Support vector machines for histogram-based image classification

By Olivier Chapelle, Patrick Haffner, Vladimir Naumovich Vapnik. 1999

Subfields: Computer Vision and Pattern Recognition

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

Constrained parametric min-cuts for automatic object segmentation (2010, methodology): “We have presented an algorithm that casts the automatic image segmentation problem as one of finding a set of plausible figure-ground object hypotheses.”
Asymmetric Minwise Hashing for Indexing Binary Inner Products and Set Containment (2015, background): “Thus in practice, often only the presence or absence information suffices [9, 20, 24].”
Learning with Distance Substitution Kernels (2004, methodology): “Statements on theoretical properties of the kernels follow in Section 3 and comments on consequences for use in SVMs are given in Section 4.”
Support vector machines in DSC‐based glioma imaging: Suggestions for optimal characterization (2010, background): “However, the choice of kernel function, a key concept of SVMs, influences prediction outcome and inappropriate kernels might result in poor performance (19,20).”
Image Labeling on a Network: Using Social-Network Metadata for Image Classification (2012, methodology): “1) (which we refer to as ‘flat’ models since they consider each image independently and thus ignore relationships between images) are routinely applied to classification based on image features [18], and have also been used for classification based on image tags, where as features one can simply cre”
Efficient Classification for Additive Kernel SVMs (2013, methodology): “In our experiments we restrict ourselves to these cases as one can approximate any function arbitrary well.”
Kernel Methods and Machine Learning (2014, unknown): “For a few examples, see [29, 35, 74, 89, 97, 103, 109, 113, 173, 184, 188, 211, 245, 256, 272, 273, 318].”
Beyond sliding windows: Object localization by efficient subwindow search (2008, methodology): “In our example, we choose the χ(2)-distance that has shown good performance for histogram-based retrieval and classification tasks [5].”
Marginalized Multi-Instance Kernels (2007, methodology): “Table 2 shows the results, along with those of the DDSVM, Hist-SVM [Chapelle et al., 1999] and MI-SVM as reported in [Chen and Wang, 2004].”
Random Fourier Approximations for Skewed Multiplicative Histogram Kernels (2010, background): “kernel [ 10 ]. However, this kernel cannot be approximated with RF. Our aim is to design a kernel that has similar performance, but fits within the RF framework.”
In Defense of Minhash over Simhash (2014, background): “It is often the case that just the presence or absence information suffices in practice [7, 14, 17, 23].”
Densifying One Permutation Hashing via Rotation for Fast Near Neighbor Search (2014, methodology): “Chapelle et al. (1999) reported good performance by using binary data for histogram-based image classification.”