Corpus ID: 184487798

FASTER Recurrent Networks for Video Classification

@article{Zhu2019FASTERRN,
  title={FASTER Recurrent Networks for Video Classification},
  author={Linchao Zhu and Laura Sevilla-Lara and Du Tran and Matt Feiszli and Yi Yang and H. Wang},
  journal={ArXiv},
  year={2019},
  volume={abs/1906.04226}
}
  • Linchao Zhu, Laura Sevilla-Lara, +3 authors H. Wang
  • Published 2019
  • Computer Science
  • ArXiv
  • Video classification methods often divide the video into short clips, do inference on these clips independently, and then aggregate these predictions to generate the final classification result. Treating these highly-correlated clips as independent both ignores the temporal structure of the signal and carries a large computational cost: the model must process each clip from scratch. To reduce this cost, recent efforts have focused on designing more efficient clip-level network architectures… CONTINUE READING

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 59 REFERENCES
    Myogenic activity in isolated subepicardial and subendocardial coronary arterioles.
    185
    Emerging drugs for hepatitis C.
    28
    Evolution of Collective Commitment during Teamwork
    34
    Changes in thymic function with age and during the treatment of HIV infection
    1819
    Sodium and potassium intake and balance in adults consuming self-selected diets.
    269
    Real-time quantitative RT–PCR after laser-assisted cell picking
    592
    Changes in carbon dioxide during an oceanic anoxic event linked to intrusion into Gondwana coals
    311