Home > Research > Publications & Outputs > Context-guided diffusion for label propagation ...

Electronic data

  • ICCV2015

    Rights statement: ©2015 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.

    Accepted author manuscript, 369 KB, PDF document

    Available under license: CC BY: Creative Commons Attribution 4.0 International License

Links

Text available via DOI:

View graph of relations

Context-guided diffusion for label propagation on graphs

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

Published

Standard

Context-guided diffusion for label propagation on graphs. / Kim, Kwang In; Tompkin, James; Pfister, Hanspeter et al.
2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015. p. 2776-2784.

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

Harvard

Kim, KI, Tompkin, J, Pfister, H & Theobalt, C 2015, Context-guided diffusion for label propagation on graphs. in 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, pp. 2776-2784. https://doi.org/10.1109/ICCV.2015.318

APA

Kim, K. I., Tompkin, J., Pfister, H., & Theobalt, C. (2015). Context-guided diffusion for label propagation on graphs. In 2015 IEEE International Conference on Computer Vision (ICCV) (pp. 2776-2784). IEEE. https://doi.org/10.1109/ICCV.2015.318

Vancouver

Kim KI, Tompkin J, Pfister H, Theobalt C. Context-guided diffusion for label propagation on graphs. In 2015 IEEE International Conference on Computer Vision (ICCV). IEEE. 2015. p. 2776-2784 doi: 10.1109/ICCV.2015.318

Author

Kim, Kwang In ; Tompkin, James ; Pfister, Hanspeter et al. / Context-guided diffusion for label propagation on graphs. 2015 IEEE International Conference on Computer Vision (ICCV). IEEE, 2015. pp. 2776-2784

Bibtex

@inproceedings{f6fbe139091c4585adefd9da3871d753,
title = "Context-guided diffusion for label propagation on graphs",
abstract = "Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.",
author = "Kim, {Kwang In} and James Tompkin and Hanspeter Pfister and Christian Theobalt",
note = "{\textcopyright}2015 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.",
year = "2015",
month = dec,
day = "7",
doi = "10.1109/ICCV.2015.318",
language = "English",
isbn = "9781467383905",
pages = "2776--2784",
booktitle = "2015 IEEE International Conference on Computer Vision (ICCV)",
publisher = "IEEE",

}

RIS

TY - GEN

T1 - Context-guided diffusion for label propagation on graphs

AU - Kim, Kwang In

AU - Tompkin, James

AU - Pfister, Hanspeter

AU - Theobalt, Christian

N1 - ©2015 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 - 2015/12/7

Y1 - 2015/12/7

N2 - Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.

AB - Existing approaches for diffusion on graphs, e.g., for label propagation, are mainly focused on isotropic diffusion, which is induced by the commonly-used graph Laplacian regularizer. Inspired by the success of diffusivity tensors for anisotropic diffusion in image processing, we presents anisotropic diffusion on graphs and the corresponding label propagation algorithm. We develop positive definite diffusivity operators on the vector bundles of Riemannian manifolds, and discretize them to diffusivity operators on graphs. This enables us to easily define new robust diffusivity operators which significantly improve semi-supervised learning performance over existing diffusion algorithms.

U2 - 10.1109/ICCV.2015.318

DO - 10.1109/ICCV.2015.318

M3 - Conference contribution/Paper

SN - 9781467383905

SP - 2776

EP - 2784

BT - 2015 IEEE International Conference on Computer Vision (ICCV)

PB - IEEE

ER -