Jimei joined Adobe Research in September 2015, working in the areas of computer vision and deep learning.
He received his Ph.D. degree from UC Merced in 2015 under supervision of Prof. Ming-Hsuan Yang. He was a visiting Ph.D. student in Prof. Honglak Lee’s group at University of Michigan, Ann Arbor. Previously, he received his master’s degree from University of Science and Technology of China.
Jimei’s research interests include object segmentation, contour detection, scene parsing, image synthesis, deep generative models and representation learning with transformations.
For more information, please visit his personal website.
Learning to Trace: Expressive Line Drawing Generation from Photographs
On the Continuity of Rotation Representations in Neural Networks
Deep GrabCut for Object Selection
Forecasting Human Dynamics from Static Images
Deep Interactive Object Selection
Object Contour Detection with a Fully Convolutional Encoder-Decoder Network
Weakly-supervised Disentangling with Recurrent Transformations for 3D View Synthesis
Attribute2Image: Conditional Image Generation from Visual Attributes
PatchCut: Data-Driven Object Segmentation via Local Shape Transfer
Context Driven Scene Parsing with Attention to Rare Classes