activity
20162023
most citedVariational Autoencoder for Deep Learning of Images, Labels and Captions

371 citations · 2k across the 57 of their papers we have counts for

collaborators
Showing 2016Show all

8 papers · 1 filter

cs.SD2016

Adaptive DCTNet for Audio Signal Classification

Yin Xian, Yunchen Pu, Zhe Gan +2

In this paper, we investigate DCTNet for audio signal classification. Its output feature is related to Cohen's class of time-frequency distributions. We introduce the use of adapti…

stat.ML2016

Unsupervised Learning with Truncated Gaussian Graphical Models

Qinliang Su, Xuejun Liao, Chunyuan Li +2

Gaussian graphical models (GGMs) are widely used for statistical modeling, because of ease of inference and the ubiquitous use of the normal distribution in practical approximation…

cs.CL2016

Scalable Bayesian Learning of Recurrent Neural Networks for Language Modeling

Zhe Gan, Chunyuan Li, Changyou Chen +3

Recurrent neural networks (RNNs) have shown promising performance for language modeling. However, traditional training of RNNs using back-propagation through time often suffers fro…

cs.CV2016★ 18 cited

Semantic Compositional Networks for Visual Captioning

Zhe Gan, Chuang Gan, Xiaodong He +5

A Semantic Compositional Network (SCN) is developed for image captioning, in which semantic concepts (i.e., tags) are detected from the image, and the probability of each tag is us…

cs.CL2016

Learning Generic Sentence Representations Using Convolutional Neural Networks

Zhe Gan, Yunchen Pu, Ricardo Henao +3

We propose a new encoder-decoder approach to learn distributed sentence representations that are applicable to multiple purposes. The model is learned by using a convolutional neur…

cs.CV2016

Adaptive Feature Abstraction for Translating Video to Text

Yunchen Pu, Martin Renqiang Min, Zhe Gan +1

Previous models for video captioning often use the output from a specific layer of a Convolutional Neural Network (CNN) as video features. However, the variable context-dependent s…