Modeling Video Dynamics with Deep Dynencoder

47 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

RGB-D-based Human Motion Recognition with Deep Learning: A Survey (2017, background): “[164] proposed Dynencoder, a three layer auto-encoder, to capture video dynamics.”
3D deep shape descriptor (2015, background): “Despite the enormous success of deep learning as a technique for feature learning in images and videos [3, 32, 52, 50], very few techniques based on deep learning have been developed for learning 3D shape features.”
Going deeper into action recognition: A survey (2016, methodology): “Figure 16: The structure and training of the Dynencoder presented in Yan et al. (2014). Left: In the first stage, the outer autoencoding layers are trained on input frame xt reconstruction.”
Kernel Learning for Dynamic Texture Synthesis (2016, background): “Date of publication August 9, 2016; date of current version August 26, 2016.”