Spectrum-Guided Adversarial Disparity Learning

@article{Liu2020SpectrumGuidedAD,
  title={Spectrum-Guided Adversarial Disparity Learning},
  author={Zhe Liu and L. Yao and Lei Bai and Xianzhi Wang and Can Wang},
  journal={Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining},
  year={2020}
}
  • Zhe Liu, L. Yao, +2 authors Can Wang
  • Published 2020
  • Computer Science, Mathematics
  • Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
  • It has been a significant challenge to portray intraclass disparity precisely in the area of activity recognition, as it requires a robust representation of the correlation between subject-specific variation for each activity class. In this work, we propose a novel end-to-end knowledge directed adversarial learning framework, which portrays the class-conditioned intraclass disparity using two competitive encoding distributions and learns the purified latent codes by denoising learned disparity… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-5 OF 5 REFERENCES
    Deep Convolutional Neural Networks on Multichannel Time Series for Human Activity Recognition
    516
    Introducing a New Benchmarked Dataset for Activity Monitoring
    352
    Recognizing Daily and Sports Activities in Two Open Source Machine Learning Environments Using Body-Worn Sensor Units
    140
    Principles of digital communication and coding
    315
    mHealth- Droid: a novel framework for agile development of mobile health applications
    • 2014