Y
Yangqing Jia
Researcher at Facebook
Publications - 61
Citations - 93683
Yangqing Jia is an academic researcher from Facebook. The author has contributed to research in topics: Deep learning & Image segmentation. The author has an hindex of 37, co-authored 61 publications receiving 78214 citations. Previous affiliations of Yangqing Jia include Tsinghua University & Google.
Papers
More filters
Proceedings Article
Factorized multi-modal topic model
TL;DR: In this paper, the authors combine the two approaches by presenting a novel HDP-based topic model that automatically learns both shared and private topics, which is shown to be especially useful for querying the contents of one domain given samples of the other.
Proceedings ArticleDOI
Learning distance metric for semi-supervised image segmentation
Yangqing Jia,Changshui Zhang +1 more
TL;DR: This paper introduces distance metric learning into graph-based semi-supervised segmentation to automatically obtain good results for images with different appearances and derives the optimization problem with respect to the distance metric as well as the segmentation labels.
Proceedings Article
On Compact Codes for Spatially Pooled Features
TL;DR: This paper analyzes the classification accuracy with respect to dictionary size by linking the encoding stage to kernel methods and Nystrom sampling, and obtains useful bounds on accuracy as a function of size.
Patent
Artifact reduction for image style transfer
TL;DR: In this paper, an image processing system transforms content images into the style of another reference style image by applying computer models to the noisy version of the content image, which reduces artifacts in the stylized image compared to that of a stylised image generated by applying the computer models on the original content image.
Proceedings ArticleDOI
Augmented tree partitioning for interactive image segmentation
TL;DR: A new fast semi-supervised image segmentation method based on augmented tree partitioning, which uses a tree-based structure called the augmented tree, which is built up by augmenting several abstract label nodes to the minimum spanning tree of the original graph.