Conference paper · 2017 · Open access

G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition

Qilong Wang, Peihua Li, Lei Zhang

IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 6507–6516 · Published 1 July 2017 · DOI 10.1109/cvpr.2017.689

Open PDFView at the publisherCite this paper

In brief

“G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition” is a 2017 conference paper by Qilong Wang and 2 co-authors, published in IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings. OpenAlex counts 127 citations as of 18 November 2026, which puts it in the top 5% of works published in 2017 by citations. It is open access: the full text is free to read at PolyU Institutional Research Archive (Hong Kong Polytechnic University).

Citations
127
Most cited in
2019 (24)
Field-weighted impact
3.87
References
50
Authors
3

Abstract

Recently, plugging trainable structural layers into deep convolutional neural networks (CNNs) as image representations has made promising progress. However, there has been little work on inserting parametric probability distributions, which can effectively model feature statistics, into deep CNNs in an end-to-end manner. This paper proposes a Global Gaussian Distribution embedding Network (G2DeNet) to take a step towards addressing this problem. The core of G2DeNet is a novel trainable layer of a global Gaussian as an image representation plugged into deep CNNs for end-to-end learning. The challenge is that the proposed layer involves Gaussian distributions whose space is not a linear space, which makes its forward and backward propagations be non-intuitive and non-trivial. To tackle this issue, we employ a Gaussian embedding strategy which respects the structures of both Riemannian manifold and smooth group of Gaussians. Based on this strategy, we construct the proposed global Gaussian embedding layer and decompose it into two sub-layers: the matrix partition sub-layer decoupling the mean vector and covariance matrix entangled in the embedding matrix, and the square-rooted, symmetric positive definite matrix sub-layer. In this way, we can derive the partial derivatives associated with the proposed structural layer and thus allow backpropagation of gradients. Experimental results on large scale region classification and fine-grained recognition tasks show that G2DeNet is superior to its counterparts, capable of achieving state-of-the-art performance.

Cite this paper

Formatted from the catalogue record. Check names, capitals and page numbers against the paper before you submit.

APA 7

Wang, Q., Li, P., & Zhang, L. (2017). G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 6507–6516. https://doi.org/10.1109/cvpr.2017.689

MLA 9

Wang, Qilong, et al. “G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 2017, pp. 6507–6516. https://doi.org/10.1109/cvpr.2017.689.

Chicago

Wang, Qilong, Peihua Li, and Lei Zhang. 2017. “G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition.” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings: 6507–6516. https://doi.org/10.1109/cvpr.2017.689.

Harvard

Wang, Q., Li, P. and Zhang, L. (2017) ‘G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition’, IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 6507–6516. doi:10.1109/cvpr.2017.689.

IEEE

Q. Wang, P. Li, and L. Zhang, “G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition,” IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, pp. 6507–6516, 2017, doi: 10.1109/cvpr.2017.689.

BibTeX

@inproceedings{wang2017denet,
  title     = {{G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition}},
  author    = {Wang, Qilong and Li, Peihua and Zhang, Lei},
  booktitle = {IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings},
  year      = {2017},
  pages     = {6507--6516},
  doi       = {10.1109/cvpr.2017.689},
  url       = {https://doi.org/10.1109/cvpr.2017.689}
}

Download for a reference manager: BibTeX (.bib) · RIS for Zotero, Mendeley and EndNote (.ris)

Citations by year

YearCitationsShare of the best year
20181212
20192424
20201919
20212323
20221212
20231515
20241313
202544
202655

Its field-weighted citation impact is 3.87: it has been cited 3.87 times as often as the average work of the same field, type and year (1.00 is the world average).

Topic and keywords

Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Advanced Neural Network Applications

  • image representation
  • Riemannian manifolds
  • covariance matrix decomposition
  • symmetric positive definite matrices
  • backpropagation
  • regional classification
  • fine-grained classification
  • end-to-end learning

Work with this paper

Most-cited papers in Computer Science

All highly cited Computer Science papers

Questions about this paper

How do I cite this paper in APA style?

Wang, Q., Li, P., & Zhang, L. (2017). G2DeNet: Global Gaussian Distribution Embedding Network and Its Application to Visual Recognition. IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings, 6507–6516. https://doi.org/10.1109/cvpr.2017.689

How many times has this paper been cited?

127 times, according to OpenAlex on 18 November 2026. Google Scholar and Scopus count different sets of sources, so their numbers differ.

Is this paper free to read?

Yes. It is open access at PolyU Institutional Research Archive (Hong Kong Polytechnic University): sign in and open the PDF from this page.

Who wrote this paper?

Qilong Wang, Peihua Li, Lei Zhang.

What is the DOI of this paper?

10.1109/cvpr.2017.689, permanently at https://doi.org/10.1109/cvpr.2017.689. Sign in and open it from this page.

Bibliographic data from OpenAlex (CC0), last checked 18 November 2026. ResearchGuru does not host this paper; once you are signed in, the links open it at the publisher or the repository that does.