activity
20192023
most citedJPGNet: Joint Predictive Filtering and Generative Network for Image Inpainting

34 citations · 130 across the 28 of their papers we have counts for

collaborators
Showing 2021Show all

16 papers · 1 filter

cs.LG2021★ 4 cited

ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks

Hua Qi, Zhijie Wang, Qing Guo +4

Over the past few years, deep neural networks (DNNs) have achieved tremendous success and have been continuously applied in many application domains. However, during the practical…

cs.CV2021★ 2 cited

Benchmarking Shadow Removal for Facial Landmark Detection and Beyond

Lan Fu, Qing Guo, Felix Juefei-Xu +4

Facial landmark detection is a very fundamental and significant vision task with many important applications. In practice, facial landmark detection can be affected by a lot of nat…

cs.CV2021★ 4 cited

Natural & Adversarial Bokeh Rendering via Circle-of-Confusion Predictive Network

Yihao Huang, Felix Juefei-Xu, Qing Guo +2

Bokeh effect is a natural shallow depth-of-field phenomenon that blurs the out-of-focus part in photography. In recent years, a series of works have proposed automatic and realisti…

cs.CV2021

Adversarial Relighting Against Face Recognition

Qian Zhang, Qing Guo, Ruijun Gao +3

Deep face recognition (FR) has achieved significantly high accuracy on several challenging datasets and fosters successful real-world applications, even showing high robustness to…

cs.CV2021

CarveNet: Carving Point-Block for Complex 3D Shape Completion

Qing Guo, Zhijie Wang, Felix Juefei-Xu +4

3D point cloud completion is very challenging because it heavily relies on the accurate understanding of the complex 3D shapes (e.g., high-curvature, concave/convex, and hollowed-o…

cs.IT2021

Bidirectional Approximate Message Passing for RIS-Assisted Multi-User MISO Communications

Li Wei, Chongwen Huang, Qinghua Guo +3

Reconfigurable intelligent surfaces (RISs) have been recently considered as a promising candidate for energy-efficient solutions in future wireless networks. Their dynamic and lowp…