Robust visual tracking using ℓ1 minimization

By Xue Mei, Haibin Ling. IEEE International Conference on Computer Vision, 2009

715 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/b5e17a0ed14349d6c4066d2408409751f9595e04

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

1. Julien Mairal
2. Francis R. Bach
3. Jean Ponce
4. Peter Richtárik
5. Zeyuan Allen-Zhu
6. Jianping Shi
7. Lei Zhang
8. Jiaya Jia

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Ming-Hsuan Yang
3. Dacheng Tao
4. Xiaogang Wang
5. Trevor Darrell
6. Andrea Vedaldi
7. Jitendra Malik
8. Abhinav Kumar Gupta

Citations in the corpus

• Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models (2017, methodology): “Such methods are typically based on templates (Alt, Hinterstoisser, and Navab 2010; Matthews, Ishikawa, and Baker 2004; Arandjelović 2015), principal component analysis (Ross et al. 2008), sparse coding (Mei and Ling 2009), and dictionary learning (Wang, Wang, and Yeung 2013).”
• Siamese Instance Search for Tracking (2016, methodology): “nto the matching function. MST [6] relies on probabilistic matching. FRT [1] uses the earth mover’s distance matching. And IVT [38] matches by the metric of eigen images obtained during tracking. L1T [30] is successful with L1- metric matching on graphs of fragments. SPT [50] uses super-pixels for m”
• Understanding and Diagnosing Visual Tracking Systems (2015, methodology): “ckers typically assume a generative process of the appearance of the target and search for the most similar candidate in the video. Some representative methods are (robust) PCA [26,32], sparse coding [23], and dictionary learning [34]. On the other hand, discriminative trackers take a different appr”
• Sparse Modeling for Image and Vision Processing (2014, methodology): “It selects the new bounding box with (4.16), and then updates the dictionary D and the weights ηj , according to an ad-hoc procedure [see Mei and Ling, 2009, for the details].”
• Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, methodology): “To maintain the target appearance model, various approaches have been proposed including sparse representation (Bao et al., 2012; Jia et al., 2012; Mei & Ling, 2009; Zhang et al., 2012; Zhong et al., 2012), online density estimation (Han et al., 2008), incremental subspace learning (Ross et al.,…”