Robust Object Tracking via Sparse Collaborative Appearance Model

By Wei Zhong, Huchuan Lu, Ming-Hsuan Yang. IEEE Transactions on Image Processing, 2014

333 citations recorded by the source corpus.

How researchers see this paper

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

Hierarchical Convolutional Features for Visual Tracking (2015, background): “These trackers can be broadly categorized into three classes: (i) deep learning tracker DLT [30] (ii) correlation filter trackers including the CSK [16], STC [35], and KCF [17]; and (iii) representative tracking algorithms using single or multiple online classifiers, including the MIL [1], Struck [1”
Object Tracking Benchmark (2015, methodology): “For better evaluation and analysis of the strength and weakness of tracking approaches, we propose to categorize the sequences by annotating them with the 11 attributes shown in Table 2.”
Visual Tracking with Fully Convolutional Networks (2015, methodology): “In [40], the generative and discriminative models were incorporated for more accurate online tracking.”
Long-term correlation tracking (2015, methodology): “Struck [9], CT [29], and ASLA [13]); and (iii) tracking by multiple online classifiers (TLD [14], SCM [30], MEEM [27], and TGPR [8]).”
Kernel Cross-Correlator (2017, methodology): “KCC performs signiﬁcantly better than all the methods reported in (Wu, Lim, and Yang 2013), with an average relative improvement of 20% with respect to the best tracker evaluated in the original benchmark (SCM (Zhong, Lu, and Yang 2014)).”