Learning Similarity: Feature-Aligning Network for Few-shot Action Recognition

@article{Tan2019LearningSF,
  title={Learning Similarity: Feature-Aligning Network for Few-shot Action Recognition},
  author={Shaoqing Tan and Ruoyu Yang},
  journal={2019 International Joint Conference on Neural Networks (IJCNN)},
  year={2019},
  pages={1-7}
}
Deep learning structures have achieved impressive results in action recognition. However, most of deep models require extensive training on large scale datasets. Besides, Insufficient data can easily lead to overfitting. In this work, we propose a conceptually simple, flexible, and general approach for few-shot action recognition, where a model must learn to reliably classify an example having seen only few previous instances which belongs to the same class with it. Our method, called the… CONTINUE READING

Figures, Tables, and Topics from this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 38 REFERENCES

Learning Spatiotemporal Features with 3D Convolutional Networks

  • 2015 IEEE International Conference on Computer Vision (ICCV)
  • 2014
VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Matching video net: Memory-based embedding for video action recognition

  • 2017 International Joint Conference on Neural Networks (IJCNN)
  • 2017
VIEW 7 EXCERPTS
HIGHLY INFLUENTIAL

The Action Similarity Labeling Challenge

  • IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2012
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Few-Shot Learning with Graph Neural Networks

Victor Garcia Satorras, Joan Bruna
  • ICLR
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Learning to Compare: Relation Network for Few-Shot Learning

  • 2018 IEEE/CVF Conference on Computer Vision and Pattern Recognition
  • 2017
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Dynamic Image Networks for Action Recognition

  • 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
  • 2016
VIEW 3 EXCERPTS
HIGHLY INFLUENTIAL