Pedestrian Detection via Classification on Riemannian Manifolds
By Oncel Tuzel, Fatih Murat Porikli, Peter Meer. IEEE Transactions on Pattern Analysis and Machine Intelligence, 2008
1,065 citations recorded by the source corpus.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Ocean Engineering
View Paper: https://www.semanticscholar.org/paper/33e46a618fdb22d46951f548d6ceeb384e7f1687
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
- Bernt Schiele
- Xiaogang Wang
- Luc Van Gool
- Wanli Ouyang
- Trevor Darrell
- Ross B. Girshick
- Xiaoou Tang
- Rodrigo Benenson
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Xiaogang Wang
- Dacheng Tao
- Ming-Hsuan Yang
- Yi Yang
- Bernt Schiele
- Jitendra Malik
- Wanli Ouyang
In Ocean Engineering
- Xiaogang Wang
- Xiaoou Tang
- Wanli Ouyang
- Bernt Schiele
- Shanshan Zhang
- Mehrtash Harandi
- Mathieu Salzmann
- Richard I. Hartley
Citations in the corpus
- Approximate Log-Hilbert-Schmidt Distances between Covariance Operators for Image Classification (2016, background): “This representation has been demonstrated to work very well in numerous vision tasks, including tracking [24], object detection and classification [31, 30], and image retrieval [7].”
- Filtered channel features for pedestrian detection (2015, background): “Covariance) Another pop ular way to encode richer information is to compute the co variance amongst features (commonly colour, gradient, and oriented gradient) [38, 29].”
- Online action recognition using covariance of shape and motion (2014, methodology): “[18] show that covariance descriptors lie in a nonlinear Riemannian space.”
- Local Descriptors Encoded by Fisher Vectors for Person Re-identification (2012, methodology): “In order to capture the local properties of images, we have designed a very simple 7-d descriptor inspired by [21]:”
- Sparse Coding and Dictionary Learning for Symmetric Positive Definite Matrices: A Kernel Approach (2012, background): “A notable example is the covariance descriptor [3], which offer a compact way of describing regions/cuboids in images/videos and fusion of multiple features.”
- CoDeL: A Human Co-detection and Labeling Framework (2013, methodology): “Follow-up methods extend it to combination with color [14], texture feature [23, 25], etc.”
- Efficient HOG human detection (2011, background): “Region covariance matrix (RCM) [18] [7] is among the state-of-the-art features for human detection.”
- Multiclass Brain–Computer Interface Classification by Riemannian Geometry (2012, methodology): “) operator consists in keeping the upper triangular part of a symmetric matrix and vectorizing it by applying unity weight for diagonal elements and √ 2 weight for outof-diagonal elements [8].”
- Brownian descriptor: A rich meta-feature for appearance matching (2014, methodology): “We evaluate our approach on tracking related applications, demonstrating that the Brownian descriptor outperforms the classical covariance in terms of matching accuracy and efficiency.”
- Pedestrian Detection: An Evaluation of the State of the Art (2012, positive): “Tuzel et al. [64] utilized covariance matrices computed locally over various features as object descriptors.”
- Joint Deep Learning for Pedestrian Detection (2013, background): “It has attracted a great deal of research interest [2, 5, 12, 47, 8].”