Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 241

The DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.

MeMOT: Multi-Object Tracking with Memory

Open access
Cai, Jiarui, Xu, Mingze, Li, Wei, Xiong, Yuanjun, Xia, Wei, Tu, Zhuowen, Soatto, Stefano·2022·2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

Abstract

We propose an online tracking algorithm that performs the object detection and data association under a common framework, capable of linking objects after a long time span. This is realized by preserving a large spatio-temporal memory to store the identity embeddings of the tracked objects, and by adaptively referencing and aggregating useful information from the memory as needed. Our model, called MeMOT, consists of three main modules that are all Transformer-based: 1) Hypothesis Generation that produce object proposals in the current video frame; 2) Memory Encoding that extracts the core information from the memory for each tracked object; and 3) Memory Decoding that solves the object detection and data association tasks simultaneously for multi-object tracking. When evaluated on widely adopted MOT benchmark datasets, MeMOT observes very competitive performance.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1109/cvpr52688.2022.00792

Cites

24 of 24 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 24 references

Research works printed but not linked: 51

  1. zhu, 2020, Deformable DETR: Deformable transform-ers for end-to-end object detection, ArXiv, 2
  2. zhou, 0, Tracking objects as points, ECCV, 2
  3. zhang, 2020, FairMOT: On the fairness of detection and re-identification in multiple object tracking, ArXiv, 1,2,4
  4. peng, 0, Chained-tracker: Chaining paired attentive regression results for end-to-end joint multiple-object detection and tracking, ECCV, 6
  5. paszke, 0, PyTorch: An imperative style, high-performance deep learning library, NeurIPS, 5
  6. 10.1007/s11263-020-01375-2 · DOI · Paper page
  7. lu, 0, Video object segmentation with episodic graph memory networks, ECCV, 2
  8. loshchilov, 2017, Decoupled weight decay regularization, ArXiv, 5
  9. 10.1109/ICCV.2019.00932 · DOI · Paper page
  10. 10.1109/CVPR46437.2021.01217 · DOI · Paper page
  11. xing, 0, Multi-object tracking through occlusions by local tracklets filtering and global tracklets association with detection responses, CVPR, 2
  12. xing, 2010, Multiple player tracking in sports video: A dual-mode two-way bayesian inference approach with progressive observation modeling, TIP, 2
  13. liu, 0, Berg. SSD: Single shot multibox detector, ECCV, 1
  14. xiong, 0, Dynamic memory networks for visual and textual question answering, ICML, 2
  15. lin, 0, Microsoft coco: Common objects in context, ECCV, 5
  16. 10.1007/978-3-030-01246-5_39 · DOI
  17. xu, 0, Long short-term trans-former for online action detection, NeurIPS, 2
  18. xu, 2021, TransCenter: Transformers with dense queries for multiple-object tracking, ArXiv, 2
  19. 10.1007/978-3-030-01240-3_10 · DOI · Paper page
  20. 10.1109/ICCV48922.2021.00676 · DOI · Paper page
  21. 10.1109/78.978396 · DOI · Paper page
  22. 10.1109/MOT.2001.937982 · DOI
  23. kristan, 0, The visual object tracking vot2015 challenge results, ICCVW, 2
  24. isard, 1998, Condensation-conditional density propagation for visual tracking, IJCV, 2
  25. li, 2021, Semi- Tcl: Semi-supervised track contrastive representation learning, ArXiv, 2
  26. kumar, 0, Ask me anything: Dynamic memory networks for natural language processing, ICML, 2
  27. vaswani, 0, Attention is all you need, NeurIPS, 2
  28. 10.1145/3343031.3350853 · DOI · Paper page
  29. wu, 0, Longterm feature banks for detailed video understanding, CVPR, 2
  30. wu, 0, Global-to-local memory pointer networks for task-oriented dialogue, ICLRE, 2
  31. 10.1109/ICIP.2017.8296962 · DOI · Paper page
  32. weston, 2014, Memory networks, ArXiv, 2
  33. welch, 1995, An introduction to the Kalman filter, 2
  34. wang, 0, Joint object detection and multi-object tracking with graph neural net-works, ICRA, 6
  35. dendorfer, 2020, MOT20: A benchmark for multi object tracking in crowded scenes, ArXiv, 2
  36. dosovitskiy, 2021, An image is worth 16×16 words: Transformers for image recognition at scale, ICLRE, 2
  37. 10.1109/CVPR.2006.195 · DOI · Paper page
  38. feng, 2019, Multi-object tracking with multiple cues and switcher-aware classification, ArXiv, 2
  39. 10.1109/CVPR46437.2021.01356 · DOI · Paper page
  40. ge, 2021, YOLOX: Exceeding yolo series in 2021, ArXiv, 1
  41. 10.1007/978-3-540-24673-2_20 · DOI
  42. 10.1109/ICCV.2019.00103 · DOI · Paper page
  43. 10.1109/CVPR42600.2020.00628 · DOI · Paper page
  44. 10.1109/ICCV.2019.00627 · DOI · Paper page
  45. 10.1007/978-3-642-15561-1_40 · DOI
  46. chu, 2021, TransMOT: Spatial-temporal graph trans-former for multiple object tracking, ArXiv, 2
  47. shen, 2003, Probabilistic multiple cue integration for particle filter based tracking, Australian Pattern Recognition Society, 2
  48. sharir, 2021, An image is worth 16×16 words, what is a video worth, ArXiv, 2
  49. sun, 2020, Transtrack: Multiple-object tracking with trans-former, ArXiv, 2
  50. sukhbaatar, 0, End-to-end memory networks, NeurIPS, 2
  51. rangesh, 2021, TrackMPNN: A message passing graph neural architecture for multi-object tracking, ArXiv, 2

Cited by

See all 241

Metadata

Authors
Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., & Soatto, S.
Venue
2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2022-06
Pages
8080-8090
ISSN
1063-6919 (ISSN-L)
OpenAlex
W4313117614
Cited by
241
References
24
FWCI
19.60
Type
conference paper
Language
en
Open access
green

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: MeMOT: Multi-Object Tracking with Memory. https://app.cochat.ai/papers/10.1109/cvpr52688.2022.00792
The paper
Cai, J., Xu, M., Li, W., Xiong, Y., Xia, W., Tu, Z., & Soatto, S. (2022). MeMOT: Multi-Object Tracking with Memory. 2022 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). https://doi.org/10.1109/cvpr52688.2022.00792

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.