Incremental Learning for Visual Tracking

By Jongwoo Lim, David A. Ross, Ruei-Sung Lin, Ming-Hsuan Yang. Neural Information Processing Systems, 2004

341 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/14ee8cf76e31fdf4381d29c1fb61017beb52f672

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

Real-Time Tracking via On-line Boosting (2006, methodology): “Figure 6: These sequences have been provided by Lim and Ross ([17]).”
P-N learning: Bootstrapping binary classifiers by structural constraints (2010, unknown): “The classifier 0 1000 0 1 Number of Frames Processed F-Measure 0.0 0.5 0.6 0.9 Figure 6.”
Online sketching hashing (2015, background): “Intuitively, in order to avoid the mean-varying problem, one can augment every data chunk with a virtual sample [23], which is carefully chosen to correct the time-varying mean.”
Forward-Backward Error: Automatic Detection of Tracking Failures (2010, background): “Sequence Frames [7] [4] [1] [2] T0 TFB TNCC TSSD TFB+NCC David 761 17 n/a 94 135 93 761 144 28 761 Jumping 313 75 313 44 313 36 76 87 79 170 Pedestrian 1 140 11 6 22 101 15 37 40 12 140 Pedestrian 2 338 33 8 118 37 97 97 97 97 97 Pedestrian 3 184 50 5 53 49 52 52 52 52 52 Car 945 163 n/a 10 45 248 5”
Robust Superpixel Tracking (2014, methodology): “In [3], an incremental visual tracker (IVT) with adaptive appearance model that aims to account for appearance variation of rigid or limited deformable motion is presented.”
Semi-supervised On-Line Boosting for Robust Tracking (2008, background): “There has also been considerable work along these lines, e.g. , Lim et al. [6] used incremental subspace learning for tracker updating and Avidan [7] use an adaptive ensemble of classiﬁers.”
Incremental Learning for Robust Visual Tracking (2008, methodology): “Our algorithm, a variation of which was first presented in Lim et al. (2005), has also been applied to algorithms where the subspace mean plays an important role.”
Online Action Recognition via Nonparametric Incremental Learning (2014, background): “Examples include face recognition [38], object tracking [23] and detection [45], gait recognition [21], visual tracking [29], and robot cooperation [10].”
Superpixel tracking (2011, background): “In [13], an incremental visual tracker (IVT) with adaptive appearance model that aims to account for appearance variation of rigid or limited deformable motion is presented.”
A Scale Adaptive Kernel Correlation Filter Tracker with Feature Integration (2014, background): “Meanwhile, generative model-based trackers [22] [15] [21][29] [3] [30] [24] aim to build the metric model to search the most similar patches for the tracked object.”