Multimodal Gesture Recognition Using Multi-stream Recurrent Neural Network

@inproceedings{Nishida2015MultimodalGR,
  title={Multimodal Gesture Recognition Using Multi-stream Recurrent Neural Network},
  author={Noriki Nishida and Hideki Nakayama},
  booktitle={PSIVT},
  year={2015}
}
In this paper, we present a novel method for multimodal gesture recognition based on neural networks. Our multi-stream recurrent neural network (MRNN) is a completely data-driven model that can be trained from end to end without domain-specific hand engineering. The MRNN extends recurrent neural networks with Long Short-Term Memory cells (LSTM-RNNs) that facilitate the handling of variable-length gestures. We propose a recurrent approach for fusing multiple temporal modalities using multiple… CONTINUE READING
Highly Cited
This paper has 36 citations. REVIEW CITATIONS

Citations

Publications citing this paper.
Showing 1-10 of 18 extracted citations

References

Publications referenced by this paper.
Showing 1-10 of 32 references

Similar Papers

Loading similar papers…