mlsanityData to 7 Oct 2026

Multiple Object Tracking with Mixture Density Networks for Trajectory Estimation

arXiv 2106.10950 ↗First posted 21 Jun 2021cs.CVcited by 8

Not on the map. Why?

Abstract (arXiv)

Multiple object tracking faces several challenges that may be alleviated with trajectory information. Knowing the posterior locations of an object helps disambiguating and solving situations such as occlusions, re-identification, and identity switching. In this work, we show that trajectory estimation can become a key factor for tracking, and present TrajE, a trajectory estimator based on recurrent mixture density networks, as a generic module that can be added to existing object trackers. To provide several trajectory hypotheses, our method uses beam search. Also, relying on the same estimated trajectory, we propose to reconstruct a track after an occlusion occurs. We integrate TrajE into two state of the art tracking algorithms, CenterTrack [63] and Tracktor [3]. Their respective performances in the MOTChallenge 2017 test set are boosted 6.3 and 0.3 points in MOTA score, and 1.8 and 3.1 in IDF1, setting a new state of the art for the CenterTrack+TrajE configuration

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 34 of its 65 references that are in the map. First posted on arXiv 21 Jun 2021.

Builds on

34 of 65 references.

References · 34

  1. 2015Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networkscited by 9,617
  2. 2014Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translationcited by 4,016
  3. 2015SSD: Single Shot MultiBox Detectorcited by 3,125
  4. 2016YOLO9000: Better, Faster, Strongercited by 1,429
  5. 2017Simple Online and Realtime Tracking with a Deep Association Metriccited by 908
  6. 2016Simple Online and Realtime Trackingcited by 862
  7. 2018Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networkscited by 687
  8. 2019CenterNet: Keypoint Triplets for Object Detectioncited by 654
  9. 2013Generating Sequences With Recurrent Neural Networkscited by 549
  10. 2020HOTA: A Higher Order Metric for Evaluating Multi-Object Trackingcited by 546
  11. 2016MOT16: A Benchmark for Multi-Object Trackingcited by 531
  12. 2020Tracking Objects as Pointscited by 483
22 more
  1. 2019Tracking without bells and whistlescited by 382
  2. 2019Human Motion Trajectory Prediction: A Surveycited by 231
  3. 2019Learning a Neural Solver for Multiple Object Trackingcited by 198
  4. 2017Detect to Track and Track to Detectcited by 131
  5. 2015UA-DETRAC: A New Benchmark and Protocol for Multi-Object Detection and Trackingcited by 98
  6. 2018Real-time Multiple People Tracking with Deeply Learned Candidate Selection and Person Re-Identificationcited by 96
  7. 2019Overcoming Limitations of Mixture Density Networks: A Sampling and Fitting Framework for Multimodal Future Predictioncited by 96
  8. 2018Deep Affinity Network for Multiple Object Trackingcited by 82
  9. 2019Online Multi-Object Tracking with Dual Matching Attention Networkscited by 77
  10. 2017Tracking The Untrackable: Learning To Track Multiple Cues with Long-Term Dependenciescited by 76
  11. 2016POI: Multiple Object Tracking with High Performance Detection and Appearance Featurecited by 74
  12. 2019Spatial-Temporal Relation Networks for Multi-Object Trackingcited by 74
  13. 2019FAMNet: Joint Learning of Feature, Affinity and Multi-dimensional Assignment for Online Multiple Object Trackingcited by 65
  14. 2016Online Multi-Target Tracking Using Recurrent Neural Networkscited by 59
  15. 2020Lifted Disjoint Paths with Application in Multiple Object Trackingcited by 55
  16. 2017Deep Network Flow for Multi-Object Trackingcited by 45
  17. 2018Exploit the Connectivity: Multi-Object Tracking with TrackletNetcited by 30
  18. 2015Learning Complexity-Aware Cascades for Deep Pedestrian Detectioncited by 18
  19. 2019Online Multi-Object Tracking with Instance-Aware Tracker and Dynamic Model Refreshmentcited by 18
  20. 2018Convolutional Neural Network for Trajectory Predictioncited by 11
  21. 2018Trajectory Factory: Tracklet Cleaving and Re-connection by Deep Siamese Bi-GRU for Multiple Object Trackingcited by 7
  22. 2018Learning Non-Uniform Hypergraph for Multi-Object Trackingcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2022: 3; 2023: 1; 2024: 1; 2025: 2; 2026: 1.

8 papers.

  1. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  2. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  3. 2025Hyperparameter Optimisation with Practical Interpretability and Explanation Methods in Probabilistic Curriculum Learningcited by 1
  4. 2022Improving tracking with a tracklet associatorcited by 0
  5. 2023A Hybrid Approach To Real-Time Multi-Object Trackingcited by 0
  6. 2024ConsistencyTrack: A Robust Multi-Object Tracker with a Generation Strategy of Consistency Modelcited by 0
  7. 2025Trajectory Prediction in Dynamic Object Tracking: A Critical Studycited by 0
  8. 2026Conditional Normalizing Flows for Forward and Backward Joint State and Parameter Estimationcited by 0