Visual tracking decomposition

By Junseok Kwon, Kyoung Mu Lee. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

1,263 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/29e1e20323f7cb6c15c6acf5cc6573a2f84e6478

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

Online Object Tracking: A Benchmark (2013, background): “To better handle appearance variations, some approaches regarding integration of multiple representation schemes have recently been proposed [62, 51, 33].”
Self-Paced Learning for Long-Term Tracking (2013, methodology): “Inference algorithms: To capture multiple hypotheses, many trackers use sampling-based schemes such as particle filtering [21, 22] or Markov-chain Monte-Carlo techniques [23, 24].”
Locally Orderless Tracking (2012, methodology): “A second occlusion at around frame 60 throws VTD off track as well.”
Real time robust L1 tracker using accelerated proximal gradient approach (2012, background): “Only our APG-L1 tracker and VTD can track the target through the sequence.”
Online Tracking by Learning Discriminative Saliency Map with Convolutional Neural Network (2015, neutral): “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 ”
Tracking by Sampling Trackers (2011, methodology): “Among them, one of promising methods is the visual tracking decomposition (VTD), which utilizes a set of multiple trackers and runs them simultaneously and interactively [11].”
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”
Learning a Deep Compact Image Representation for Visual Tracking (2013, methodology): “VTD and DLT give satisfactory results which are followed by CT. Compared to shaking, the singer1 sequence is easier to track.”
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.”
Transfer Learning Based Visual Tracking with Gaussian Processes Regression (2014, methodology): “For fair comparison, we only compare the proposed TGPR tracker with the eight RGB competitors, including Struck [8], VTD [17], CT [41], TLD [15], MIL [2], SemiB [7] and the other 2 RGB baseline algorithms provided by the benchmark providers, RGBdet [30] and OF [30].”
Tracking-Learning-Detection (2012, background): “The generative models are either built offline [21] or during runtime [22], [23].”
Context tracker: Exploring supporters and distracters in unconstrained environments (2011, methodology): “It is also important to note that the maximum number of frames run by VTDTracker is 1000 frames; hence, its results shown in Table 1 are the average of 1000 frames at the maximum.”
Real-Time Compressive Tracking (2012, background): “The Animal, Shaking and Soccer sequences are provided in [28] and the Box and Jumping are from [29].”
Tracking Revisited Using RGBD Camera: Unified Benchmark and Baselines (2013, methodology): “We also evaluated six state-of-theart RGB trackers: TLD[15], CT[30], MIL[3], semi-B[11], Struck[12] and VTD[16], since currently there is no other public available RGBD tracking algorithms for general objects.”
Robust visual tracking via multi-task sparse learning (2012, methodology): “Other trackers experience drift at different instances: Frag at frame 248, OAB and IVT at frame 436, and VTD at frame 477.”
In defense of color-based model-free tracking (2015, background): “published video sequences from various authors (including [1, 17, 28, 29, 38]).”
Minimum error bounded efficient ℓ1 tracker with occlusion detection (2011, methodology): “The VTD starts to show some target drifting around 200 frames, and finally loses the target.”
Recent advances and trends in visual tracking: A review (2011, background): “A great breakthrough of Monte Carlo sampling methods is [125], which achieved high tracking robustness in extremely complicated scenarios.”