An Efficient Approach to Informative Feature Extraction from Multimodal Data
@article{Wang2019AnEA, title={An Efficient Approach to Informative Feature Extraction from Multimodal Data}, author={L. Wang and J. Wu and Shao-Lun Huang and L. Zheng and Xiangxiang Xu and Lin Zhang and J. Huang}, journal={ArXiv}, year={2019}, volume={abs/1811.08979} }
One primary focus in multimodal feature extraction is to find the representations of individual modalities that are maximally correlated. [...] Key Method Specifically, our framework prevents the "hard" whitening constraints, while simultaneously preserving the same feature geometry as in the HGR maximal correlation. The objective of Soft-HGR is straightforward, only involving two inner products, which guarantees the efficiency and stability in optimization.Expand
17 Citations
TCGM: An Information-Theoretic Framework for Semi-Supervised Multi-Modality Learning
- Computer Science
- ECCV
- 2020
- 2
- Highly Influenced
- PDF
Semantically Supervised Maximal Correlation For Cross-Modal Retrieval
- Computer Science
- 2020 IEEE International Conference on Image Processing (ICIP)
- 2020
An Information-Theoretic Approach to Unsupervised Feature Selection for High-Dimensional Data
- Computer Science
- IEEE Journal on Selected Areas in Information Theory
- 2020
- 1
Knowledge As Priors: Cross-Modal Knowledge Generalization for Datasets Without Superior Knowledge
- Computer Science
- 2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
- 2020
- 9
- PDF
An End-to-End Learning Approach for Multimodal Emotion Recognition: Extracting Common and Private Information
- Computer Science
- 2019 IEEE International Conference on Multimedia and Expo (ICME)
- 2019
Generalizing Correspondence Analysis for Applications in Machine Learning
- Computer Science, Mathematics
- 2018
- 1
- PDF
An Information-Theoretic Approach to Transferability in Task Transfer Learning
- Computer Science
- 2019 IEEE International Conference on Image Processing (ICIP)
- 2019
- 5
Multimodal Emotion Recognition by extracting common and modality-specific information
- Computer Science
- SenSys
- 2018
- 3
- PDF
On the Sample Complexity of HGR Maximal Correlation Functions for Large Datasets
- Computer Science
- IEEE Transactions on Information Theory
- 2021
References
SHOWING 1-10 OF 45 REFERENCES
Heterogeneous Feature Selection With Multi-Modal Deep Neural Networks and Sparse Group LASSO
- Computer Science
- IEEE Transactions on Multimedia
- 2015
- 53
- PDF
Multimodal Machine Learning: A Survey and Taxonomy
- Computer Science, Medicine
- IEEE Transactions on Pattern Analysis and Machine Intelligence
- 2019
- 648
- PDF
An information-theoretic approach to universal feature selection in high-dimensional inference
- Computer Science
- 2017 IEEE International Symposium on Information Theory (ISIT)
- 2017
- 21
- PDF
Scalable and Effective Deep CCA via Soft Decorrelation
- Computer Science
- 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
- 2018
- 25
- PDF