Learning The Discriminative Power-Invariance Trade-Off

By Manik Varma, Debajyoti Ray. IEEE International Conference on Computer Vision, 2007

590 citations recorded by the source corpus.

View Paper: https://www.semanticscholar.org/paper/36316e01657459c3d4c1e1ba3985881377b40b83

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

“Who are you?” - Learning person specific classifiers from video (2009, methodology): “Rather than using a single pre-specified kernel, the kernel is a linear combination of given base kernels [3, 19 ], with each base kernel corresponding to a different feature.”
From region similarity to category discovery (2011, methodology): “While MKL algorithms have been widely applied in computer vision applications [22, 23], most research has focused on binary classifiers (i.”
Multiple Kernel Learning Algorithms (2011, unknown): “Instead of solving this SOCP problem directly, Varma and Ray (2007) also propose an alternating optimization problem that performs projected gradient updates for kernel weights and solves a QP”
EnsembleMatrix: interactive visualization to support machine learning with multiple classifiers (2009, unknown): “Our experiments in this paper use 30 images per class (3030 images in total), and are exactly same as the ones used by Varma and Ray [34].”
Prediction of the Leadership Style of an Emergent Leader Using Audio and Visual Nonverbal Features (2017, unknown): “The only exception was the autocratic leader detec tion when binary classification was applied to holistic meetings where GMKL performed significantly better (p-value 0.01) than all others.”
Classification using intersection kernel support vector machines is efficient (2008, unknown): “[1]; Varma & Ray [26]; and Chum & Zisserman [5], which together represent some of the best results on the Caltech and Pascal VOC datasets.”
More generality in efficient multiple kernel learning (2009, methodology): “Note that the algorithm is virtually unchanged from (Varma & Ray, 2007) apart from the more general form of the kernel k and regularizer r.”
Generalized RBF feature maps for Efficient Detection (2010, methodology): “This problem is known as Multiple Kernel Learning SVM (MKL-SVM) [2, 18] where we defined a base kernel for each projection ω j.”
Character Recognition in Natural Images (2009, methodology): “An additional experiment was performed with the multiple kernel learning (MKL) method of (Varma and Ray, 2007), which gave stateof-the-art results in the Caltech256 challenge.”
Learning Hybrid Image Templates (HIT) by Information Projection (2012, background): “In recent years, by combining different types of features in a discriminative framework [25], [26], [27], [28], [29], [30], [31], [32], much progress has been made toward improving the accuracy of object categorization.”
Fast image search for learned metrics (2008, methodology): “Recent work has yielded various approaches to metric learning, including several techniques to learn a combination of existing kernels [19, 29], as well as methods to learn a Mahalanobis metric [30, 3, 8], and methods to learn example-specific local distance functions [10].”
A Survey on Multi-view Learning (2013, methodology): “As for multiple kernel learning, Kumar and Sminchisescu (2007); Lin et al. (2007) and Varma and Ray (2007) applied it to object classification by linearly combining similarity functions between images so that the combined similarity function yields improved classification performance.”
Spike and Slab Variational Inference for Multi-Task and Multiple Kernel Learning (2011, background): “In [22] it is shown that these weights can be learned by solving a convex optimization problem.”
Automated Flower Classification over a Large Number of Classes (2008, methodology): “flowers/index.html, which was introduced in [12], with the two previous publications that have classified this dataset: Nilsback and Zisserman [12], and Varma and Ray [ 16 ].”