Post-Data Augmentation to Improve Deep Pose Estimation of Extreme and Wild Motions

@article{Toyoda2019PostDataAT,
  title={Post-Data Augmentation to Improve Deep Pose Estimation of Extreme and Wild Motions},
  author={K. Toyoda and Michinari Kono and J. Rekimoto},
  journal={2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)},
  year={2019},
  pages={1570-1574}
}
  • K. Toyoda, Michinari Kono, J. Rekimoto
  • Published 2019
  • Computer Science, Mathematics
  • 2019 IEEE Conference on Virtual Reality and 3D User Interfaces (VR)
  • Contributions of recent deep-neural-network (DNN) based techniques have been playing a significant role in human-computer interaction (HCI) and user interface (UI) domains. [...] Key Method To address these issues, we propose a method to improve the pose estimation accuracy for extreme/wild motions by using pre-trained models, i.e., without performing the training procedure by yourselves. We assume our method to encourage usage of these DNN techniques for users in application areas that are out of the ML field…Expand Abstract

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 15 REFERENCES
    Human exposure to phthalates via consumer products.
    635
    Prognostic and predictive values of long non-coding RNA LINC00472 in breast cancer
    61
    Realtime Multi-person 2D Pose Estimation Using Part Affinity Fields
    2218
    End-to-End Recovery of Human Shape and Pose
    414
    ParaPara: Synthesizing Pseudo-2.5D Content from Monocular Videos for Mixed Reality
    1
    Prediction of Basketball Free Throw Shooting by OpenPose
    5
    SFV: Reinforcement Learning of Physical Skills from Videos
    59