On-line Boosting and Vision

By Helmut Grabner, Horst Bischof. Computer Vision and Pattern Recognition, 2006

1,131 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/075bfb99ce2dbaa2005500dff90f893b7caa68c2

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

Detection and Tracking of Multiple, Partially Occluded Humans by Bayesian Combination of Edgelet based Part Detectors (2007, neutral): “There is some existing work on online learning of classiﬁers for object detection and tracking, (e.g., Avidan, 2005; Grabner and Bischof, 2006).”
Robust Object Tracking via Sparse Collaborative Appearance Model (2014, background): “Although numerous update approaches have been proposed [1], [4], [5], [7], [15], straightforward and frequent updates of tracking results may gradually result in drifts due to accumulated errors, especially when occlusion occurs.”
Boosting for transfer learning with multiple sources (2010, background): “Some related work has extended boosting for multi-task learning [26] and on-line incremental learning [12].”
On-line Random Forests (2009, background): “Compared to other adaptive tracking-by-detection methods, e.g., on-line boosting [11], we show that our algorithm is more stable and more resistant to occlusions due to higher noise tolerance and the possibility to forget information by controlled discarding of entire trees.”
Robust Multiperson Tracking from a Mobile Platform (2009, background): “In such cases, background subtraction [49], [52] is no longer a viable option and tracking-by-detection appears to be the most promising alternative [1], [2], [19], [21], [29], [32], [39], [57], [60].”
You'll never walk alone: Modeling social behavior for multi-target tracking (2009, background): “To this end, researchers have focused on improving the appearance model [10, 5], the object detector [2, 7, 9, 22], and/or the optimization strategy [14, 16, 23].”
Recent advances and trends in visual tracking: A review (2011, methodology): “Many state-of-the-art discriminative online learning based tracking methods [85,87–89, 93”
Multi-target tracking by on-line learned discriminative appearance models (2010, methodology): “To enhance the appearance model for tracking, several methods [4] [7] [9] [13] obtain dynamic feature selection or the target observation model by online learning techniques.”
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.”
Online Multiperson Tracking-by-Detection from a Single, Uncalibrated Camera (2011, methodology): “Similarly, tracking can be performed by exploiting a classifier trained to distinguish between object and background [2], [17].”
Towards Scalable Dataset Construction: An Active Learning Approach (2008, neutral): “Several sophisticated online learning schemes have been proposed for boosting ([20,21]), but we consider two simple, heuristic schemes.”
Multiobject tracking as maximum weight independent set (2011, background): “Tracking-bydetection approaches have demonstrated impressive results in addressing these challenges [16, 8, 13, 22, 1, 10, 23, 3, 4].”
People-tracking-by-detection and people-detection-by-tracking (2008, background): “Tracking by detection has been a focus of recent work [18, 8, 27, 1].”
Robust object tracking via sparsity-based collaborative model (2012, background): “Numerous successful update approaches have been proposed [6, 10, 3, 21, 19].”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “In addition, we also select ﬁve baseline trackers, Frag [60], IVT [4], MIL [13], OAB [11] and CT [55] for comparison.”
Online sketching hashing (2015, methodology): “The online Boosting [29] was further applied to obtain an online feature selection approach [10].”