EmbraceNet: A robust deep learning architecture for multimodal classification

@article{Choi2019EmbraceNetAR,
  title={EmbraceNet: A robust deep learning architecture for multimodal classification},
  author={Junho Choi and Jong-Seok Lee},
  journal={ArXiv},
  year={2019},
  volume={abs/1904.09078}
}
  • Junho Choi, Jong-Seok Lee
  • Published 2019
  • Computer Science, Mathematics
  • ArXiv
  • 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… CONTINUE READING

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 10 CITATIONS

    Multimodal Representation Learning: Advances, Trends and Challenges

    VIEW 2 EXCERPTS
    CITES METHODS

    EmbraceNet for activity: a deep multimodal fusion architecture for activity recognition

    VIEW 12 EXCERPTS
    CITES METHODS
    HIGHLY INFLUENCED

    A Hybrid Deep Learning Architecture for Leukemic B-lymphoblast Classification

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Breast Cancer Diagnosis with Transfer Learning and Global Pooling

    VIEW 1 EXCERPT
    CITES METHODS

    Robust face recognition method based on similarity fusion

    VIEW 3 EXCERPTS
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 57 REFERENCES

    Deep Multimodal Fusion: A Hybrid Approach

    VIEW 1 EXCERPT

    Multimodal deep learning for robust RGB-D object recognition

    VIEW 1 EXCERPT

    Berkeley MHAD: A comprehensive Multimodal Human Action Database

    VIEW 3 EXCERPTS

    Multimodal Deep Learning

    VIEW 3 EXCERPTS

    Multimodal autoencoder: A deep learning approach to filling in missing sensor data and enabling better mood prediction

    VIEW 6 EXCERPTS
    HIGHLY INFLUENTIAL