Dynamic Video Segmentation Network

@article{Xu2018DynamicVS,
  title={Dynamic Video Segmentation Network},
  author={Yu-Syuan Xu and Tsu-Jui Fu and Hsuan-Kung Yang and Chun-Yi Lee},
  journal={2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition},
  year={2018},
  pages={6556-6565}
}
  • Yu-Syuan Xu, Tsu-Jui Fu, +1 author Chun-Yi Lee
  • Published in
    IEEE/CVF Conference on…
    2018
  • Computer Science
  • In this paper, we present a detailed design of dynamic video segmentation network (DVSNet) for fast and efficient semantic video segmentation. [...] Key Result The experimental results show that our DVSNet is able to achieve up to 70.4% mIoU at 19.8 fps on the Cityscape dataset. A high speed version of DVSNet is able to deliver an fps of 30.4 with 63.2% mIoU on the same dataset. DVSNet is also able to reduce up to 95% of the computational workloads.Expand Abstract

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 17 CITATIONS

    A Distributed Scheme for Accelerating Semantic Video Segmentation on An Embedded Cluster

    VIEW 6 EXCERPTS
    CITES BACKGROUND

    Dynamic Face Video Segmentation via Reinforcement Learning

    VIEW 8 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Fast Video Object Segmentation via Dynamic Targeting Network

    VIEW 5 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    Efficient Semantic Video Segmentation with Per-frame Inference

    VIEW 3 EXCERPTS
    CITES METHODS & BACKGROUND

    Attention-Guided Network for Semantic Video Segmentation

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Boosting Real-Time Driving Scene Parsing With Shared Semantics

    VIEW 1 EXCERPT
    CITES METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 47 REFERENCES

    Deep Feature Flow for Video Recognition

    VIEW 20 EXCERPTS
    HIGHLY INFLUENTIAL

    FlowNet: Learning Optical Flow with Convolutional Networks

    VIEW 14 EXCERPTS
    HIGHLY INFLUENTIAL

    DeepLab: Semantic Image Segmentation with Deep Convolutional Nets, Atrous Convolution, and Fully Connected CRFs

    VIEW 17 EXCERPTS
    HIGHLY INFLUENTIAL

    Clockwork Convnets for Video Semantic Segmentation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Wider or Deeper: Revisiting the ResNet Model for Visual Recognition

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Understanding Convolution for Semantic Segmentation

    VIEW 4 EXCERPTS
    HIGHLY INFLUENTIAL

    Pyramid Scene Parsing Network

    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL