• Publications
  • Influence
Deep High-Resolution Representation Learning for Human Pose Estimation
We present a novel architecture, namely HighResolution Net (HRNet), which is able to maintain highresolution representations through the whole process. Expand
High-Resolution Representations for Labeling Pixels and Regions
We introduce a simple modification by exploring the representations from all the high-to-low resolution parallel convolutions in parallel and apply it to a wide range of vision tasks. Expand
A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
We present a CNN-based post-processing algorithm for High Efficiency Video Coding (HEVC), the state-of-the-art video coding standard. Expand
Robust visual domain adaptation with low-rank reconstruction
In this paper, we present a low-rank reconstruction method to reduce the domain distribution disparity. Expand
Tag ranking
Social media sharing web sites like Flickr allow users to annotate images with free tags, which significantly facilitate Web image search and organization. However, the tags associated with an imageExpand
Looking at Both Sides of the Social Exchange Coin: A Social Cognitive Perspective on the Joint Effects of Relationship Quality and Differentiation on Creativity
We propose a cross-level contingent process model based on social cognitive theory to explain how and when the quality of social exchange relationships with a supervisor (leader-member exchange; LMX)Expand
Activated protein C blocks p53-mediated apoptosis in ischemic human brain endothelium and is neuroprotective
Activated protein C (APC) is a systemic anti-coagulant and anti-inflammatory factor. It reduces organ damage in animal models of sepsis, ischemic injury and stroke and substantially reduces mortalityExpand
The Dark Side of Leadership: A Three-Level Investigation of the Cascading Effect of Abusive Supervision on Employee Creativity
This research sheds light on the role of the dark side of leadership in employee creativity by examining how and when department leader abusive supervision may flow down organizational levels to un...
\(\propto\)SVM for Learning with Label Proportions
We propose a new method called proportion-SVM, or $\propto$ SVM, which explicitly models the latent unknown instance labels together with the known group label proportions in a large-margin framework. Expand
Pseudo-sequence-based light field image compression
We propose a pseudo-sequence-based scheme for light field image compression. Expand