Robust Visual Tracking using 1 Minimization

By Xue Mei, Haibin Ling. 2009

523 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/f317983dfb75ff280d314f9538bb185dc51c6147

How researchers see this paper

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

Citations in the corpus

Learning Adaptive Discriminative Correlation Filters via Temporal Consistency Preserving Spatial Feature Selection for Robust Visual Object Tracking (2018, background): “Recently, trackers based on sparse and low-rank representations had also achieved robust results by considering structural constraints and manifold information [24]–[28].”
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).”
Minimum error bounded efficient ℓ1 tracker with occlusion detection (2011, methodology): “Particle filter for L1-Tracker 1: At t = 0, initialize samples x i 0 , for i = 1, 2, · · · , N 2: for t = 1 to number of frames do 3: for i = 1 to number of samples do 4: Draw sample x i t with respect to p(x t |x t−1 ) 5: Prepare the observation y i t from x i t .”
Modeling and Propagating CNNs in a Tree Structure for Visual Tracking (2016, methodology): “Some algorithms employ multiple models [38, 28, 40], multi-modal representations [11] or nonlinear classifiers [10, 12] to address these issues.”
Robust Visual Tracking and Vehicle Classification via Sparse Representation (2011, background): “A preliminary conference version of this paper appears in [34].”
Learning deep features for multiple object tracking by using a multi-task learning strategy (2014, background): “Model-free object tracking approaches can be divided into two categories: generative [8, 9, 10, 11, 12] and discriminative [13, 14, 15, 16, 17].”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, methodology): “R-CNN [13] applies a CNN to an object detection task, where the training data are scarce, by pretraining on a large auxiliary dataset and ﬁne-tuning on the target dataset.”
A survey of appearance models in visual object tracking (2013, unknown): “…techniques 13 [Lim et al. 2006; Chin and Suter 2007] — — Nonlinear subspace learning Local linear embedding Kernel principle component analysis 14 [Mei and Ling 2009; Li et al. 2011] [Zhang et al. 2012; Jia et al. 2012] [Bao et al. 2012] — — Sparse representation 1 sparse approximation 15 [Li…”
Real-time part-based visual tracking via adaptive correlation filters (2015, methodology): “In [31], a series of target trivial templates were used to model the tracked target with the sparsity constraints.”
Learning Collaborative Sparse Representation for Grayscale-Thermal Tracking (2016, methodology): “Sparse representation, directly related to compressed sensing [12], has recently attracted much attention in visual tracking [13]–[16].”
Robust Object Tracking via Sparse Collaborative Appearance Model (2014, methodology): “In [17], an algorithm based on histograms of local sparse representation for object tracking is 1Preliminary results of this work are presented in [25]. proposed where the target object is located via mode seeking (using the mean shift algorithm) of voting maps constructed by reconstruction errors.”
Real-time visual tracking using compressive sensing (2011, methodology): “Our algorithms are up to about 5, 000 times faster than the standard `1 tracker of [5].”
A Survey of Sparse Representation: Algorithms and Applications (2015, methodology): “employed the idea of sparse representation to visual tracking [200] and vehicle classification [201], which introduced nonnegative sparse constraints and dynamic template updating strategy.”
Graph mode-based contextual kernels for robust SVM tracking (2011, methodology): “Specifically, the six competing trackers are referred to as SVMWC (SVM without using the contextual information), MIBT (multiple instance boosting-based tracker [9]), VTD (visual tracking decomposition [17]), OAB (online AdaBoost [5]), IPCA (incremental PCA [18]), and L1T (`1-minimization tracker [4”