CoChat
Sign Up
Cited by 59Multimodal Machine Learning ApplicationsGenerative Adversarial Networks and Image SynthesisDomain Adaptation and Few-Shot Learning

The DOI matches its Crossref record; 7 of the 7 references it cites were found in a registry or an index.

Private-Shared Disentangled Multimodal VAE for Learning of Latent Representations

Lee, Mihee, Pavlovic, Vladimir·2021·2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
DOI 10.1109/cvprw53098.2021.00185
Open this paper in CoChat — free account

Abstract

Multi-modal generative models represent an important family of deep models, whose goal is to facilitate representation learning on data with multiple views or modalities. However, current deep multi-modal models focus on the inference of shared representations, while neglecting the important private aspects of data within individual modalities. In this paper, we introduce a disentangled multi-modal variational autoencoder (DMVAE) that utilizes disentangled VAE strategy to separate the private and shared latent spaces of multiple modalities. We demonstrate the utility of DMVAE two image modalities of MNIST and Google Street View House Number (SVHN) datasets as well as image and text modalities from the Oxford-102 Flowers dataset. Our experiments indicate the essence of retaining the private representation as well as the private-shared disentanglement to effectively direct the information across multiple analysis-synthesis conduits.

Overview

Integrity signals

Registry

Crossref · 10.1109/cvprw53098.2021.00185

Cites

7 of 7 references verified0 citation errors · 0 not checkable

Statistics

Recomputing p-values needs the paper’s full text.

Verification

Claims the paper makes

This paper’s full text isn’t openly available, so its claims and self-check weren’t run. The registry and citation checks still apply.

Claims other papers make about this one

Each is checked against this paper’s own text: does it say what the citing paper says it does?

  • The combinations of unimodal-specific representations exhibited an increment of multimodal representation learning.

    “In addition to the shared representations, the combinations of unimodal-specific representations also exhibited an increment of multimodal representation learning [56].”

    From Challenges in AI-driven Biomedical Multimodal Data Fusion and Analysis (2025) · cites this paper as [56]

Citations

Cites

Flagged first, then by citations

Research works printed but not linked: 16

  1. kingma, 2014, Auto-encoding variational bayes, 2nd International Conference on Learning Representations ICLR 2014
  2. 10.1109/CVPR.2015.7299073 · DOI
  3. lee, 2018, Diverse imageto-image translation via disentangled representations, European Conference on Computer Vision
  4. 10.1109/ICCV.2017.209 · DOI
  5. mikolov, 2013, Distributed representations of words and phrases and their compositionality, Advances in neural information processing systems, 26
  6. 10.1093/bioinformatics/btu703 · DOI
  7. 10.1109/ICCV.2019.00591 · DOI
  8. gonzalez-garcia, 2018, Image-to-image translation for cross-domain disentanglement, Proceedings of the 32nd International Conference on Neural Information Processing Systems NIPS’18, 1294
  9. 10.1049/cp:19991075 · DOI
  10. goodfellow, 2014, Advances in Neural Information Processing Systems 27, 2672
  11. huang, 2018, Multimodal unsupervised image-to-image translation, ECCV
  12. 10.1109/CVPR.2016.13 · DOI
  13. vedantam, 2018, Generative models of visually grounded imagination, 6th International Conference on Learning Representations ICLR 2018
  14. 10.1007/978-3-030-01246-5_42 · DOI
  15. wu, 2018, Advances in Neural IInformation Processing Systems, 5575
  16. zhu, 2017, Toward multimodal image-to-image translation, NIPS’17, 465

Cited by

Sorted by citations

Metadata

Authors
Lee, M., & Pavlovic, V.
Affiliations
  • Rutgers, The State University of New Jersey (US)
  • Rutgers University,Piscataway,NJ,USA
ORCID
Lee, Mihee
Venue
2021 IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW)
Publisher
IEEE
Published
2021-06
Pages
1692-1700
DOI
10.1109/cvprw53098.2021.00185
OpenAlex
W3184212829
Cited by
59
References
7
Citations by year
2026: 15 · 2025: 14 · 2024: 12 · 2023: 10 · 2022: 8
FWCI
2.33
Type
conference paper
Language
en
Open access
closed
Licence
Locations
IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) (publishedVersion)
Funders
National Science Foundation
Topics
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Multimodal Machine Learning Applications
  • Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Generative Adversarial Networks and Image Synthesis
  • Physical Sciences › Computer Science › Artificial Intelligence › Domain Adaptation and Few-Shot Learning
Keywords
disentangled representation learning, multimodal variational autoencoder, shared latent representation, multimodal generative models, image-text representation learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review