mlsanityData to 7 Oct 2026

Lifted Disjoint Paths with Application in Multiple Object Tracking

arXiv 2006.14550 ↗First posted 25 Jun 2020cs.CV cs.DMcited by 55

Not on the map. Why?

Abstract (arXiv)

We present an extension to the disjoint paths problem in which additional lifted edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities. The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long range temporal interactions. Lifted edges help to prevent id switches and to re-identify persons. Our lifted disjoint paths tracker achieves nearly optimal assignments with respect to input detections. As a consequence, it leads on all three main benchmarks of the MOT challenge, improving significantly over state-of-the-art.

Key facts. Cited by 55 papers in the map (data through 7 Oct 2026). First posted on arXiv 25 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year

Citing papers per year: 2021: 23; 2022: 19; 2023: 6; 2024: 5; 2025: 2.

55 papers.

Sort:

By area:

  1. 2021ByteTrack: Multi-Object Tracking by Associating Every Detection Boxcited by 812
  2. 2021TrackFormer: Multi-Object Tracking with Transformerscited by 515
  3. 2022Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Trackingcited by 345
  4. 2021SimpleTrack: Understanding and Rethinking 3D Multi-object Trackingcited by 102
  5. 2021Spatial-Temporal Transformer for Dynamic Scene Graph Generationcited by 95
  6. 2021TransMOT: Spatial-Temporal Graph Transformer for Multiple Object Trackingcited by 93
  7. 2021MOTSynth: How Can Synthetic Data Help Pedestrian Detection and Tracking?cited by 68
  8. 2021Multiple Object Tracking with Correlation Learningcited by 67
  9. 2022Unifying Short and Long-Term Tracking with Graph Hierarchiescited by 62
  10. 2021Learnable Graph Matching: Incorporating Graph Partitioning with Deep Feature Learning for Multiple Object Trackingcited by 47
  11. 2022GIAOTracker: A comprehensive framework for MCMOT with global information and optimizing strategies in VisDrone 2021cited by 46
  12. 2022Simple Cues Lead to a Strong Multi-Object Trackercited by 44
38 more
  1. 2021Learning a Proposal Classifier for Multiple Object Trackingcited by 42
  2. 2021TransCenter: Transformers with Dense Representations for Multiple-Object Trackingcited by 42
  3. 2021LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Trackingcited by 34
  4. 20223D Multi-Object Tracking Using Graph Neural Networks with Cross-Edge Modality Attentioncited by 27
  5. 2021Track without Appearance: Learn Box and Tracklet Embedding with Local and Global Motion Patterns for Vehicle Trackingcited by 26
  6. 2021One More Check: Making "Fake Background" Be Tracked Againcited by 25
  7. 2022The Caltech Fish Counting Dataset: A Benchmark for Multiple-Object Tracking and Countingcited by 24
  8. 2022Adiabatic Quantum Computing for Multi Object Trackingcited by 22
  9. 2021Looking Beyond Two Frames: End-to-End Multi-Object Tracking Using Spatial and Temporal Transformerscited by 21
  10. 2023ByteTrackV2: 2D and 3D Multi-Object Tracking by Associating Every Detection Boxcited by 20
  11. 2021Making Higher Order MOT Scalable: An Efficient Approximate Solver for Lifted Disjoint Pathscited by 19
  12. 2021Split and Connect: A Universal Tracklet Booster for Multi-Object Trackingcited by 17
  13. 2022Efficient tracking of team sport players with few game-specific annotationscited by 17
  14. 2022Online Multi-Object Tracking with Unsupervised Re-Identification Learning and Occlusion Estimationcited by 16
  15. 2021Online Multiple Object Tracking with Cross-Task Synergycited by 12
  16. 2022Learning of Global Objective for Network Flow in Multi-Object Trackingcited by 11
  17. 2023Siamese-DETR for Generic Multi-Object Trackingcited by 11
  18. 2021RAMA: A Rapid Multicut Algorithm on GPUcited by 9
  19. 2022Multi-Object Tracking and Segmentation via Neural Message Passingcited by 9
  20. 2021Local Metrics for Multi-Object Trackingcited by 8
  21. 2021Know Your Surroundings: Panoramic Multi-Object Tracking by Multimodality Collaborationcited by 8
  22. 2021Multiple Object Tracking with Mixture Density Networks for Trajectory Estimationcited by 8
  23. 2022Recent Advances in Embedding Methods for Multi-Object Tracking: A Surveycited by 8
  24. 2022Depth Perspective-aware Multiple Object Trackingcited by 8
  25. 2024FeatureSORT: Essential Features for Effective Trackingcited by 8
  26. 2022Robust Multi-Object Tracking by Marginal Inferencecited by 7
  27. 2023Multi-Scene Generalized Trajectory Global Graph Solver with Composite Nodes for Multiple Object Trackingcited by 7
  28. 2022Towards Frame Rate Agnostic Multi-Object Trackingcited by 6
  29. 2022Multiple Object Tracking from appearance by hierarchically clustering trackletscited by 5
  30. 2022Structured Prediction Problem Archivecited by 4
  31. 2024OW-VISCapTor: Abstractors for Open-World Video Instance Segmentation and Captioningcited by 4
  32. 2021Uncertainty in Minimum Cost Multicuts for Image and Motion Segmentationcited by 3
  33. 2025NOOUGAT: Towards Unified Online and Offline Multi-Object Trackingcited by 3
  34. 2023Learnable Graph Matching: A Practical Paradigm for Data Associationcited by 2
  35. 2023A Graph Multi-separator Problem for Image Segmentationcited by 1
  36. 2024DINTR: Tracking via Diffusion-based Interpolationcited by 1
  37. 2024Learning a Neural Association Network for Self-supervised Multi-Object Trackingcited by 1
  38. 2021A Generic Object Re-identification System for Short Videoscited by 0

50 most cited of 55 All 55 (JSON)