CoChat

EmbraceNet: A robust deep learning architecture for multimodal classification

Open access
Choi, Jun-Ho, Lee, Jong-Seok · 2019 · Information Fusion
Cited by 156

The DOI matches its Crossref record; 14 of the 14 references it cites were found in a registry or an index.

Abstract

Classification using multimodal data arises in many machine learning applications. It is crucial not only to model cross-modal relationship effectively but also to ensure robustness against loss of part of data or modalities. In this paper, we propose a novel deep learning-based multimodal fusion architecture for classification tasks, which guarantees compatibility with any kind of learning models, deals with cross-modal information carefully, and prevents performance degradation due to partial absence of data. We employ two datasets for multimodal classification tasks, build models based on our architecture and other state-of-the-art models, and analyze their performance on various situations. The results show that our architecture outperforms the other multimodal fusion architectures when some parts of data are not available.

Overview

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1016/j.inffus.2019.02.010

Cites

14 of 14 references verified0 citation errors · 0 not checkable

Statistics

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 14 references

Research works printed but not linked: 17

  1. Schmidhuber, 2015, Deep learning in neural networks: An overview, Neural Networks, 61, 85, 10.1016/j.neunet.2014.09.003 · DOI · Paper page
  2. Kwon, 2014, Unsupervised learning for human activity recognition using smartphone sensors, Expert Systems with Applications, 41, 6067, 10.1016/j.eswa.2014.04.037 · DOI · Paper page
  3. Vergara, 2013, On the performance of gas sensor arrays in open sampling systems using Inhibitory Support Vector Machines, Sensors and Actuators B: Chemical, 185, 462, 10.1016/j.snb.2013.05.027 · DOI · Paper page
  4. Matthews, 2002, Extraction of visual features for lipreading, IEEE Transactions on Pattern Analysis and Machine Intelligence, 24, 198, 10.1109/34.982900 · DOI · Paper page
  5. Higuera, 2015, Self-organizing feature maps identify proteins critical to learning in a mouse model of Down syndrome, PLOS ONE, 10, 1, 10.1371/journal.pone.0129126 · DOI
  6. Singh, 2014, Fusion of multimodal medical images using Daubechies complex wavelet transform – A multiresolution approach, Information Fusion, 19, 49, 10.1016/j.inffus.2012.09.005 · DOI · Paper page
  7. Lee, 2008, Robust audio-visual speech recognition based on late integration, IEEE Transactions on Multimedia, 10, 767, 10.1109/TMM.2008.922789 · DOI
  8. Moon, 2015, Perceptual experience analysis for tone-mapped HDR videos based on EEG and peripheral physiological signals, IEEE Transactions on Autonomous Mental Development, 7, 236, 10.1109/TAMD.2015.2449553 · doi:10.1109/tamd.2015.2449553
  9. Kusuma, 2011, PCA-based image recombination for multimodal 2D + 3D face recognition, Image and Vision Computing, 29, 306, 10.1016/j.imavis.2010.12.003 · DOI
  10. Bengio, 2004, Multimodal speech processing using asynchronous Hidden Markov Models, Information Fusion, 5, 81, 10.1016/j.inffus.2003.04.001 · DOI
  11. Kittler, 1998, On combining classifiers, IEEE Transactions on Pattern Analysis and Machine Intelligence, 20, 226, 10.1109/34.667881 · DOI · Paper page
  12. Bharadwaj, 2015, QFuse: Online learning framework for adaptive biometric system, Pattern Recognition, 48, 3428, 10.1016/j.patcog.2015.05.002 · DOI
  13. Costa, 2017, An evaluation of convolutional neural networks for music classification using spectrograms, Applied Soft Computing, 52, 28, 10.1016/j.asoc.2016.12.024 · DOI · Paper page
  14. Amer, 2018, Deep multimodal fusion: A hybrid approach, International Journal of Computer Vision, 126, 440, 10.1007/s11263-017-0997-7 · DOI
  15. Srivastava, 2014, Dropout: A simple way to prevent neural networks from overfitting, Journal of Machine Learning Research, 15, 1929
  16. Livnat, 2010, Sex, mixability, and modularity, Proceedings of the National Academy of Sciences, 107, 1452, 10.1073/pnas.0910734106 · DOI
  17. Algashaam, 2017, Multispectral periocular classification with multimodal compact multi-linear pooling, IEEE Access, 5, 14572, 10.1109/ACCESS.2017.2731118 · DOI

Cited by

See all 156

Metadata

Authors
Choi, J.-H., & Lee, J.-S.
Venue
Information Fusion
Publisher
Elsevier BV
Published
2019-11
Volume
51
Pages
259-270
ISSN
1566-2535 (ISSN-L)
OpenAlex
W2936150952
Cited by
156
References
14
FWCI
6.59
Type
journal article
Language
en
Open access
green
Licence
  • www.elsevier.com/tdm/userlicense/1.0/ (tdm)
  • www.elsevier.com/legal/tdmrep-license (tdm)
Funders
  • MSIT (Ministry of Science and ICT), Korea (IITP-2018-2017-0-01015)
  • IITP (R7124-16-0004)

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

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: EmbraceNet: A robust deep learning architecture for multimodal classification. https://app.cochat.ai/papers/10.1016/j.inffus.2019.02.010
The paper
Choi, J.-H., & Lee, J.-S. (2019). EmbraceNet: A robust deep learning architecture for multimodal classification. Information Fusion. https://doi.org/10.1016/j.inffus.2019.02.010

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.