CoChat
Sign Up
Cited by 1,515Video Surveillance and Tracking MethodsAdvanced Neural Network ApplicationsVisual Attention and Saliency Detection

Learning Discriminative Model Prediction for Tracking

Open access
Bhat, Goutam, Danelljan, Martin, Van Gool, Luc, Timofte, Radu·2019·2019 IEEE/CVF International Conference on Computer Vision (ICCV)
DOI 10.1109/iccv.2019.00628
Open this paper in CoChat — free accountOpen PDF

Abstract

The current strive towards end-to-end trainable computer vision systems imposes major challenges for the task of visual tracking. In contrast to most other vision problems, tracking requires the learning of a robust target-specific appearance model online, during the inference stage. To be end-to-end trainable, the online learning of the target model thus needs to be embedded in the tracking architecture itself. Due to the imposed challenges, the popular Siamese paradigm simply predicts a target feature template, while ignoring the background appearance information during inference. Consequently, the predicted model possesses limited target-background discriminability. We develop an end-to-end tracking architecture, capable of fully exploiting both target and background appearance information for target model prediction. Our architecture is derived from a discriminative learning loss by designing a dedicated optimization process that is capable of predicting a powerful model in only a few iterations. Furthermore, our approach is able to learn key aspects of the discriminative loss itself. The proposed tracker sets a new state-of-the-art on 6 tracking benchmarks, achieving an EAO score of 0.440 on VOT2018, while running at over 40 FPS. The code and models are available at https://github.com/visionml/pytracking.

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.2019.00628

Cites

6 of 6 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 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 [2]

    Section 3.2 describes an optimizer module that adapts the target model online, and the online-model-update analysis reports improved tracking performance from that approach. These passages support citing the paper as an example of an effective online updater, but they do not establish that it improves nonlinear representation ability. (LLM, conf=0.82)

    Experimental — accuracy not yet measured

  • STARKS50 achieves a competitive result on VOT2020, better than DiMP and UPDT.

    “Tab. 3 shows that STARKS50 achieves a competitive result, which is better than DiMP [3] and UPDT [4].”

    From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [3]

  • 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 [3]

  • Current prevailing trackers, including offline Siamese trackers and online learning models, are almost all built upon convolutional operations.

    “Current prevailing trackers, including both the offline Siamese trackers and the online learning models, are almost all build upon convolutional operations [2, 37, 3, 47].”

    From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [3]

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: 38

  1. L. Bertinetto, J. F. Henriques, J. Valmadre, P. H. S. Torr, and A. Vedaldi. Learning feed-forward one-shot learners. In NIPS, 2016. 2
  2. G. Bhat, J. Johnander, M. Danelljan, F. S. Khan, and M. Fels- berg. Unveiling the power of deep tracking. In ECCV, 2018. 6, 7, 8
  3. D. S. Bolme, J. R. Beveridge, B. A. Draper, and Y. M. Lui. Visual object tracking using adaptive correlation filters. In CVPR, 2010. 3
  4. J. Choi, J. Kwon, and K. M. Lee. Deep meta learning for real-time visual tracking based on target-specific feature space. CoRR, abs/1712.09153, 2017. · arXiv
  5. M. Danelljan, G. Bhat, F. S. Khan, and M. Felsberg. ATOM: Accurate tracking by overlap maximization. In CVPR, 2019. 2, 3, 5, 6, 7, 8, 12
  6. M. Danelljan, G. Häger, F. Shahbaz Khan, and M. Felsberg. Learning spatially regularized correlation filters for visual tracking. In ICCV, 2015. 2
  7. M. Danelljan, A. Robinson, F. Shahbaz Khan, and M. Fels- berg. Beyond correlation filters: Learning continuous con- volution operators for visual tracking. In ECCV, 2016. 2, 8
  8. C. Finn, P. Abbeel, and S. Levine. Model-agnostic meta- learning for fast adaptation of deep networks. In ICML, 2017. 2
  9. H. K. Galoogahi, A. Fagg, C. Huang, D. Ramanan, and S. Lucey. Need for speed: A benchmark for higher frame rate object tracking. In ICCV, 2017. 2, 6, 8, 12
  10. 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. 2
  11. D. Held, S. Thrun, and S. Savarese. Learning to track at 100 fps with deep regression networks. In ECCV, 2016. 8
  12. L. Huang, X. Zhao, and K. Huang. Got-10k: A large high- diversity benchmark for generic object tracking in the wild. arXiv preprint arXiv:1810.11981, 2018. 2, 6, 8, 12 · arXiv
  13. B. Jiang, R. Luo, J. Mao, T. Xiao, and Y. Jiang. Acquisition of localization confidence for accurate object detection. In ECCV, 2018. 4
  14. H. Kiani Galoogahi, A. Fagg, and S. Lucey. Learning background-aware correlation filters for visual tracking. In ICCV, 2017. 2, 7
  15. D. P. Kingma and J. Ba. Adam: A method for stochastic optimization. In ICLR, 2014. 6
  16. M. Kristan, A. Leonardis, J. Matas, M. Felsberg, R. Pfugfelder, L. C. Zajc, T. Vojir, G. Bhat, A. Lukezic, A. Eldesokey, G. Fernandez, and et al. The sixth visual ob- ject tracking vot2018 challenge results. In ECCV workshop, 2018. 2, 7, 12
  17. M. Kristan, J. Matas, A. Leonardis, M. Felsberg, L. Čehovin, G. Fernández, T. Vojír, G. Nebehay, R. Pflugfelder, and G. Hger. The visual object tracking vot2015 challenge re- sults. In ICCV workshop, 2015. 12
  18. B. Li, W. Wu, Q. Wang, F. Zhang, J. Xing, and J. Yan. Siamrpn++: Evolution of siamese visual tracking with very deep networks. In CVPR, 2019. 7, 8, 12
  19. 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
  20. T. Lin, M. Maire, S. J. Belongie, L. D. Bourdev, R. B. Gir- shick, J. Hays, P. Perona, D. Ramanan, P. Dollár, and C. L. Zitnick. Microsoft COCO: common objects in context. In ECCV, 2014. 6, 12
  21. C. Ma, J.-B. Huang, X. Yang, and M.-H. Yang. Hierarchical convolutional features for visual tracking. In ICCV, 2015. 2, 8
  22. M. Mueller, N. Smith, and B. Ghanem. A benchmark and simulator for uav tracking. In ECCV, 2016. 2, 6, 8, 12
  23. M. Müller, A. Bibi, S. Giancola, S. Al-Subaihi, and B. Ghanem. Trackingnet: A large-scale dataset and bench- mark for object tracking in the wild. In ECCV, 2018. 2, 6, 8, 12
  24. T. Munkhdalai and H. Yu. Meta networks. Proceedings of machine learning research, 70:2554-2563, 2017. 2
  25. D. B. Naik and R. J. Mammone. Meta-neural networks that learn by learning. [Proceedings 1992] IJCNN Inter- national Joint Conference on Neural Networks, 1:437-442 vol.1, 1992. 2
  26. H. Nam and B. Han. Learning multi-domain convolutional neural networks for visual tracking. In CVPR, 2016. 2, 8
  27. J. Nocedal and S. J. Wright. Numerical Optimization. Springer, 2nd edition, 2006. 4
  28. E. Park and A. C. Berg. Meta-tracker: Fast and robust online adaptation for visual object trackers. In ECCV, 2018. 2
  29. S. Ravi and H. Larochelle. Optimization as a model for few- shot learning. In ICLR, 2017. 2
  30. S. Ren, K. He, R. B. Girshick, and J. Sun. Faster R-CNN: towards real-time object detection with region proposal net- works. In NIPS, 2015. 2
  31. J. Schmidhuber. Evolutionary principles in self-referential learning. on learning now to learn: The meta-meta-meta...- hook. Diploma thesis, Technische Universitat Munchen, Germany, 14 May 1987. 2
  32. C. Sun, D. Wang, H. Lu, and M. Yang. Correlation tracking via joint discrimination and reliability learning. In CVPR, 2018. 7
  33. R. Tao, E. Gavves, and A. W. M. Smeulders. Siamese in- stance search for tracking. In CVPR, 2016. 2
  34. J. Valmadre, L. Bertinetto, J. F. Henriques, A. Vedaldi, and P. H. S. Torr. End-to-end representation learning for correla- tion filter based tracking. In CVPR, 2017. 2, 7, 8
  35. Q. Wang, Z. Teng, J. Xing, J. Gao, W. Hu, and S. J. Maybank. Learning attentions: Residual attentional siamese network for high performance online visual tracking. In CVPR, 2018. 2
  36. T. Xu, Z. Feng, X. Wu, and J. Kittler. Learning adaptive dis- criminative correlation filters via temporal consistency pre- serving spatial feature selection for robust visual tracking. CoRR, abs/1807.11348, 2018. 7 · arXiv
  37. Y. Yao, X. Wu, S. Shan, and W. Zuo. Joint representation and truncated inference learning for correlation filter based tracking. In ECCV, 2018. 2
  38. Z. Zhu, Q. Wang, L. Bo, W. Wu, J. Yan, and W. Hu. Distractor-aware siamese networks for visual object track- ing. In ECCV, 2018. 2, 7, 8

Cited by

Sorted by citations

Authors
Bhat, G., Danelljan, M., Van Gool, L., & Timofte, R.
Affiliations
ETH Zurich (CH)
ORCID
Venue
2019 IEEE/CVF International Conference on Computer Vision (ICCV)
Publisher
IEEE
Published
2019-10
Pages
6181-6190
DOI
10.1109/iccv.2019.00628
OpenAlex
W2936520980
Cited by
1,515
References
6
Citations by year
2026: 98 · 2025: 218 · 2024: 301 · 2023: 314 · 2022: 259 · 2021: 220 · 2020: 94 · 2019: 10 · 2018: 1
FWCI
47.52
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
Nvidia
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
visual object tracking, end-to-end tracking, discriminative loss, Siamese tracking, real-time tracking

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