Online Metric-Weighted Linear Representations for Robust Visual Tracking

@article{Li2016OnlineML,
  title={Online Metric-Weighted Linear Representations for Robust Visual Tracking},
  author={Xi Li and Chunhua Shen and Anthony R. Dick and Zhongfei Zhang and Yueting Zhuang},
  journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
  year={2016},
  volume={38},
  pages={931-950}
}
In this paper, we propose a visual tracker based on a metric-weighted linear representation of appearance. In order to capture the interdependence of different feature dimensions, we develop two online distance metric learning methods using proximity comparison information and structured output learning. The learned metric is then incorporated into a linear representation of appearance. We show that online distance metric learning significantly improves the robustness of the tracker, especially… CONTINUE READING
Related Discussions
This paper has been referenced on Twitter 1 time. VIEW TWEETS

Citations

Publications citing this paper.
Showing 1-9 of 9 extracted citations

Sketch metric learning

2016 International Joint Conference on Neural Networks (IJCNN) • 2016
View 10 Excerpts
Highly Influenced

Not All Negatives Are Equal: Learning to Track With Multiple Background Clusters

IEEE Transactions on Circuits and Systems for Video Technology • 2018
View 1 Excerpt

Part-Based Data Association for Visual Tracking

2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA) • 2017
View 3 Excerpts

References

Publications referenced by this paper.
Showing 1-10 of 49 references

Robust Visual Tracking and Vehicle Classification via Sparse Representation

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2011
View 13 Excerpts
Highly Influenced

Struck: Structured Output Tracking with Kernels

IEEE Transactions on Pattern Analysis and Machine Intelligence • 2011
View 19 Excerpts
Highly Influenced

Online Distance Metric Learning for Object Tracking

IEEE Transactions on Circuits and Systems for Video Technology • 2011
View 4 Excerpts
Highly Influenced

Discriminative Tracking by Metric Learning

View 5 Excerpts
Highly Influenced

Visual tracking with online Multiple Instance Learning

2009 IEEE Conference on Computer Vision and Pattern Recognition • 2009
View 4 Excerpts
Highly Influenced

Incremental Learning for Robust Visual Tracking

International Journal of Computer Vision • 2007
View 4 Excerpts
Highly Influenced

Weighted random sampling with a reservoir

Inf. Process. Lett. • 2006
View 5 Excerpts
Highly Influenced

Random Sampling with a Reservoir

ACM Trans. Math. Softw. • 1985
View 4 Excerpts
Highly Influenced

Similar Papers

Loading similar papers…