387 citations · 2k across the 64 of their papers we have counts for
Showing 2016Show all
3 papers · 1 filter
cs.CV2016
A DNN Framework For Text Image Rectification From Planar Transformations
Chengzhe Yan, Jie Hu, Changshui Zhang
In this paper, a novel neural network architecture is proposed attempting to rectify text images with mild assumptions. A new dataset of text images is collected to verify our mode…
stat.ML2016★ 10 cited
Neural Network Architecture Optimization through Submodularity and Supermodularity
Junqi Jin, Ziang Yan, Kun Fu +2
Deep learning models' architectures, including depth and width, are key factors influencing models' performance, such as test accuracy and computation time. This paper solves two p…
stat.ML2016★ 1 cited
Optimizing Recurrent Neural Networks Architectures under Time Constraints
Junqi Jin, Ziang Yan, Kun Fu +2
Recurrent neural network (RNN)'s architecture is a key factor influencing its performance. We propose algorithms to optimize hidden sizes under running time constraint. We convert…