Corpus ID: 52195297

Parallel Separable 3D Convolution for Video and Volumetric Data Understanding

@article{Gonda2018ParallelS3,
  title={Parallel Separable 3D Convolution for Video and Volumetric Data Understanding},
  author={Felix Gonda and Donglai Wei and Toufiq Parag and Hanspeter Pfister},
  journal={ArXiv},
  year={2018},
  volume={abs/1809.04096}
}
  • Felix Gonda, Donglai Wei, +1 author Hanspeter Pfister
  • Published 2018
  • Computer Science
  • ArXiv
  • For video and volumetric data understanding, 3D convolution layers are widely used in deep learning, however, at the cost of increasing computation and training time. Recent works seek to replace the 3D convolution layer with convolution blocks, e.g. structured combinations of 2D and 1D convolution layers. In this paper, we propose a novel convolution block, Parallel Separable 3D Convolution (PmSCn), which applies m parallel streams of n 2D and one 1D convolution layers along different… CONTINUE READING

    Figures and Topics from this paper.

    Explore Further: Topics Discussed in This Paper

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 48 REFERENCES

    Learning Spatio-Temporal Representation with Pseudo-3D Residual Networks

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning Spatiotemporal Features with 3D Convolutional Networks

    VIEW 1 EXCERPT

    Convolutional Two-Stream Network Fusion for Video Action Recognition

    VIEW 1 EXCERPT

    Densely Connected Convolutional Networks

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL