DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition

@article{Perrett2019DDLSTMDL,
  title={DDLSTM: Dual-Domain LSTM for Cross-Dataset Action Recognition},
  author={Toby Perrett and Dima Damen},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={7844-7853}
}
  • Toby Perrett, Dima Damen
  • Published 2019
  • Computer Science
  • 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)
  • Domain alignment in convolutional networks aims to learn the degree of layer-specific feature alignment beneficial to the joint learning of source and target datasets. While increasingly popular in convolutional networks, there have been no previous attempts to achieve domain alignment in recurrent networks. Similar to spatial features, both source and target domains are likely to exhibit temporal dependencies that can be jointly learnt and aligned. In this paper we introduce Dual-Domain LSTM… CONTINUE READING

    Figures, Tables, and Topics from this paper.

    Explore key concepts

    Links to highly relevant papers for key concepts in this paper:

    Citations

    Publications citing this paper.
    SHOWING 1-3 OF 3 CITATIONS

    A review on the long short-term memory model

    VIEW 1 EXCERPT
    CITES BACKGROUND

    Voice Conversion by Dual-Domain Bidirectional Long Short-Term Memory Networks with Temporal Attention

    VIEW 1 EXCERPT
    CITES METHODS

    Dynamic Spatio-Temporal Feature Learning via Graph Convolution in 3D Convolutional Networks

    VIEW 2 EXCERPTS
    CITES BACKGROUND & METHODS

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 46 REFERENCES

    Recurrent Assistance: Cross-Dataset Training of LSTMs on Kitchen Tasks

    • Toby Perrett, Dima Damen
    • Computer Science
    • 2017 IEEE International Conference on Computer Vision Workshops (ICCVW)
    • 2017
    VIEW 1 EXCERPT

    AutoDIAL: Automatic Domain Alignment Layers

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Associative Domain Adaptation

    VIEW 1 EXCERPT

    Beyond short snippets: Deep networks for video classification

    VIEW 1 EXCERPT

    Cross-Stitch Networks for Multi-task Learning

    VIEW 2 EXCERPTS

    Quo Vadis, Action Recognition? A New Model and the Kinetics Dataset

    VIEW 2 EXCERPTS

    Multi-view action recognition by cross-domain learning

    VIEW 1 EXCERPT