Deep Learning in Video Multi-Object Tracking: A Survey
Not on the map. Why?
Abstract (arXiv)
The problem of Multiple Object Tracking (MOT) consists in following the trajectory of different objects in a sequence, usually a video. In recent years, with the rise of Deep Learning, the algorithms that provide a solution to this problem have benefited from the representational power of deep models. This paper provides a comprehensive survey on works that employ Deep Learning models to solve the task of MOT on single-camera videos. Four main steps in MOT algorithms are identified, and an in-depth review of how Deep Learning was employed in each one of these stages is presented. A complete experimental comparison of the presented works on the three MOTChallenge datasets is also provided, identifying a number of similarities among the top-performing methods and presenting some possible future research directions.
Key facts. Cited by 107 papers in the map (data through 14 Oct 2026). First posted on arXiv 18 Jul 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 24; 2022: 25; 2023: 23; 2024: 11; 2025: 21; 2026: 3.
107 papers.
Sort:
By area:
- 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
- 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
- 2021DEFT: Detection Embeddings for Trackingcited by 56
- 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
- 2021A Survey of Sound Source Localization with Deep Learning Methodscited by 46
- 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
- 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
- 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
- 2023Learning Object State Changes in Videos: An Open-World Perspectivecited by 36
- 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
- 2022Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractorcited by 27
- 2021Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmarkcited by 25
38 more
- 2021Regular Polytope Networkscited by 24
- 2021Near-field Perception for Low-Speed Vehicle Automation using Surround-view Fisheye Camerascited by 24
- 2022The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Countingcited by 24
- 2023RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloudcited by 21
- 2022Global Instance Tracking: Locating Target More Like Humanscited by 18
- 2023Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AIcited by 17
- 2022EmbedTrack -- Simultaneous Cell Segmentation and Tracking Through Learning Offsets and Clustering Bandwidthscited by 16
- 2021Tracking People by Predicting 3D Appearance, Location & Posecited by 15
- 2022Transformers for Multi-Object Tracking on Point Cloudscited by 14
- 2023S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representationscited by 12
- 2022Visual Adversarial Attacks and Defenses in the Physical World: A Surveycited by 11
- 2022SOTVerse: A User-defined Task Space of Single Object Trackingcited by 10
- 2023Transformers in Single Object Tracking: An Experimental Surveycited by 10
- 2024Computer Vision for Primate Behavior Analysis in the Wildcited by 10
- 2022A Region-Based Deep Learning Approach to Automated Retail Checkoutcited by 9
- 2023Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Datacited by 9
- 2021Online Clustering-based Multi-Camera Vehicle Tracking in Scenarios with overlapping FOVscited by 8
- 2022Towards PAC Multi-Object Detection and Trackingcited by 8
- 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
- 2021CFTrack: Center-based Radar and Camera Fusion for 3D Multi-Object Trackingcited by 7
- 2022Edge Video Analytics: A Survey on Applications, Systems and Enabling Techniquescited by 7
- 2022Multi-view Tracking, Re-ID, and Social Network Analysis of a Flock of Visually Similar Birds in an Outdoor Aviarycited by 7
- 2023Objects do not disappear: Video object detection by single-frame object location anticipationcited by 7
- 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Viewscited by 7
- 2021Next Generation Multitarget Trackers: Random Finite Set Methods vs Transformer-based Deep Learningcited by 6
- 2022InterTrack: Interaction Transformer for 3D Multi-Object Trackingcited by 6
- 2023SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Featurescited by 6
- 2021Cross-Modal Analysis of Human Detection for Robotics: An Industrial Case Studycited by 5
- 2021Unlocking the potential of deep learning for marine ecology: overview, applications, and outlookcited by 5
- 2022Can Deep Learning be Applied to Model-Based Multi-Object Tracking?cited by 5
- 2025OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cookingcited by 5
- 2025WildLive: Near Real-time Visual Wildlife Tracking onboard UAVscited by 5
- 2024Engineering an Efficient Object Tracker for Non-Linear Motioncited by 4
- 2025Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Artcited by 4
- 2022Optical tracking in team sportscited by 3
- 2023TAU: A Framework for Video-Based Traffic Analytics Leveraging Artificial Intelligence and Unmanned Aerial Systemscited by 3
- 2023A review of UAV Visual Detection and Tracking Methodscited by 3
- 2023The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theorycited by 3
50 most cited of 107 All 107 (JSON)
- 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT14 Sep 2026
- 2026Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment22 Jul 2026
- 2026Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution6 May 2026
- 2025Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?25 Nov 2025
- 2025Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration20 Nov 2025
- 2025Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature23 Oct 2025
- 2025Distant Object Localisation from Noisy Image Segmentation Sequences25 Sep 2025
- 2025Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding14 Sep 2025
- 2025TrackOR: Towards Personalized Intelligent Operating Rooms Through Robust Tracking11 Aug 2025
- 2025Head Anchor Enhanced Detection and Association for Crowded Pedestrian Tracking7 Aug 2025
- 2025Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering7 Aug 2025
- 2025MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results17 Jul 2025
38 more
- 2025One Graph to Track Them All: Dynamic GNNs for Single- and Multi-View Tracking11 Jul 2025
- 2025SAMO: A Lightweight Sharpness-Aware Approach for Multi-Task Optimization with Joint Global-Local Perturbation10 Jul 2025
- 2025Deep Learning-Based Multi-Object Tracking: A Comprehensive Survey from Foundations to State-of-the-Art16 Jun 2025
- 2025O-MaMa: Learning Object Mask Matching between Egocentric and Exocentric Views6 Jun 2025
- 2025Visual Trajectory Prediction of Vessels for Inland Navigation1 May 2025
- 2025WildLive: Near Real-time Visual Wildlife Tracking onboard UAVs14 Apr 2025
- 2025SAVeD: Learning to Denoise Low-SNR Video for Improved Downstream Performance31 Mar 2025
- 2025How good are deep learning methods for automated road safety analysis using video data? An experimental study12 Mar 2025
- 2025OSCAR: Object Status and Contextual Awareness for Recipes to Support Non-Visual Cooking7 Mar 2025
- 2025ReynoldsFlow: Physics-Inspired Spatiotemporal Flow Representation for Video Understanding6 Mar 2025
- 2025Towards long-term player tracking with graph hierarchies and domain-specific features28 Feb 2025
- 2025YOLO11-JDE: Fast and Accurate Multi-Object Tracking with Self-Supervised Re-ID23 Jan 2025
- 2024Gotta Hear Them All: Towards Sound Source Aware Audio Generation23 Nov 2024
- 2024LITE: A Paradigm Shift in Multi-Object Tracking with Efficient ReID Feature Integration6 Sep 2024
- 2024FMRFT: Fusion Mamba and DETR for Query Time Sequence Intersection Fish Tracking2 Sep 2024
- 2024Engineering an Efficient Object Tracker for Non-Linear Motion30 Jun 2024
- 2024Scale-Translation Equivariant Network for Oceanic Internal Solitary Wave Localization18 Jun 2024
- 2024Multi-Granularity Language-Guided Training for Multi-Object Tracking7 Jun 2024
- 2024MAML MOT: Multiple Object Tracking based on Meta-Learning12 May 2024
- 2024Unsupervised Skin Feature Tracking with Deep Neural Networks8 May 2024
- 2024Vision-based Discovery of Nonlinear Dynamics for 3D Moving Target27 Apr 2024
- 2024Computer Vision for Primate Behavior Analysis in the Wild29 Jan 2024
- 2024VONet: Unsupervised Video Object Learning With Parallel U-Net Attention and Object-wise Sequential VAE20 Jan 2024
- 2023Transformer-Based Multi-Object Smoothing with Decoupled Data Association and Smoothing22 Dec 2023
- 2023Real-time Neural Network Inference on Extremely Weak Devices: Agile Offloading with Explainable AI21 Dec 2023
- 2023Learning Object State Changes in Videos: An Open-World Perspective19 Dec 2023
- 2023Automated Behavioral Analysis Using Instance Segmentation12 Dec 2023
- 2023Mixture of Dynamical Variational Autoencoders for Multi-Source Trajectory Modeling and Separation7 Dec 2023
- 2023Neural Texture Puppeteer: A Framework for Neural Geometry and Texture Rendering of Articulated Shapes, Enabling Re-Identification at Interactive Speed28 Nov 2023
- 2023Acquiring Weak Annotations for Tumor Localization in Temporal and Volumetric Data23 Oct 2023
- 2023SpikeMOT: Event-based Multi-Object Tracking with Sparse Motion Features29 Sep 2023
- 2023RaTrack: Moving Object Detection and Tracking with 4D Radar Point Cloud18 Sep 2023
- 2023FishMOT: A Simple and Effective Method for Fish Tracking Based on IoU Matching6 Sep 2023
- 2023Objects do not disappear: Video object detection by single-frame object location anticipation9 Aug 2023
- 2023Model Compression Methods for YOLOv5: A Review21 Jul 2023
- 2023S.T.A.R.-Track: Latent Motion Models for End-to-End 3D Object Tracking with Adaptive Spatio-Temporal Appearance Representations30 Jun 2023
- 2023The Deep Arbitrary Polynomial Chaos Neural Network or how Deep Artificial Neural Networks could benefit from Data-Driven Homogeneous Chaos Theory26 Jun 2023
- 2023A review of UAV Visual Detection and Tracking Methods8 Jun 2023
50 newest of 107 All 107 (JSON)
- 2022Sparse4D: Multi-view 3D Object Detection with Sparse Spatial-Temporal Fusioncited by 162
- 2023EgoHumans: An Egocentric 3D Multi-Human Benchmarkcited by 60
- 2021DEFT: Detection Embeddings for Trackingcited by 56
- 2021RelationTrack: Relation-aware Multiple Object Tracking with Decoupled Representationcited by 52
- 2021A Survey of Sound Source Localization with Deep Learning Methodscited by 46
- 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
- 2021Tracking Pedestrian Heads in Dense Crowdcited by 42
- 2022AnimalTrack: A Benchmark for Multi-Animal Tracking in the Wildcited by 37
- 2023Learning Object State Changes in Videos: An Open-World Perspectivecited by 36
- 2023A Survey on Deep Learning-Based Monocular Spacecraft Pose Estimation: Current State, Limitations and Prospectscited by 30
- 2022Continual Learning with Bayesian Model based on a Fixed Pre-trained Feature Extractorcited by 27
- 2021Unmanned Aerial Vehicle Visual Detection and Tracking using Deep Neural Networks: A Performance Benchmarkcited by 25
12 most cited of 105 All 105 (JSON)
- 2026Beyond the Survey: A Systematic Empirical Study of Detection and Association in Visual MOT14 Sep 2026
- 2026Calibration-Free 3D Multi-Camera People Tracking for Indoor Environment22 Jul 2026
- 2026Seeing What Shouldn't Be There: Counterfactual GANs for Medical Image Attribution6 May 2026
- 2025Video Object Recognition in Mobile Edge Networks: Local Tracking or Edge Detection?25 Nov 2025
- 2025Enhancing Multi-Camera Gymnast Tracking Through Domain Knowledge Integration20 Nov 2025
- 2025Radar-Camera Fused Multi-Object Tracking: Online Calibration and Common Feature23 Oct 2025
- 2025Distant Object Localisation from Noisy Image Segmentation Sequences25 Sep 2025
- 2025Motion Estimation for Multi-Object Tracking using KalmanNet with Semantic-Independent Encoding14 Sep 2025
- 2025TrackOR: Towards Personalized Intelligent Operating Rooms Through Robust Tracking11 Aug 2025
- 2025Head Anchor Enhanced Detection and Association for Crowded Pedestrian Tracking7 Aug 2025
- 2025Multi-tracklet Tracking for Generic Targets with Adaptive Detection Clustering7 Aug 2025
- 2025MVA 2025 Small Multi-Object Tracking for Spotting Birds Challenge: Dataset, Methods, and Results17 Jul 2025
12 newest of 105 All 105 (JSON)