120 citations · 310 across the 27 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
cs.CV2016★ 14 cited
Deep Feature Consistent Variational Autoencoder
Xianxu Hou, Linlin Shen, Ke Sun +1
We present a novel method for constructing Variational Autoencoder (VAE). Instead of using pixel-by-pixel loss, we enforce deep feature consistency between the input and the output…
cs.CV2016
Automatic Visual Theme Discovery from Joint Image and Text Corpora
Ke Sun, Xianxu Hou, Qian Zhang +1
A popular approach to semantic image understanding is to manually tag images with keywords and then learn a mapping from vi- sual features to keywords. Manually tagging images is a…
cs.CV2016
Object Specific Deep Learning Feature and Its Application to Face Detection
Xianxu Hou, Ke Sun, Linlin Shen +1
We present a method for discovering and exploiting object specific deep learning features and use face detection as a case study. Motivated by the observation that certain convolut…