Tracking by Sampling Trackers

By Junseok Kwon, Kyoung Mu Lee. Vision, 2011

445 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/68cc57640bfd04f697048534f82d16bf10a002ec

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

Citations in the corpus

Real-time part-based visual tracking via adaptive correlation filters (2015, methodology): “Generative methods treat tracking problem as searching for the regions which are the most similar to the tracked targets [3, 4, 6, 22, 24, 26– 28, 46, 52].”
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration (2014, methodology): “Figure 2 shows the detailed report of SAMF compared with the top rank trackers, KCF [14], SCM [36], Struck [11], CN [4], TLD [16], ASLA [15], CX- T [5], VTS [20], DFT [29], CPF [26], LSK [23], LOT [25] and VTD [21] in the benchmark.”
Object Tracking Benchmark (2015, background): “Even multiple trackers [34] or multiple feature sets [61] are maintained and selected in a Bayesian framework to better account for appearance changes.”
Visual Tracking: an Experimental Survey (2013, unknown): “In histogram representations the use of color is common, for example MST [54], TMC [46], HBT [63] and SPT [67], while FRT [53] and ACT [58] even use plain intensity histograms.”
Adaptive Color Attributes for Real-Time Visual Tracking (2014, methodology): “The generative methods [2, 15, 16] tackle the problem by searching for regions that are most similar to the target model.”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, unknown): “We compared our method with top 10 trackers in (Wu et al., 2013), which include SCM (Zhong et al., 2012), Struck (Hare et al., 2011), TLD (Kalal et al., 2012), ASLA (Jia et al., 2012), CXT (Dinh et al., 2011), VTD (Kwon & Lee, 2010), VTS (Kwon & Lee, 2011), CSK (Henriques et al., 2012), LSK (Liu et ”
MUlti-Store Tracker (MUSTer): A cognitive psychology inspired approach to object tracking (2015, background): “29 popular approaches whose results are available in OOTB, such as Struck [14], TLD [23], SCM [52], VTD [26], VTS [27], and ASLA [22].”
MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization (2014, background): “In [17], multiple trackers from a tracker space are sampled and combined to handle challenging scenarios.”
Robust Visual Tracking via Convolutional Networks Without Training (2015, background): “These results show that all the filers, soft shrinkage, and model update components play key roles in the proposed algorithm for robust visual tracking.”
Discriminative Scale Space Tracking (2016, unknown): “[15], [16] or discriminative [1], [3], [17], [18] approaches.”
Visual Tracking With Weighted Adaptive Local Sparse Appearance Model via Spatio-Temporal Context Learning (2018, background): “Numerous effective representations have been proposed to design the appearance models that can be categorized into either generative [19], [25]–[29] or discriminative models [11]–[18], [22], [30]–[38].”
Fast Visual Tracking via Dense Spatio-temporal Context Learning (2014, background): “Numerous algorithms have been proposed with focus on effective appearance models, which are based on the target appearance [8,1,28,22,17,18,19,23,21,31] or the difference between appearances of the target and its local background [11,16,14,2,30,15].”
Track and Segment: An Iterative Unsupervised Approach for Video Object Proposals (2016, methodology): “We first evaluate the quality of our spatio-temporal box proposals against tracking algorithms on the Visual Tracker SCM [59] Struck [20] TLD [26] ASLA [25] CXT [12] VTD [30] VTS [31] TGPR [17] RPT [34] [52] [35] We compare our unsupervised video object box proposals to state-of-the-art supervised t”
Staple: Complementary Learners for Real-Time Tracking (2015, background): “In [27, 28], Kwon et al . make use of complementary basic trackers, built by combining different observation models and motion models, and then integrate their estimates in a sampling framework.”
Gesture recognition for human-robot collaboration: A review (2017, methodology): “Since skeleton model method utilises and simpli ﬁ es point cloud information, skeleton model method is a better option for depth sensor based systems (Han et al., 2013).”
Reliable Patch Trackers: Robust visual tracking by exploiting reliable patches (2015, methodology): “To locate those patches, both trackable confidence and motion information are incorporated into the particle filter framework, which are further employed to vote for the target location and estimate the object scale.”
Online Object Tracking: A Benchmark (2013, background): “Even multiple trackers [34] or multiple feature sets [61] are maintained and selected in a Bayesian framework to better account for appearance changes.”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, methodology): “These trackers include Struck [8], SCM [45], TLD [15], ASLA [14], VTD [17], VTS [18], CXT [4], LSK [24], CSK [10], MTT [44] and LOT [27].”