100 citations · 308 across the 28 of their papers we have counts for
4 papers · 1 filter
A Context-aware Attention Network for Interactive Question Answering
Huayu Li, Martin Renqiang Min, Yong Ge +1
Neural network based sequence-to-sequence models in an encoder-decoder framework have been successfully applied to solve Question Answering (QA) problems, predicting answers from s…
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…
A Shallow High-Order Parametric Approach to Data Visualization and Compression
Martin Renqiang Min, Hongyu Guo, Dongjin Song
Explicit high-order feature interactions efficiently capture essential structural knowledge about the data of interest and have been used for constructing generative models. We pre…
Accelerating Deep Neural Network Training with Inconsistent Stochastic Gradient Descent
Linnan Wang, Yi Yang, Martin Renqiang Min +1
SGD is the widely adopted method to train CNN. Conceptually it approximates the population with a randomly sampled batch; then it evenly trains batches by conducting a gradient upd…