Region Covariance: A Fast Descriptor for Detection and Classification

By Oncel Tuzel, Fatih Murat Porikli, Peter Meer. 2006

1,478 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Media Technology

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

When Kernel Methods Meet Feature Learning: Log-Covariance Network for Action Recognition From Skeletal Data (2017, methodology): “In addition to Bregman-divergence of the infinite covariance representation [11] and the fast region covariance descriptor of [34], we included the trial-specific encoding of an action with a Gram matrix [37] reporting both Ker-RP-POL and Ker-RP-RBF (polynomial vs.”
Covariance Tracking using Model Update Based on Lie Algebra (2006, methodology): “To overcome the shortcomings of the existing approaches, we proposed a covariance matrix representation to describe the object windows.”
Online action recognition using covariance of shape and motion (2014, methodology): “The covariance descriptor [17,18], originally designed for object detection, was recently successfully employed for action recognition [19–21].”
Shape and Appearance Context Modeling (2007, methodology): “Recently, [22] used (3) as a region descriptor to perform object detection and texture classification, where f(x) was the output of a bank of filters applied to the input image I(x).”
Kernelized covariance for action recognition (2016, methodology): “Precisely, the following algorithms were compared in our experiments: RegionCOV [23] (covariance region descriptor), temporal pyramid of covariance descriptors (Hierarchy of COVs) [16] and, finally, an infinite covariance operator which exploits Bregman divergence, namely COV-JH-SVM [29].”
Few-Shot Learning via Saliency-Guided Hallucination of Samples (2019, methodology): “Second-order statistics have been studied in the context of texture recognition [35, 30] via so-called Region Covariance Descriptors (RCD), often applied to semantic segmentation [5] and object category recognition [17, 18].”
Color Invariants for Person Reidentification (2013, background): “In addition, surveillance cameras are often of a low resolution.”
A survey on face detection in the wild: Past, present and future (2015, background): “Region covariance is another statistics based feature, proposed in [89] for generic object detection and texture classification tasks.”
Multi-target tracking by on-line learned discriminative appearance models (2010, methodology): “The distance measurement of covariance matrices is described in [23]: σ(Ci,Cj) = √√√√ 5 ∑”
Deep Learning for Generic Object Detection: A Survey (2018, background): “Handcrafted local invariant features gained tremendous popularity, starting from the Scale Invariant Feature Transform (SIFT) feature [139], and the progress on various visual recognition tasks was based substantially on the use of local descriptors [145] such as Haar like features [213], SIFT [140]”
Geodesic Convolutional Neural Networks on Riemannian Manifolds (2015, methodology): “Covariance (COV) layer is used in applications such as retrieval where one needs to aggregate the point-wise descriptors and produce a global shape descriptor [46],”
Gabor-Based Region Covariance Matrices for Face Recognition (2008, methodology): “[18] proposed to use eigenvalue-based distance”
Vehicle detection in aerial imagery : A small target detection benchmark (2016, methodology): “…but also histogram of gradients (HOG) ( e.g. [4, 62]), bag-of-words ( e.g. [63]), multi-scale spatial pyramids [64], covariance descriptors ( e.g. [38]), co-occurrence features ( e.g. [65]), local binary patterns ( e.g. [66]), color-self-similarity ( e.g. [67]), or combinations of such features (…”
Visual saliency estimation by nonlinearly integrating features using region covariances. (2013, methodology): “Hence, to compute the distance between two covariances C1 and C2, Tuzel et al. (2006) suggested using the metric proposed by Föerstner and Moonen (1999): qðC1;C2Þ ¼ ffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiffiXn i¼1 ln2kiðC1;C2Þ s ð3Þ where…”
Online Object Tracking: A Benchmark (2013, methodology): “In addition to template, many other visual features have been adopted in tracking algorithms, such as color histograms [16], histograms of oriented gradients (HOG) [17, 52], covariance region descriptor [53, 46, 56] and Haar-like features [54, 22].”
Spatio-Temporal Graph Convolution for Skeleton Based Action Recognition (2018, background): “Data Processing As skeletal data is usually captured from multi-view points and human actions are independent on the user coordinate system, we modify the origin of the coor-Table Method Accuracy Multi-part Bag-of-Poses (Seidenari et al. 2013) 82.00% Riemannian Manifold (Devanne et al. 2015) 87.04% ”