J
Junyuan Xie
Researcher at Amazon.com
Publications - 26
Citations - 6004
Junyuan Xie is an academic researcher from Amazon.com. The author has contributed to research in topics: Computer science & Convolutional neural network. The author has an hindex of 14, co-authored 20 publications receiving 4371 citations. Previous affiliations of Junyuan Xie include University of Science and Technology of China & University of Washington.
Papers
More filters
Proceedings Article
Unsupervised deep embedding for clustering analysis
TL;DR: Deep Embedded Clustering (DEC) as discussed by the authors learns a mapping from the data space to a lower-dimensional feature space in which it iteratively optimizes a clustering objective.
Proceedings Article
Image Denoising and Inpainting with Deep Neural Networks
Junyuan Xie,Linli Xu,Enhong Chen +2 more
TL;DR: A novel approach to low-level vision problems that combines sparse coding and deep networks pre-trained with denoising auto-encoder (DA) is presented and can automatically remove complex patterns like superimposed text from an image, rather than simple patterns like pixels missing at random.
Proceedings ArticleDOI
Bag of Tricks for Image Classification with Convolutional Neural Networks
TL;DR: This article examined a collection of such refinements and empirically evaluated their impact on the final model accuracy through ablation study, and showed that by combining these refinements together, they are able to improve various CNN models significantly.
Book ChapterDOI
Deep3D: Fully Automatic 2D-to-3D Video Conversion with Deep Convolutional Neural Networks
TL;DR: Deep3D as discussed by the authors uses deep neural networks to automatically convert 2D videos and images to a stereoscopic 3D format, which is trained end-to-end directly on stereo pairs extracted from existing 3D movies.
Posted Content
Bag of Tricks for Image Classification with Convolutional Neural Networks
TL;DR: This paper examines a collection of training procedure refinements and empirically evaluates their impact on the final model accuracy through ablation study, and shows that by combining these refinements together, they are able to improve various CNN models significantly.