Boosting Image Retrieval

By Kinh H. Tieu, Paul A. Viola. Proceedings IEEE Conference on Computer Vision and Pattern Recognition. CVPR 2000 (Cat. No.PR00662), 2000

733 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/eda4ebc9529f7b4cd53e47f051999a26134c0191

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

Using the Forest to See the Trees: A Graphical Model Relating Features, Objects, and Scenes (2003, methodology): “For the weak classifiers we use decision stumps [ 12 ], i.e., each picks a single component of the feature vector and chooses the corresponding optimal threshold.”
A Discriminative Kernel-Based Approach to Rank Images from Text Queries (2008, background): “This classification problem is typically addressed using Support Vector Machines (SVMs) [33], [46] or boosting classifiers [43], as these large margin approaches enjoy good generalization properties [45].”
Robust Real-time Object Detection (2001, methodology): “Motivated by the work of Tieu and Viola, feature selection is achieved through a simple modification of the AdaBoost procedure: the weak learner is constrained so that each weak classifier returned can depend on only a single feature [17].”
Large Scale Online Learning of Image Similarity Through Ranking (2009, methodology): “Figure 6 and Table 4 compare the precision obtained with OASIS, with four competing approaches , as described above (Section 5.3.1).”
Content based image retrieval using motif cooccurrence matrix (2004, background): “Tieu and Viola [15] propose to mix one or more features by computing a very large number of highly selective features and comparing these features over a set of known relevant images and using only those features, which capture the similarity amongst these sets.”
Person Re-identification by Descriptive and Discriminative Classification (2011, methodology): “In the second stage of our system we apply a discriminative model, which is estimated by Boosting for Feature Selection [19, 21].”
WhittleSearch: Image search with relative attribute feedback (2012, methodology): “We use a binary feedback baseline that is intended to represent traditional approaches such as [3, 7, 22, 25].”
Robust Real-Time Face Detection (2001, unknown): “Motivated by the work of Tieu and Viola (2000) feature selection is achieved using the AdaBoost learning algorithm by constraining each weak classifier to depend on only a single feature.”
Object tracking: A survey (2006, methodology): “Adaboost is a method for .nding a strong classi.er based on a combination of moderately inaccurate weak classi.ers.”
A Multimedia Retrieval Framework Based on Semi-Supervised Ranking and Relevance Feedback (2012, unknown): “Compared with the inductive methods, such as [28], only the query example is required.”
Asymmetric bagging and random subspace for support vector machines-based relevance feedback in image retrieval (2006, methodology): “In Tieu and Viola’s AdaBoost image retrieval [26], a set of weak two-class classifiers were incorporated by some weights and, thus, a strong classifier is built as a weighted sum of the weak classifiers.”
Image retrieval: Ideas, influences, and trends of the new age (2008, background): “Some of the other recent, more generic feature selection proposals involve boosting [Tieu and Viola 2004], evolutionary searching [Kim et al. 2000], Bayes classi.cation error [Carneiro and Vasconcelos 2005], and feature dependency/similarity measures [Mitra et al. 2002].”
Semi-supervised On-Line Boosting for Robust Tracking (2008, background): “Thus, a conﬁdence measure is provided by Furthermore, boosting can be applied for feature selection [22] where each feature corresponds to a weak classiﬁer.”
Semantic manifold learning for image retrieval (2005, methodology): “In [28], Tieu and Viola have used AdaBoost to establish a classifier for retrieval, by selecting discriminant features from a very huge candidate pool.”
FloatBoost learning and statistical face detection (2004, methodology): “The system of Viola and Jones [22], [23]makes a successful applicationofAdaBoost to facedetection, after earlierworkof Tieu and Viola [24] and Schneiderman [25].”
Recovering intrinsic images from a single image (2005, methodology): “Freeman and Viola [6] used a smoothness prior on the inferred shape in an image to classify the image as either entirely created by shading or all due to reflectance changes.”
Manifold-ranking based image retrieval (2004, background): “More recently, some researchers apply statistical learning methods to relevance feedback, which have been extensively demonstrated to outperform traditional ones [7, 24, 25, 27, 28].”