Hand pose estimation on hybrid CNN-AE model

Automatic hand detection and accurate hand pose estimation from depth data in real system are challenging and vital tasks for human-computer interaction. In this paper, we introduce a Convolutional Neural Network (CNN) as Deep learning regression framework while employing an embedding denoising auto-encoder in the bottom layer of the network to learn latent representation of hand pose and account for joint dependencies. Our model is trained end-to-end and parameters are jointly fine-tuned via gradient descent algorithm. We verify our approach on two public hand pose datasets: NYU and ICVL datasets. Experimental results show that our method achieves competitive performance to the compared state-of-the-art methods.