Home > Research > Publications & Outputs > High-order Tensor Regularization with Applicati...

Electronic data

Links

Text available via DOI:

View graph of relations

High-order Tensor Regularization with Application to Attribute Ranking

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Published

Standard

High-order Tensor Regularization with Application to Attribute Ranking. / Kim, Kwang In; Park, Juhyun; Tompkin, James.

2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2018. p. 4349-4357.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Kim, KI, Park, J & Tompkin, J 2018, High-order Tensor Regularization with Application to Attribute Ranking. in 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, pp. 4349-4357, EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018, 18/06/18. https://doi.org/10.1109/CVPR.2018.00457

APA

Kim, K. I., Park, J., & Tompkin, J. (2018). High-order Tensor Regularization with Application to Attribute Ranking. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 4349-4357). IEEE. https://doi.org/10.1109/CVPR.2018.00457

Vancouver

Kim KI, Park J, Tompkin J. High-order Tensor Regularization with Application to Attribute Ranking. In 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE. 2018. p. 4349-4357 https://doi.org/10.1109/CVPR.2018.00457

Author

Kim, Kwang In ; Park, Juhyun ; Tompkin, James. / High-order Tensor Regularization with Application to Attribute Ranking. 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition. IEEE, 2018. pp. 4349-4357

Bibtex

@inproceedings{64ed9af2b1444212b80f3b71482f9d85,
title = "High-order Tensor Regularization with Application to Attribute Ranking",
abstract = "When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.",
author = "Kim, {Kwang In} and Juhyun Park and James Tompkin",
note = "{\textcopyright}2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.; EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018 ; Conference date: 18-06-2018 Through 22-06-2018",
year = "2018",
month = jun,
day = "18",
doi = "10.1109/CVPR.2018.00457",
language = "English",
pages = "4349--4357",
booktitle = "2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - High-order Tensor Regularization with Application to Attribute Ranking

AU - Kim, Kwang In

AU - Park, Juhyun

AU - Tompkin, James

N1 - ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.

PY - 2018/6/18

Y1 - 2018/6/18

N2 - When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.

AB - When learning functions on manifolds, we can improve performance by regularizing with respect to the intrinsic manifold geometry rather than the ambient space. However, when regularizing tensor learning, calculating the derivatives along this intrinsic geometry is not possible, and so existing approaches are limited to regularizing in Euclidean space. Our new method for intrinsically regularizing and learning tensors on Riemannian manifolds introduces a surrogate object to encapsulate the geometric characteristic of the tensor. Regularizing this instead allows us to learn non-symmetric and high-order tensors. We apply our approach to the relative attributes problem, and we demonstrate that explicitly regularizing high-order relationships between pairs of data points improves performance.

U2 - 10.1109/CVPR.2018.00457

DO - 10.1109/CVPR.2018.00457

M3 - Conference contribution/Paper

SP - 4349

EP - 4357

BT - 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition

PB - IEEE

T2 - EventIEEE Conference on Computer Vision and Pattern Recognition (CVPR) 2018

Y2 - 18 June 2018 through 22 June 2018

ER -