Corpus ID: 22939330

TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation

@article{Ding2017TricorNetAH,
  title={TricorNet: A Hybrid Temporal Convolutional and Recurrent Network for Video Action Segmentation},
  author={Li Ding and Chenliang Xu},
  journal={ArXiv},
  year={2017},
  volume={abs/1705.07818}
}
  • Li Ding, Chenliang Xu
  • Published in ArXiv 2017
  • Computer Science
  • Action segmentation as a milestone towards building automatic systems to understand untrimmed videos has received considerable attention in the recent years. It is typically being modeled as a sequence labeling problem but contains intrinsic and sufficient differences than text parsing or speech processing. In this paper, we introduce a novel hybrid temporal convolutional and recurrent network (TricorNet), which has an encoder-decoder architecture: the encoder consists of a hierarchy of… CONTINUE READING

    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 20 CITATIONS

    Coupled Generative Adversarial Network for Continuous Fine-Grained Action Segmentation

    VIEW 1 EXCERPT

    Fine-grained Action Segmentation using the Semi-Supervised Action GAN

    VIEW 2 EXCERPTS
    CITES BACKGROUND & RESULTS

    Time Series Prediction Based on Temporal Convolutional Network

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Unsupervised Learning of Action Classes With Continuous Temporal Embedding

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 30 REFERENCES

    Temporal Convolutional Networks for Action Segmentation and Detection

    VIEW 11 EXCERPTS
    HIGHLY INFLUENTIAL

    et al

    • Y. Gao, S. S. Vedula, +7 authors D. D. Yuh
    • Jhu-isi gesture and skill assessment working set (jigsaws): A surgical activity dataset for human motion modeling. In MICCAI Workshop: M2CAI, volume 3
    • 2014
    VIEW 7 EXCERPTS
    HIGHLY INFLUENTIAL

    Learning to recognize objects in egocentric activities

    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Every Moment Counts: Dense Detailed Labeling of Actions in Complex Videos

    VIEW 2 EXCERPTS

    A Multi-stream Bi-directional Recurrent Neural Network for Fine-Grained Action Detection

    VIEW 3 EXCERPTS

    First Person Action Recognition Using Deep Learned Descriptors

    VIEW 1 EXCERPT