Real-Time Tracking via On-line Boosting

By Helmut Grabner, Michael Grabner, Horst Bischof. British Machine Vision Conference, 2006

1,317 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/460a435a492107e9c8ec23ae8e79b0420de619e9

How researchers see this paper

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

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Discriminative Correlation Filter Tracker with Channel and Spatial Reliability (2016, background): “Recent short-term tracking evaluations [42, 28, 29, 26] consistently confirm the advantages of semi-supervised discriminative tracking approaches [16, 1, 17, 4].”
Semi-supervised On-Line Boosting for Robust Tracking (2008, methodology): “We first briefly review the on-line boosting tracker that is based on on-line boosting for feature selection [8, 4], which is replaced by our proposed on-line SemiBoost algorithm.”
Learning Multi-domain Convolutional Neural Networks for Visual Tracking (2015, background): “These tracking algorithms typically learn classiﬁers based on multiple instance learning [2], P-N learning [24], online boosting [14, 15], structured output SVMs [17], etc.”
Visual Object Tracking for Unmanned Aerial Vehicles: A Benchmark and New Motion Models (2017, methodology): “Many advanced machine learning techniques have been applied, including boosting (Grabner, Grabner, and Bischof 2006; Grabner, Leistner, and Bischof 2008), multiple-instance learning (Babenko, Yang, and Belongie 2011), structured output support vector machine (Hare, Saffari, and Torr 2011), and…”
MEEM: Robust Tracking via Multiple Experts Using Entropy Minimization (2014, methodology): “One straightforward option, which is in the same spirit of many ensemble based tracking methods [16,7,4], is to base the loss function (or weighting function) on the likelihood of the experts, in other words, how well the experts fit the labeled training samples.”
PROST: Parallel robust online simple tracking (2010, background): “In order to allow for fast appearance changes, recent works use online learners that perform updating on the target object based on the tracking result (selfupdating) [9].”
Tracking the Untrackable: Learning to Track Multiple Cues with Long-Term Dependencies (2017, background): “To this end, many works have been improving only the appearance model [16, 6], while some have been combining the dynamics and interaction between targets with the target appearance [55, 3, 51, 71, 9, 58, 52].”
Understanding and Diagnosing Visual Tracking Systems (2015, methodology): “Thanks to advances made by machine learning researchers, many sophisticated techniques have been applied to visual tracking, including boosting [12, 13], multiple-instance learning [3], structured output SVM [14], Gaussian process regression [11], and deep learning [36, 34, 16].”
Part-based multiple-person tracking with partial occlusion handling (2012, background): “On the other hand, discriminative tracking approaches with online learning have flourished recently [1, 2, 11, 6, 10, 8].”
Struck: Structured Output Tracking with Kernels (2016, positive): “…in §4 that this approach can be straightforwardly extended to deal with other types of motion, e.g. scale can be incorporated by using parameter vectors of the form (x, y, s), where s ∈ R+ denotes a factor that can be used to scale the bounding box around the object, and choosing Y appropriately.”
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 non-linear classiﬁers [10, 12] to address these issues.”
Graph mode-based contextual kernels for robust SVM tracking (2011, methodology): “OAB learns an AdaBoost classifier for object tracking.”
Recent advances and trends in visual tracking: A review (2011, methodology): “Discriminative Method OnlineRF, MILBoosting [77–93]”
Correlation filters with limited boundaries (2014, methodology): “MOSSE KMOSSE MILTrack STRUCK OAB(1) SemiBoost FragTrack Our method [5] [13] [3] [11] [9] [10] [1] FaceOcc1 {1.”
Action-Decision Networks for Visual Tracking with Deep Reinforcement Learning (2017, methodology): “The approach based on Trackingby-Detection [10, 11, 1, 17] aims to build a discriminative classifier that distinguishes the target from the surrounding background.”
Object Tracking Benchmark (2015, methodology): “Effective update algorithms have also been proposed via online mixture model [29], online boosting [22], and incremental subspace update [47].”
Siam R-CNN: Visual Tracking by Re-Detection (2019, methodology): “Many classical methods use an online learned classifier to re-detect the object of interest over the full image [1, 21, 2, 56, 23, 57, 32].”
Large Margin Object Tracking with Circulant Feature Maps (2017, methodology): “There are many classiﬁcation algorithms used in this framework, such as multiple instance learning [1], P-N learning [17], online boosting [11, 12], support vector machines (SVM) [13, 15, 22, 31] and so on.”