CoChat
Sign Up
Cited by 475Video Surveillance and Tracking MethodsAdvanced Neural Network ApplicationsVisual Attention and Saliency Detection

Learning the Model Update for Siamese Trackers

Open access
Zhang, Lichao, Gonzalez-Garcia, Abel, Weijer, Joost Van De, Danelljan, Martin, Khan, Fahad Shahbaz·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00411
Open this paper in CoChat — free accountOpen PDF

Abstract

Siamese approaches address the visual tracking problem by extracting an appearance template from the current frame, which is used to localize the target in the next frame. In general, this template is linearly combined with the accumulated template from the previous frame, resulting in an exponential decay of information over time. While such an approach to updating has led to improved results, its simplicity limits the potential gain likely to be obtained by learning to update. Therefore, we propose to replace the handcrafted update function with a method which learns to update. We use a convolutional neural network, called UpdateNet, which given the initial template, the accumulated template and the template of the current frame aims to estimate the optimal template for the next frame. The UpdateNet is compact and can easily be integrated into existing Siamese trackers. We demonstrate the generality of the proposed approach by applying it to two Siamese trackers, SiamFC and DaSiamRPN. Extensive experiments on VOT2016, VOT2018, LaSOT, and TrackingNet datasets demonstrate that our UpdateNet effectively predicts the new target template, outperforming the standard linear update. On the large-scale TrackingNet dataset, our UpdateNet improves the results of DaSiamRPN with an absolute gain of 3.9% in terms of success score.

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/iccv.2019.00411

Cites

8 of 8 references verified0 citation errors · 0 not checkable

Statistics

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

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?

  • Previous Siamese trackers only exploit spatial information for tracking, while online methods use historical predictions for model updates.

    “Previous Siamese trackers [25, 51, 14, 6] only exploit the spatial information for tracking, while online methods [54, 57, 9, 3] use historical predictions for model updates.”

    From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [57]

  • Previous models have to improve nonlinear representation ability by introducing fashion structures, using additional modules, or designing effective online updaters.

    “Thus, previous models have to improve the nonlinear representation ability by introducing fashion structures [21, 44, 48], using additional modules [7, 46, 13], designing effective online updaters [2, 47, 10], to name a few.”

    From Transformer Tracking (2021) · cites this paper as [46]

Self-check

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

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

Cites

Flagged first, then by citations

Research works printed but not linked: 40

  1. G. Bhat, J. Johnander, M. Danelljan, F. Shahbaz Khan, and M. Felsberg. Unveiling the power of deep tracking. In ECCV, 2018. 7
  2. D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. Visual object tracking using adaptive correlation filters. In CVPR, 2010. 1, 2, 3
  3. D. S. Bolme, B. A. Draper, and J. R. Beveridge. Average of synthetic exact filters. In CVPR, 2009. 3
  4. J. Choi, H. Jin Chang, T. Fischer, S. Yun, K. Lee, J. Jeong, Y. Demiris, and J. Young Choi. Context-aware deep feature compression for high-speed visual tracking. In CVPR, 2018. 2
  5. J. Choi, J. Kwon, and K. M. Lee. Visual tracking by rein- forced decision making. CoRR, abs/1702.06291, 2017. · arXiv
  6. M. Danelljan, G. Bhat, F. S. Khan, and M. Felsberg. Atom: Accurate tracking by overlap maximization. In CVPR, 2019. 7, 8
  7. M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. Learning spatially regularized correlation filters for visual tracking. In ICCV, 2015. 2
  8. M. Danelljan, G. Hager, F. Shahbaz Khan, and M. Felsberg. Adaptive decontamination of the training set: A unified for- mulation for discriminative visual tracking. In CVPR, 2016. 2
  9. M. Danelljan, A. Robinson, F. S. Khan, and M. Felsberg. Beyond correlation filters: Learning continuous convolution operators for visual tracking. In ECCV, 2016. 1, 2, 3
  10. H. Fan and H. Ling. Siamese cascaded region proposal net- works for real-time visual tracking. CoRR, abs/1812.06148, 2018. 5 · arXiv
  11. Q. Guo, W. Feng, C. Zhou, R. Huang, L. Wan, and S. Wang. Learning dynamic siamese network for visual object track- ing. In ICCV, 2017. 3, 8
  12. A. He, C. Luo, X. Tian, and W. Zeng. A twofold siamese network for real-time object tracking. In CVPR, 2018. 2
  13. H. Kiani Galoogahi, A. Fagg, and S. Lucey. Learning background-aware correlation filters for visual tracking. In ICCV, 2017. 2
  14. H. Kiani Galoogahi, T. Sim, and S. Lucey. Correlation filters with limited boundaries. In CVPR, 2015. 3
  15. M. Kristan, A. Leonardis, J. Matas, M. Felsberg, R. Pflugfelder, L. Č. Zajc, T. Vojír, G. Bhat, A. Lukežič, A. Eldesokey, et al. The sixth visual object tracking vot2018 challenge results. In ECCV workshop, 2018. 2, 5, 6, 7, 8
  16. M. Kristan, J. Matas, A. Leonardis, T. Vojir, R. Pflugfelder, G. Fernandez, G. Nebehay, F. Porikli, and L. Čehovin. A novel performance evaluation methodology for single-target trackers. TPAMI, 38(11):2137-2155, Nov 2016. 5
  17. M. Kristan, R. Pflugfelder, A. Leonardis, J. Matas, F. Porikli, L. Cehovin, G. Nebehay, G. Fernandez, T. Vojir, A. Gatt, et al. The visual object tracking vot2016 challenge results. In ECCV workshop, 2016. 2, 5
  18. H. Lee and D. Kim. Salient region-based online object track- ing. In WACV, 2018. 7
  19. B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, and J. Yan. Siamrpn++: Evolution of siamese visual tracking with very deep networks. CoRR, abs/1812.11703, 2018. 5 · arXiv
  20. B. Li, J. Yan, W. Wu, Z. Zhu, and X. Hu. High performance visual tracking with siamese region proposal network. In CVPR, 2018. 1, 2, 3
  21. F. Li, C. Tian, W. Zuo, L. Zhang, and M.-H. Yang. Learn- ing spatial-temporal regularized correlation filters for visual tracking. In CVPR, 2018. 7, 8
  22. A. Lukezic, T. Vojír, L. C. Zajc, J. Matas, and M. Kristan. Discriminative correlation filter with channel and spatial re- liability. In CVPR, 2017. 7
  23. M. Muller, A. Bibi, S. Giancola, S. Alsubaihi, and B. Ghanem. Trackingnet: A large-scale dataset and bench- mark for object tracking in the wild. In ECCV, 2018. 5, 8
  24. H. Nam and B. Han. Learning multi-domain convolutional neural networks for visual tracking. In CVPR, 2016. 1, 8
  25. E. Park and A. C. Berg. Meta-tracker: Fast and robust online adaptation for visual object trackers. In ECCV, 2018. 3
  26. B. Renoust, D.-D. Le, and S. Satoh. Visual analytics of polit- ical networks from face-tracking of news video. IEEE Trans- actions on Multimedia, 18(11):2184-2195, 2016. 1
  27. Y. Song, C. Ma, X. Wu, L. Gong, L. Bao, W. Zuo, C. Shen, R. W. Lau, and M.-H. Yang. Vital: Visual tracking via ad- versarial learning. In CVPR, 2018. 8
  28. C. Stauffer and W. E. L. Grimson. Adaptive background mix- ture models for real-time tracking. In CVPR, 1999. 2, 3
  29. C. Sun, D. Wang, H. Lu, and M.-H. Yang. Correlation track- ing via joint discrimination and reliability learning. In CVPR, 2018. 7
  30. C. Sun, D. Wang, H. Lu, and M.-H. Yang. Learning spatial- aware regressions for visual tracking. In CVPR, 2018. 7
  31. R. Tao, E. Gavves, and A. W. Smeulders. Siamese instance search for tracking. In CVPR, 2016. 8
  32. J. Valmadre, L. Bertinetto, J. Henriques, A. Vedaldi, and P. H. Torr. End-to-end representation learning for correla- tion filter based tracking. In CVPR, 2017. 2, 3, 5, 7, 8
  33. Q. Wang, Z. Teng, J. Xing, J. Gao, W. Hu, and S. Maybank. Learning attentions: residual attentional siamese network for high performance online visual tracking. In CVPR, 2018. 1, 2, 3
  34. T. Xu, Z.-H. Feng, X.-J. Wu, and J. Kittler. Learning adap- tive discriminative correlation filters via temporal consis- tency preserving spatial feature selection for robust visual tracking. CoRR, abs/1807.11348, 2018. 7 · arXiv
  35. T. Yang and A. B. Chan. Learning dynamic memory net- works for object tracking. In ECCV, 2018. 3, 8
  36. Y. Yao, X. Wu, L. Zhang, S. Shan, and W. Zuo. Joint rep- resentation and truncated inference learning for correlation filter based tracking. In ECCV, 2018. 3
  37. K. Zhang, L. Zhang, Q. Liu, D. Zhang, and M.-H. Yang. Fast visual tracking via dense spatio-temporal context learning. In ECCV, 2014. 1
  38. T. Zhang, C. Xu, and M.-H. Yang. Learning multi-task corre- lation particle filters for visual tracking. TPAMI, 41(2):365- 378, 2019. 1, 2, 7
  39. Y. Zhang, L. Wang, J. Qi, D. Wang, M. Feng, and H. Lu. Structured siamese network for real-time visual tracking. In ECCV, 2018. 2, 8
  40. Z. Zhu, Q. Wang, B. Li, W. Wu, J. Yan, and W. Hu. Distractor-aware siamese networks for visual object track- ing. In ECCV, 2018. 1, 2, 3, 5, 7, 8

Cited by

Sorted by citations

Authors
Zhang, L., Gonzalez-Garcia, A., Weijer, J. V. D., Danelljan, M., & Khan, F. S.
Affiliations
  • Universitat Autònoma de Barcelona (ES)
  • ETH Zurich (CH)
  • Linköping University (SE)
ORCID
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
4009-4018
DOI
10.1109/iccv.2019.00411
OpenAlex
W2987460522
Cited by
475
References
8
Citations by year
2026: 28 · 2025: 61 · 2024: 83 · 2023: 108 · 2022: 95 · 2021: 70 · 2020: 30
FWCI
15.89
Type
conference paper
Language
en
Open access
Licence
Locations
  • IEEE/CVF International Conference on Computer Vision (ICCV) (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
  • Centres de Recerca de Catalunya
  • Generalitat de Catalunya
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Video Surveillance and Tracking Methods
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Visual Attention and Saliency Detection
Keywords
template updating, SiamFC, LaSOT

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