Convolutional Relational Machine for Group Activity Recognition

@article{Azar2019ConvolutionalRM,
  title={Convolutional Relational Machine for Group Activity Recognition},
  author={Sina Mokhtarzadeh Azar and Mina Ghadimi Atigh and Ahmad Nickabadi and Alexandre Alahi},
  journal={CoRR},
  year={2019},
  volume={abs/1904.03308}
}
We present an end-to-end deep Convolutional Neural Network called Convolutional Relational Machine (CRM) for recognizing group activities that utilizes the information in spatial relations between individual persons in image or video. It learns to produce an intermediate spatial representation (activity map) based on individual and group activities. A multi-stage refinement component is responsible for decreasing the incorrect predictions in the activity map. Finally, an aggregation component… CONTINUE READING

References

Publications referenced by this paper.
SHOWING 1-10 OF 28 REFERENCES

Similar Papers

Loading similar papers…