An Efficient Approach to Informative Feature Extraction from Multimodal Data

@article{Wang2018AnEA,
  title={An Efficient Approach to Informative Feature Extraction from Multimodal Data},
  author={Lichen Wang and Jiaxiang Wu and Shao-Lun Huang and Lizhong Zheng and Xiangxiang Xu and Lin Zhang and Junzhou Huang},
  journal={ArXiv},
  year={2018},
  volume={abs/1811.08979}
}
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. As a well-known measure of dependence, the Hirschfeld-Gebelein-R\'{e}nyi (HGR) maximal correlation becomes an appealing objective because of its operational meaning and desirable properties. However, the strict whitening constraints formalized in the HGR maximal correlation limit its application. To address this problem, this paper proposes Soft-HGR, a novel… CONTINUE READING
1
Twitter Mention

Citations

Publications citing this paper.
SHOWING 1-5 OF 5 CITATIONS

An End-to-End Learning Approach for Multimodal Emotion Recognition: Extracting Common and Private Information

VIEW 12 EXCERPTS
CITES METHODS & BACKGROUND
HIGHLY INFLUENCED

Mining Mobility Patterns with Trip-Based Traffic Analysis Zones: A Deep Feature Embedding Approach

VIEW 3 EXCERPTS
CITES METHODS

Multimodal Emotion Recognition by extracting common and modality-specific information

VIEW 2 EXCERPTS
CITES METHODS & BACKGROUND

A Robust Localization System for Inspection Robots in Sewer Networks †

VIEW 1 EXCERPT
CITES BACKGROUND

An Information-Theoretic Approach to Transferability in Task Transfer Learning

VIEW 1 EXCERPT
CITES METHODS

References

Publications referenced by this paper.
SHOWING 1-10 OF 43 REFERENCES

T

  • X. Chang, T. Xiang, Hospedales
  • M.
  • 2018
VIEW 5 EXCERPTS
HIGHLY INFLUENTIAL

G

  • S.-L. Huang, A. Makur, L. Zheng, Wornell
  • W.
  • 2017
VIEW 11 EXCERPTS
HIGHLY INFLUENTIAL

Relations Between Two Sets of Variates

VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Multimodal Machine Learning: A Survey and Taxonomy

Scalable and Effective Deep CCA via Soft Decorrelation