Coloring Local Feature Extraction

By Joost van de Weijer, Cordelia Schmid. European Conference on Computer Vision, 2006

514 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/f4fb18a9f0d3a849d314daef1053d369998c5144

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

In Media Technology

Citations in the corpus

Adaptive Color Attributes for Real-Time Visual Tracking (2014, background): “Opp-Angle: The Opp-Angle is a 36-dimensional histogram representation [22] based on ang x = arctan ( O1x O2x ) , where the subscript x denotes the spatial derivative.”
TagProp: Discriminative metric learning in nearest neighbor models for image auto-annotation (2009, methodology): “Then, the mean precision P and recall R over keywords are computed.”
Intelligent multi-camera video surveillance: A review (2013, background): “Other color invariants (Cheng and Piccardi, 2006; Slater and Healey, 1996; Weijer and Schmid, 2006) are also proposed .”
50 Years of object recognition: Directions forward (2013, methodology): “van de Weijer and Schmid [368] ** * ** ** *** * * *”
Learning Multiple Views with Orthogonal Denoising Autoencoders (2016, methodology): “15 image features are chosen from [15] as visual descriptors: local SIFT features [27]; local hue histograms [28] (both were computed on a dense multi-scale grid and on regions found with a Harris interest-point detector); global color histograms over RGB, HSV, and LAB color spaces; the above histog”
Feature representation for statistical-learning-based object detection: A review (2015, methodology): “Hue-SIFT [72] is the concatenation of the hue histogram and SIFT features.”
Semantic Hierarchies for Visual Object Recognition (2007, background): “Due to the strong reasoning, however, each node of the semantic graph is addi- 2The object synset is defined as a visible entity. tionally supported by the union of the exemplars supporting the nodes that point to it through hypernymy or meronymy links, i.e., supp(A) = ⋃ Bi→A supp(Bi) ∪ lbl(A)…”
Human Reidentification with Transferred Metric Learning (2012, background): “Many visual features of characterizing color [5, 6], shape [7, 8] and texture [9–11] of objects have been proposed.”
A comprehensive review of current local features for computer vision (2008, methodology): “Existing descriptors can be categorized into the following ﬁve types: (i) ﬁlter-based descriptors [17,25,61], (ii) distribution-based descriptors [9,34,37,42,48], (iii) textons [40,81,82], (iv) derivative-based descriptors [23,36,63], and (v) others [12,79,80].”
Scale Invariant Feature Transform (2012, methodology): “Van de Weijer and Schmid (2006) concatenated the SIFT descriptor with either weighted hue or opponent angle histograms and evaluated the performance of the resulting composed image descriptors for computing point matches on different data sets.”
Scene Classification Using a Hybrid Generative/Discriminative Approach (2008, methodology): “Other ways of using color with SIFT features have been proposed in [12], [34].”
Multimodal semi-supervised learning for image classification (2010, methodology): “As in [10], we use local SIFT features [14], and local hue histograms [22], both were computed on a dense multiscale grid and on regions found with a Harris interest-point detector.”
Scene Segmentation with CRFs Learned from Partially Labeled Images (2007, unknown): “D hue descriptor of [12] and vector quantize it against a k h = 100 word color dictionary learned from the training set.”
Topic regression multi-modal Latent Dirichlet Allocation for image annotation (2010, methodology): “In addition, we follow the work in [13] and add additional 36-dim robust color descriptors which have been designed to complement the SIFT descriptors extracted from the gray-scale patches.”
Satellite Image Classification via Two-Layer Sparse Coding With Biased Image Representation (2011, methodology): “To introduce the category sparsity, we bring a set of coefficients, ζt = [ζt1, ζ t 2, . . . , ζ t L] T , to measure the weights of the selected categories ζtl = λ N∑ i=1 δ[ci = l]α t i (6) where λ is a tuning parameter.”
Shared Segmentation of Natural Scenes Using Dependent Pitman-Yor Processes (2008, methodology): “We describe the texture and color of each superpixel via local histograms: a gradient-based SIFT descriptor [27], as well as a robust hue descriptor [28].”
Color attributes for object detection (2012, methodology): “Photometric invariance theory provides guidelines on how to ensure invariance with respect to such events [19, 17], however photometric invariance comes at the cost of discriminative power.”
A Bayesian Model for Simultaneous Image Clustering, Annotation and Object Segmentation (2009, background): “Each superpixel is represented by both color and texture descriptors, based on the local RGB, hue [25] featur vectors and also the output of maximum response (MR) filter banks [22] ( http://www.”
A Color-Texture-Structure Descriptor for High-Resolution Satellite Image Classification (2016, background): “Methods that combine cues prior to feature extraction are called early fusion methods [32,41,42].”
Emotion related structures in large image databases (2010, methodology): “Color descriptor: The color descriptor proposed by Weijer and Schmid [29] is an extension to SIFT, where photometric invariant color histograms are added to the original SIFT descriptor.”