The DOI matches its Crossref record; 71 of the 72 references it cites were found in a registry or an index.
StrongSORT: Make DeepSORT Great Again
Open accessAbstract
Recently, Multi-Object Tracking (MOT) has attracted rising attention, and accordingly, remarkable progresses have been achieved. However, the existing methods tend to use various basic models (e.g, detector and embedding model), and different training or inference tricks, etc. As a result, the construction of a good baseline for a fair comparison is essential. In this paper, a classic tracker, i.e., DeepSORT, is first revisited, and then is significantly improved from multiple perspectives such as object detection, feature embedding, and trajectory association. The proposed tracker, named StrongSORT, contributes a strong and fair baseline for the MOT community. Moreover, two lightweight and plug-and-play algorithms are proposed to address two inherent “missing” problems of MOT: missing association and missing detection. Specifically, unlike most methods, which associate short tracklets into complete trajectories at high computation complexity, we propose an appearance-free link model (AFLink) to perform global association without appearance information, and achieve a good balance between speed and accuracy. Furthermore, we propose a Gaussian-smoothed interpolation (GSI) based on Gaussian process regression to relieve the missing detection. AFLink and GSI can be easily plugged into various trackers with a negligible extra computational cost (1.7 ms and 7.1 ms per image, respectively, on MOT17). Finally, by fusing StrongSORT with AFLink and GSI, the final tracker (StrongSORT++) achieves state-of-the-art results on multiple public benchmarks, i.e., MOT17, MOT20, DanceTrack and KITTI. Codes are available athttps://github.com/dyhBUPT/StrongSORTandhttps://github.com/open-mmlab/mmtracking.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
In the citing paper
“Gaussian Smoothed Interpolation (GSI) is introduced to fill in trajectory gaps caused by detection misses.”
From Multi-Object Vehicle Detection and Tracking Algorithm Based on Improved YOLOv8 and ByteTrack (2024) · cites this paper as [17]
Citations
Cites
Adam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 1×
“We use Adam as the optimizer [26] and cross-entropy loss as the objective function and train it for 20 epochs with a cosine annealing learning rate schedule.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472 · cited 3×
“DeepSORT uses the optimized Faster R-CNN [39] presented in [60] as the detector and trains a simple CNN as the embedding model.”
MethodFaster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2015) · arXiv · doi:10.48550/arxiv.1506.01497 · Cited by 70,812
A New Approach to Linear Filtering and Prediction Problems
Kalman, R. E. (1960) · Journal of Basic Engineering · doi:10.1115/1.3662552 · Cited by 31,751
YOLOv3: An Incremental Improvement
Redmon, J., & Farhadi, A. (2018) · arXiv · doi:10.48550/arxiv.1804.02767 · Cited by 17,141 · cited 1×
“…[60, 3, 55, 4, 32, 21] follow the tracking-by-detection paradigm, which localizes targets first and then associates them with information on appearance, motion, etc. Benefiting from the rapid development of object detection [39, 38, 18], separate trackers have been widely applied in MOT tasks.”
A Multi-Modal Distributed Real-Time IoT System for Urban Traffic Control (Invited Paper)
Khanam, Z., Achari, V. P. S., Boukhennoufa, I., Jindal, A., & Singh, A. K. (2024) · DROPS (Schloss Dagstuhl – Leibniz Center for Informatics) · doi:10.4230/oasics.ng-res.2024.2 · Cited by 14,040
The Hungarian method for the assignment problem
Kuhn, H. W. (1955) · Naval Research Logistics Quarterly · doi:10.1002/nav.3800020109 · Cited by 13,120
Vision meets robotics: The KITTI dataset
Geiger, A., Lenz, P., Stiller, C., & Urtasun, R. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913491297 · Cited by 9,913 · cited 3×
“Camera movements exist in multiple benchmarks [31, 44, 19].”
BackgroundMethodEfficientDet: Scalable and Efficient Object Detection
Tan, M., Pang, R., & Le, Q. V. (2019) · arXiv · Cited by 9,841 · cited 1×
“Benefiting from the rapid development of object detection [17, 42, 43, 52, 53, 78], seperate trackers have dominated the MOT task for years.”
MethodSimple online and realtime tracking with a deep association metric
Wojke, N., Bewley, A., & Paulus, D. (2017) · 2017 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip.2017.8296962 · Cited by 5,286 · cited 5×
“Separate trackers [60, 3, 55, 4, 32, 21] follow the tracking-by-detection paradigm, which localizes targets first and then associates them with information on appearance, motion, etc. Benefiting from the rapid development of object detection [39, 38, 18], separate trackers have been widely applied in…”
BackgroundMethodInfluential
Cited by
Deep OC-Sort: Multi-Pedestrian Tracking by Adaptive Re-Identification
Maggiolino, G., Ahmad, A., Cao, J., & Kitani, K. (2023) · 2023 IEEE International Conference on Image Processing (ICIP) · doi:10.1109/icip49359.2023.10222576 · Cited by 320
“In previous work [3, 4], the deep visual embedding used to describe a tracklet is given by an Exponential Moving Average (EMA) of the deep detection embeddings frame by frame.”
BackgroundMethodInfluentialHybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking
Yang, M., Han, G., Yan, B., Zhang, W., Qi, J., Lu, H., & Wang, D. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i7.28471 · Cited by 187
SportsMOT: A Large Multi-Object Tracking Dataset in Multiple Sports Scenes
Cui, Y., Zeng, C., Zhao, X., Yang, Y., Wu, G., & Wang, L. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.00910 · Cited by 190
“Generally, prevailing state-of-the-art trackers [1,6,11,39, 44] consist of several components to accomplish the tracking task: objects localization module, motion based objects association module and appearance based association module.”
BackgroundMotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking
Qin, Z., Zhou, S., Wang, L., Duan, J., Hua, G., & Tang, W. (2023) · 2023 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52729.2023.01720 · Cited by 172
“Meanwhile, some works [12, 13] using KF variants to further improve prediction accuracy.”
BackgroundQDTrack: Quasi-Dense Similarity Learning for Appearance-Only Multiple Object Tracking
Fischer, T., Huang, T., Pang, J., Qiu, L., Chen, H., Darrell, T., & Yu, F. (2023) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2023.3301975 · Cited by 213
“On MOT17 and MOT20, we follow the recent practice of [44], [45], [71] and train QDTrack with the popular YOLOX [73] detector on the union of CrowdHuman [64] and the respective MOT benchmark.”
Method
Metadata
- Authors
- Du, Y., Zhao, Z., Song, Y., Zhao, Y., Su, F., Gong, T., & Meng, H.
- Affiliations
- Beijing University of Posts and Telecommunications (CN)
- University of Science and Technology of China (CN)
- Brunel University of London (GB)
- Venue
- IEEE Transactions on Multimedia
- Published
- 2023
- Volume
- 25
- Pages
- 8725-8737
- ISSN
- 1520-9210 (ISSN-L)
- 1941-0077
- OpenAlex
- W4319866011
- Cited by
- 1,191
- References
- 72
- Citations by year
- 2026: 293 · 2025: 382 · 2024: 333 · 2023: 160
- FWCI
- 105.91
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Multimedia (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- Brunel University Research Archive (BURA) (Brunel University London) (submittedVersion)
- arXiv (Cornell University) (cc-by)
- Funders
- National Natural Science Foundation of China (62076033, U1931202)
- Beijing University of Posts and Telecommunications (CX2022145)
- Topics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
- Physical Sciences › Engineering › Automotive Engineering › Autonomous Vehicle Technology and Safety
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
- Keywords
- multi-target tracking, DeepSORT, StrongSORT, Gaussian process regression, missing detection, object detection, feature embedding, lightweight tracker, MOT17, MOT20
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: StrongSORT: Make DeepSORT Great Again. https://app.cochat.ai/papers/10.1109/tmm.2023.3240881
- The paper
- Du, Y., Zhao, Z., Song, Y., Zhao, Y., Su, F., Gong, T., & Meng, H. (2023). StrongSORT: Make DeepSORT Great Again. IEEE Transactions on Multimedia. https://doi.org/10.1109/tmm.2023.3240881
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.