Probabilistic boosting-tree: learning discriminative models for classification, recognition, and clustering

By Zhuowen Tu. Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1, 2005

499 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/1e56ae29377bff8e04336c778cac011f2bcf2b88

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

Detecting People Looking at Each Other in Videos (2013, background): “…two main strands in previous work: 2D approaches, where detectors are built for several aspects of the head [such as frontal and proﬁle Sivic et al. (2009)] or the pose is classiﬁed into discrete viewpoints (Tu 2005; Benfold and Reid 2008; Zhu and Ramanan 2012), or regressed (Osad-chy et al. 2007).”
Auto-context and its application to high-level vision tasks (2008, methodology): “where p(li|) is the classification model learned by boosting node in the tree. The details can be found in [ 23 ].”
Auto-Context and Its Application to High-Level Vision Tasks and 3D Brain Image Segmentation (2010, methodology): “We adopt the probabilistic boosting tree (PBT) algorithm [23] as it learns and computes a discriminative model in a hierarchical way by”
Decision Forests for Classification, Regression, Density Estimation, Manifold Learning and Semi-Supervised Learning (2011, background): “Abundant literature has shown the advantage of fusing together multiple simple learners of different types [87, 95, 102, 105].”
Combining randomization and discrimination for fine-grained image categorization (2011, methodology): “Our method differs from [18] in that for each tree node, we train an SVM classifier from one of the randomly sampled image regions, instead of using AdaBoost to combine weak features from a fixed set of regions.”
AI in Medical Imaging Informatics: Current Challenges and Future Directions (2020, unknown): “Analternative classiﬁcationmethodisprovidedbyprobabilisticboostingtrees [97],whichformsabinarytreeofstrongclassiﬁersusinga boosting approach to train each node by combining a set of weak classiﬁers.”
Integral Channel Features (2009, background): “Considerable recent progress has been made both on learning [8, 10, 24, 26] and features design [5, 23, 28].”
On Oblique Random Forests (2011, methodology): “In this we follow the idea also used, for example, in probabilistic boosting trees [43], which use “strong” discriminative model at each node to obtain overall better decision rules.”
Multi-Scale Deep Reinforcement Learning for Real-Time 3D-Landmark Detection in CT Scans (2019, background): “, extremely randomized trees [10] and probabilistic boosting trees [23]; or deep learning, e.”
A Survey of Recent Advances in Face Detection (2010, methodology): “Learn without Cluster and then train [84] subcategory Exemplar-based learning [85] labels Probabilistic boosting tree [90] Cluster with selected features [103] Multiple classifier/category boosting [41, 3, 116]”
Detecting Object Boundaries Using Low-, Mid-, and High-level Information (2007, methodology): “classifier which is easy to learn and fast to compute, therefore we adopt the recently proposed edge detector, BEL [ 6], which is built on top of a probabilistic boosting tree classifier [ 17 ].”
"Here's looking at you, kid". Detecting people looking at each other in videos (2011, background): “There are two main strands in previous work: 2D approaches, where detectors are built for several aspects of the head (such as frontal and profile [27]) or the pose is classified into discrete viewpoints [4, 28], or regressed [20].”
Four-Chamber Heart Modeling and Automatic Segmentation for 3-D Cardiac CT Volumes Using Marginal Space Learning and Steerable Features (2008, methodology): “Therefore, the same approach is used to train a boundary detector using the PBT [31] and steerable features.”