Hand pose estimation with CNN-RNN

Hand pose estimation plays an important role in human-computer interaction. The traditional way is to deal with a single frame image. We know that the gesture is continuous, so the adjacent frames must be highly correlated. Therefore, the input of model of this paper was changed from single frame image to multi-frame images in order to use the condition that the adjacent frames have relevance. So the structure of CNN-RNN was used in this paper. We discussed the effect of using the RNN module in the model. Finally, we demonstrated that our approach significantly outperforms state-of-the-art techniques in the NYU dataset.