CoChat
Sign Up
Cited by 2,806Video Surveillance and Tracking MethodsAdvanced Neural Network ApplicationsVisual Attention and Saliency Detection

Learning Multi-domain Convolutional Neural Networks for Visual Tracking

Open access
Nam, Hyeonseob, Han, Bohyung·2016·2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
DOI 10.1109/cvpr.2016.465
Open this paper in CoChat — free accountOpen PDF

Abstract

We propose a novel visual tracking algorithm based on the representations from a discriminatively trained Convolutional Neural Network (CNN). Our algorithm pretrains a CNN using a large set of videos with tracking ground-truths to obtain a generic target representation. Our network is composed of shared layers and multiple branches of domain-specific layers, where domains correspond to individual training sequences and each branch is responsible for binary classification to identify target in each domain. We train each domain in the network iteratively to obtain generic target representations in the shared layers. When tracking a target in a new sequence, we construct a new network by combining the shared layers in the pretrained CNN with a new binary classification layer, which is updated online. Online tracking is performed by evaluating the candidate windows randomly sampled around the previous target state. The proposed algorithm illustrates outstanding performance in existing tracking benchmarks.

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/cvpr.2016.465

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?

  • 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 [37]

    Section 2.2 (p. 2) says that only a limited number of tracking algorithms used CNN representations, contrary to the claim that almost all prevailing trackers relied on convolutional operations. The paper does describe its own CNN-based tracker with online learning (Conclusion, p. 8), but that example does not support the broader prevalence claim. (LLM, conf=0.87)

    Checked by a reasoning model — may be wrong.

    Experimental — accuracy not yet measured

  • LTMU B takes the combination of ATOM and SiamMask as the short-term tracker, MDNet as the verifier, and GlobalTrack as the global detector.

    “To be specific, LTMU B takes the combination of ATOM [9] and SiamMask [50] as the short-term tracker, MDNet [37] as the verifier, and GlobalTrack [19] as the global detector.”

    From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [37]

  • Gradient-based tracking methods require gradient computation during inference.

    “Gradient-based methods require gradient computation during inference. One of the classical works is MDNet [37], which updates domain-specific layers with gradient descent.”

    From Learning Spatio-Temporal Transformer for Visual Tracking (2021) · cites this paper as [37]

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: 33

  1. [2][2] B. Babenko, M.-H. Yang, and S. Belongie. Robust object tracking with online multiple instance learning. IEEE Trans. Pattern Anal. Mach. Intell. , 33(8):1619-1632, 2011. 2 -
  2. [3][3] D. S. Bolme, J. R. Beveridge, B. Draper, Y. M. Lui, et al. Visual object tracking using adaptive correlation filters. In CVPR , 2010. 2 -
  3. [5][5] K. Chatfield, K. Simonyan, A. Vedaldi, and A. Zisserman. Return of the devil in the details: Delving deep into convolutional nets. In BMVC , 2014. 1, 2, 3 -
  4. [6][6] M. Danelljan, G. H¨ ager, F. Khan, and M. Felsberg. Accurate scale estimation for robust visual tracking. In BMVC , 2014. 1, 2, 5, 8 -
  5. [7][7] H. Daum´ e III. Frustratingly easy domain adaptation. In ACL , 2007. 3 -
  6. [8][8] M. Dredze, A. Kulesza, and K. Crammer. Multi-domain learning by confidence-weighted parameter combination. Machine Learning , 79(1-2):123-149, 2010. 3 -
  7. [9][9] L. Duan, I. W. Tsang, D. Xu, and T.-S. Chua. Domain adaptation from multiple sources via auxiliary classifiers. In ICML , 2009. 3 -
  8. [10][10] J. Fan, W. Xu, Y. Wu, and Y. Gong. Human tracking using convolutional neural networks. IEEE Trans. Neural Networks , 21(10):1610-1623, 2010. 2 -
  9. [11][11] P. F. Felzenszwalb, R. B. Girshick, D. McAllester, and D. Ramanan. Object detection with discriminatively trained partbased models. IEEE Trans. Pattern Anal. Mach. Intell. , 32(9):1627-1645, 2010. 4 -
  10. [12][12] J. Gao, H. Ling, W. Hu, and J. Xing. Transfer learning based visual tracking with gaussian processes regression. In ECCV , 2014. 5 -
  11. [13][13] R. Girshick, J. Donahue, T. Darrell, and J. Malik. Rich feature hierarchies for accurate object detection and semantic segmentation. In CVPR , 2014. 1, 2, 4, 5 -
  12. [14][14] H. Grabner, M. Grabner, and H. Bischof. Real-time tracking via on-line boosting. In BMVC , 2006. 2 -
  13. [15][15] H. Grabner, C. Leistner, and H. Bischof. Semi-supervised on-line boosting for robust tracking. In ECCV , 2008. 2 -
  14. [16][16] B. Han, D. Comaniciu, Y. Zhu, and L. Davis. Sequential kernel density approximation and its application to real-time visual tracking. IEEE Trans. Pattern Anal. Mach. Intell. , 30(7):1186-1197, 2008. 2 -
  15. [17][17] S. Hare, A. Saffari, and P. H. Torr. Struck: Structured output tracking with kernels. In ICCV , 2011. 2, 6 -
  16. [18][18] J. F. Henriques, R. Caseiro, P. Martins, and J. Batista. Highspeed tracking with kernelized correlation filters. IEEE Trans. Pattern Anal. Mach. Intell. , 37(3):583-596, 2015. 1, 2, 5, 8 -
  17. [19][19] J. Hoffman, B. Kulis, T. Darrell, and K. Saenko. Discovering latent domains for multisource domain adaptation. In ECCV , 2012. 3 -
  18. [20][20] S. Hong, T. You, S. Kwak, and B. Han. Online tracking by learning discriminative saliency map with convolutional neural network. In ICML , 2015. 1, 2, 3, 5 -
  19. [21][21] Z. Hong, Z. Chen, C. Wang, X. Mei, D. Prokhorov, and D. Tao. MUlti-Store Tracker (MUSTer): a cognitive psychology inspired approach to object tracking. In CVPR , 2015. 1, 2, 5, 8 -
  20. [22][22] A. D. Jepson, D. J. Fleet, and T. F. El-Maraghi. Robust online appearance models for visual tracking. IEEE Trans. Pattern Anal. Mach. Intell. , 25(10):1296-1311, 2003. 2 -
  21. [24][24] Z. Kalal, K. Mikolajczyk, and J. Matas. Tracking-learningdetection. IEEE Transactions on Pattern Analysis and Machine Intelligence , 34(7):1409-1422, 2012. 2 -
  22. [28][28] H. Li, Y. Li, and F. Porikli. DeepTrack: Learning discriminative feature representations by convolutional neural networks for visual tracking. In BMVC , 2014. 2 -
  23. [30][30] J. Long, E. Shelhamer, and T. Darrell. Fully convolutional networks for semantic segmentation. In CVPR , 2015. 1, 2 -
  24. [31][31] X. Mei and H. Ling. Robust visual tracking using ℓ 1 minimization. In ICCV , 2009. 2 -
  25. [34][34] K. Simonyan and A. Zisserman. Very deep convolutional networks for large-scale image recognition. In ICLR , 2015. 1, 2, 3 -
  26. [35][35] K.-K. Sung and T. Poggio. Example-based learning for viewbased human face detection. IEEE Trans. Pattern Anal. Mach. Intell. , 20(1):39-51, 1998. 4 -
  27. [36][36] Y. Taigman, M. Yang, M. Ranzato, and L. Wolf. Deepface: Closing the gap to human-level performance in face verification. In CVPR , 2014. 1, 2 -
  28. [37][37] A. Toshev and C. Szegedy. Deeppose: Human pose estimation via deep neural networks. In CVPR , 2014. 1, 2 -
  29. [38][38] A. Vedaldi and K. Lenc. Matconvnet - convolutional neural networks for matlab. In ACM MM , 2015. 5 -
  30. [39][39] N. Wang, S. Li, A. Gupta, and D.-Y. Yeung. Transferring rich feature hierarchies for robust visual tracking. arXiv preprint arXiv:1501.04587 , 2015. 1, 2 - · arXiv
  31. [42][42] J. Zhang, S. Ma, and S. Sclaroff. MEEM: Robust tracking via multiple experts using entropy minimization. In ECCV , 2014. 1, 5, 8 -
  32. [43][43] T. Zhang, B. Ghanem, S. Liu, and N. Ahuja. Robust visual tracking via multi-task sparse learning. In CVPR , 2012. 2 -
  33. [44][44] W. Zhong, H. Lu, and M.-H. Yang. Robust object tracking via sparsity-based collaborative model. In CVPR , 2012. 6

Cited by

Sorted by citations

Authors
Nam, H., & Han, B.
Affiliations
Pohang University of Science and Technology (KR)
ORCID
Venue
2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Publisher
IEEE
Published
2016-06
Pages
4293-4302
ISSN
1063-6919 (ISSN-L)
DOI
10.1109/cvpr.2016.465
OpenAlex
W1857884451
Cited by
2,806
References
8
Citations by year
2026: 50 · 2025: 137 · 2024: 204 · 2023: 253 · 2022: 344 · 2021: 386 · 2020: 382 · 2019: 448 · 2018: 364 · 2017: 205 · 2016: 32 · 2015: 1
FWCI
121.28
Type
conference paper
Language
en
Open access
Locations
  • IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings (publishedVersion)
  • arXiv (Cornell University) (submittedVersion)
  • arXiv (Cornell University)
Funders
Institute for Information and Communications Technology Promotion
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, online tracking, binary classification, target representation, multi-branch network

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