 13 Apr 2016cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

We present a novel approach to online multi-target tracking based on recurrent neural networks (RNNs). Tracking multiple objects in real-world scenes involves many challenges, including a) an a-priori unknown and time-varying number of targets, b) a continuous state estimation of all present targets, and c) a discrete combinatorial problem of data association. Most previous methods involve complex models that require tedious tuning of parameters. Here, we propose for the first time, an end-to-end learning approach for online multi-target tracking. Existing deep learning methods are not designed for the above challenges and cannot be trivially applied to the task. Our solution addresses all of the above points in a principled way. Experiments on both synthetic and real data show promising results obtained at ~300 Hz on a standard CPU, and pave the way towards future research in this direction.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 13 Apr 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 19; 2023: 8; 2024: 7; 2025: 9; 2026: 2.

59 papers.

Sort:

  1. 2021Learning to Track with Object Permanencecited by 117
  2. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  3. 2022Hard to Track Objects with Irregular Motions and Similar Appearances? Make It Easier by Buffering the Matching Spacecited by 66
  4. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  5. 2022QDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Trackingcited by 61
  6. 2023OVTrack: Open-Vocabulary Multiple Object Trackingcited by 53
  7. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  8. 2022Tracking Every Thing in the Wildcited by 44
  9. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  10. 2021Deep Learning for UAV-based Object Detection and Tracking: A Surveycited by 33
  11. 2021Discriminative Appearance Modeling with Multi-track Pooling for Real-time Multi-object Trackingcited by 22
  12. 2023MotionTrack: Learning Motion Predictor for Multiple Object Trackingcited by 20
38 more
  1. 2021Split and Connect: A Universal Tracklet Booster for Multi-Object Trackingcited by 17
  2. 2023FOLT: Fast Multiple Object Tracking from UAV-captured Videos Based on Optical Flowcited by 15
  3. 2021Online Multiple Object Tracking with Cross-Task Synergycited by 12
  4. 2022In Pursuit of Many: A Review of Modern Multiple Object Tracking Systemscited by 12
  5. 2022Learning of Global Objective for Network Flow in Multi-Object Trackingcited by 11
  6. 2023Milestones in Autonomous Driving and Intelligent Vehicles Part II: Perception and Planningcited by 9
  7. 2024ETTrack: Enhanced Temporal Motion Predictor for Multi-Object Trackingcited by 9
  8. 2021Multiple Object Tracking with Mixture Density Networks for Trajectory Estimationcited by 8
  9. 2022Trajectory Forecasting from Detection with Uncertainty-Aware Motion Encodingcited by 8
  10. 2022Scenario-Assisted Deep Reinforcement Learningcited by 8
  11. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  12. 2021Safety-Oriented Pedestrian Motion and Scene Occupancy Forecastingcited by 6
  13. 2022Towards Frame Rate Agnostic Multi-Object Trackingcited by 6
  14. 2022Bridging Images and Videos: A Simple Learning Framework for Large Vocabulary Video Object Detectioncited by 6
  15. 2022Can Deep Learning be Applied to Model-Based Multi-Object Tracking?cited by 5
  16. 2024Deep Learning-Based Robust Multi-Object Tracking via Fusion of mmWave Radar and Camera Sensorscited by 5
  17. 2021Simple online and real-time tracking with occlusion handlingcited by 4
  18. 2023Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothingcited by 3
  19. 2025Bayesian Multiobject Tracking With Neural-Enhanced Motion and Measurement Modelscited by 3
  20. 2025NOOUGAT: Towards Unified Online and Offline Multi-Object Trackingcited by 3
  21. 2025One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Trackingcited by 2
  22. 2021Vehicle Detection and Tracking From Surveillance Cameras in Urban Scenescited by 1
  23. 2022Spatial-Temporal Map Vehicle Trajectory Detection Using Dynamic Mode Decomposition and Res-UNet+ Neural Networkscited by 1
  24. 2022Strong-TransCenter: Improved Multi-Object Tracking based on Transformers with Dense Representationscited by 1
  25. 2022Graph-Based Multi-Camera Soccer Player Trackercited by 1
  26. 2022Joint Counting, Detection and Re-Identification for Multi-Object Trackingcited by 1
  27. 2023Fast and Resource-Efficient Object Tracking on Edge Devices: A Measurement Studycited by 1
  28. 2023Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separationcited by 1
  29. 2024MAML MOT: Multiple Object Tracking based on Meta-Learningcited by 1
  30. 2024OCTrack: Benchmarking the Open-Corpus Multi-Object Trackingcited by 1
  31. 2025Tiny Neural Networks for Multi-Object Tracking in a Modular Kalman Frameworkcited by 1
  32. 2025A New Perspective On AI Safety Through Control Theory Methodologiescited by 1
  33. 2021Finding a Needle in a Haystack: Tiny Flying Object Detection in 4K Videos using a Joint Detection-and-Tracking Approachcited by 0
  34. 2021A Pedestrian Detection and Tracking Framework for Autonomous Cars: Efficient Fusion of Camera and LiDAR Datacited by 0
  35. 2021Multi-target tracking for video surveillance using deep affinity network: a brief reviewcited by 0
  36. 2022Unsupervised Multiple-Object Tracking with a Dynamical Variational Autoencodercited by 0
  37. 2022Sparse Message Passing Network with Feature Integration for Online Multiple Object Trackingcited by 0
  38. 2023Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of Sensor Data over Timecited by 0

50 most cited of 59 All 59 (JSON)