Robust tracking using local sparse appearance model and K-selection

By Baiyang Liu, Junzhou Huang, Lin Yang, Casimir A. Kulikowski. Computer Vision and Pattern Recognition, 2011

532 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Electrical and Electronic Engineering, Signal Processing

View Paper: https://www.semanticscholar.org/paper/625e4ee7dce9e6e4183bfebfd8be532172697142

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Electrical and Electronic Engineering

In Signal Processing

Citations in the corpus

SemiContour: A Semi-supervised Learning Approach for Contour Detection (2016, background): “Sparse representation has been proven to be effective to represent local image patches [24, 35, 21].”
Object Tracking Benchmark (2015, methodology): “To enhance tracking robustness, a local sparse appearance model was proposed in [48] with the mean shift algorithm to locate objects.”
Robust object tracking via sparsity-based collaborative model (2012, methodology): “For generative methods, tracking is formulated as searching for the most similar region to the target object within a neighborhood [6, 1, 21, 19, 16, 15].”
Tracking via Robust Multi-task Multi-view Joint Sparse Representation (2013, background): “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].”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, background): “, 2012), LSK (Liu et al., 2011) and DFT (Sevilla-Lara & LearnedMiller, 2012), and DeepTrk (Li et al.”
Robust Visual Tracking via Convolutional Networks Without Training (2015, methodology): “…61402233, Grant 41501377, Grant 61532009, Grant 61272223, and Grant 61370036, in part by the National Science Foundation of Jiangsu Province under Grant BK20151529, and in part by the Startup Foundation for Introducing Talent of Nanjing University of Information Science and Technology under Grant…”
In defense of color-based model-free tracking (2015, background): “[29, 30, 32]) which have been shown to perform favorably when tracking highly non-rigid objects or considering partial occlusions.”
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration (2014, methodology): “Success plots of OPE − deformation (19) SAMF [0.624] KCF [0.534] SCM [0.448] DFT [0.439] CN [0.438] Struck [0.393] TLD [0.378] VTD [0.377] LSK [0.377] ASLA [0.372] (c) 0 10 20 30 40 50 0 0.1 0.2 0.3 0.4 0.5 0.6 0.7 0.8 0.9 Location error threshold”
Robust Object Tracking via Sparse Collaborative Appearance Model (2014, methodology): “In this work, we present a collaborative observation model that integrates a discriminative classifier based on holistic templates and a generative model using local representations.”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, background): “Although demonstrated success of the trackers based local sparse appearance model [23], [25], [50], [51], their performance on the recently tracking benchmark [53] is not favorable.”
Online Object Tracking: A Benchmark (2013, methodology): “2Some source codes [36, 58] are obtained from direct contact, and some methods are implemented on our own [44, 16].”
Visual tracking via adaptive structural local sparse appearance model (2012, methodology): “Sparse representation has been successfully applied in numerous vision applications [21, 16, 12, 17, 11].”
Robust Visual Tracking via Structured Multi-Task Sparse Learning (2012, methodology): “Recently, sparse representation (Candès et al. 2006) has been successfully applied to visual tracking (Mei and Ling 2011; Mei et al. 2011; Liu et al. 2010, 2011).”
Discriminative Scale Space Tracking (2016, unknown): “[15], [16] or discriminative [1], [3], [17], [18] approaches.”
A Survey of Sparse Representation: Algorithms and Applications (2015, background): “[207] introduced a local sparse appearance model (SPT) with a static sparse dictionary learned from k-selection and dynamic updated basis distribution to eliminate potential drifting problems in the process of visual tracking.”
Self-Paced Learning for Long-Term Tracking (2013, background): “Generative subspace models of appearance are common [12, 13], including recent work that makes use of sparse reconstructions [14, 15].”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “To further increase the discriminative ability, a more discriminative appearance model based on sparse coding was proposed in Liu et al. [40] where the dictionary was directly learned using the patches sampled from the target image.”