A sparse texture representation using local affine regions

By Svetlana Lazebnik, Cordelia Schmid, Jean Ponce. 2005

1,263 citations recorded by the source corpus.

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

Deep Unsupervised Learning using Nonequilibrium Thermodynamics (2015, methodology): “Bark Texture Images A probabilistic model was trained on bark texture images (T01-T04) from (Lazebnik et al., 2005).”
COCO-Stuff: Thing and Stuff Classes in Context (2016, background): “Early stuff datasets [6, 15, 34, 9] focused on texture classification and had simple images completely covered with a single textured patch.”
Describing Textures in the Wild (2013, methodology): “Texture classification has been widely studied in the context of recognizing materials supported by datasets such as CUReT [9], UIUC [18], UMD [39], Outex [23], Drexel Texture Database [24], and KTH-TIPS [7, 14].”
Character Recognition in Natural Images (2009, background): “Spin image (Lazebnik et al., 2005), (Johnson and Herbert, 1999) is a two-dimensional histogram encoding the distribution of image brightness values in the neighborhood of a particular reference point.”
Texture Feature Extraction Methods: A Survey (2019, methodology): “[113] proposed a method that uses a set of affine Harris and Laplacian regions as texture elements.”
Remote Sensing Image Classification: No Features, No Clustering (2015, methodology): “with six other pixel sorting methods proposed in [11], [30], and [31].”
50 Years of object recognition: Directions forward (2013, methodology): “As descriptors, the authors investigated the use of SIFT, SPIN, and RIFT descriptors [373, 374].”
Description of interest regions with local binary patterns (2009, background): “The intensity-domain spin image [4] is a 2D histogram where the dimensions are the distance from the center point and the intensity value.”
Salient Objects in Clutter: Bringing Salient Object Detection to the Foreground (2018, methodology): “Based on the characteristics of non-salient objects, we collected 783 texture images from the DTD [21] dataset.”
Median Robust Extended Local Binary Pattern for Texture Classification (2016, methodology): “The CUReT database has only small rotation variations, whereas our proposed MRELBP has a strong rotation invariance property, nevertheless from Table XV we can see that the proposed MRELBP with SVM produces the highest classification score on CUReT despite the fact that we have no pretraining step, ”
Local Intensity Order Pattern for feature description (2011, methodology): “To avoid the local consistent orientation estimation, spin image [12] divides the local patch into 5 rings.”
Merging chrominance and luminance in early, medium, and late fusion using Convolutional Neural Networks (2015, neutral): “, 2005]; RIFT [Lazebnik et al., 2005]; and HMAX [Riesenhuber and Poggio, 1999].”
Semi-Local Affine Parts for Object Recognition (2004, positive): “For details about descriptor computation, see [10].”
A Completed Modeling of Local Binary Pattern Operator for Texture Classification (2010, positive): “Some works have been recently proposed for scale and affine invariant texture classification by using fractal analysis [9] [10] and affine adaption [11] [12].”