Real-time visual tracking using compressive sensing

By Hanxi Li, Chunhua Shen, Javen Qinfeng Shi. Computer Vision and Pattern Recognition, 2011

314 citations recorded by the source corpus.

Subfields: Computational Mechanics, Electrical and Electronic Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1ba7a9c0e658a0d98253f999bf43c2e98c07f4e0

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. Ming-Hsuan Yang
2. Kaihua Zhang
3. Tianzhu Zhang
4. Narendra Ahuja
5. Bernard Ghanem
6. Si Liu
7. Yi Wu
8. Lei Zhang

In Electrical and Electronic Engineering

1. Ming-Hsuan Yang
2. Bernard Ghanem
3. Tianzhu Zhang
4. Martin Danelljan
5. Haibin Ling
6. Bohyung Han
7. Yi Wu
8. Kaihua Zhang

In Signal Processing

1. Chen Change Loy
2. Ping Luo
3. Xiaoou Tang
4. Dacheng Tao
5. Zhanpeng Zhang
6. Bernard Ghanem
7. Ming-Hsuan Yang
8. Lei Zhang

Citations in the corpus

• Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “In Li et al. (2011), dimensionality reduction and a customized orthogonal matching pursuit algorithm are adopted to accelerate the L 1 tracker (Mei and Ling 2011).”
• Real-Time Compressive Tracking (2012, methodology): “Second, our algorithm extracts a linear combination of generalized Haar-like features but these trackers [10][9] use the holistic templates for sparse representation which are less robust as demonstrated in our experiments.”
• Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, methodology): “[52] extended this work using the orthogonal matching pursuit algorithm to solve the optimization problem efficiently.”
• Learning Deep Representation for Face Alignment with Auxiliary Attributes (2014, background): “Early stopping is not uncommon in vision learning problems [15,23].”
• Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “In Li et al. [54], a real-time tracking algorithm was proposed, which exploits the restricted isometry property (RIP) [16] in compressive sensing to reduce the dimension of the dictionary by multiplying a hashing matrix that guarantees the RIP in the two sides of Eq.”
• Facial Landmark Detection by Deep Multi-task Learning (2014, background): “Early stopping is not uncommon in vision learning problems [13,19].”
• Real time robust L1 tracker using accelerated proximal gradient approach (2012, methodology): “Sparse representation have been applied to tracking problem in [15], and later exploited in [14, 13].”
• Tracking via Robust Multi-task Multi-view Joint Sparse Representation (2013, methodology): “Sparse representation was recently introduced for tracking in [19] which casts tracking as a sparse representation problem in a particle filter framework [11] which was later exploited in [15][16][20].”
• The Visual Object Tracking VOT2014 Challenge Results (2014, unknown): “, [39,58]) exceeds a threshold, with respect to different thresholds.”