activity
20162023
most citedA Stream Learning Approach for Real-Time Identification of False Data Injection Attacks in Cyber-Physical Power Systems

50 citations · 128 across the 21 of their papers we have counts for

collaborators
Showing cs.CVShow all

9 papers · 1 filter

cs.CV20197 cited

Person Re-identification with Metric Learning using Privileged Information

Xun Yang, Meng Wang, Dacheng Tao

Despite the promising progress made in recent years, person re-identification remains a challenging task due to complex variations in human appearances from different camera views.…

cs.CV2019

Graphonomy: Universal Human Parsing via Graph Transfer Learning

Ke Gong, Yiming Gao, Xiaodan Liang +3

Prior highly-tuned human parsing models tend to fit towards each dataset in a specific domain or with discrepant label granularity, and can hardly be adapted to other human parsing…

cs.CV20195 cited

Cross-Entropy Adversarial View Adaptation for Person Re-identification

Lin Wu, Richang Hong, Yang Wang +1

Person re-identification (re-ID) is a task of matching pedestrians under disjoint camera views. To recognise paired snapshots, it has to cope with large cross-view variations cause…

cs.CV2019

Quality-aware Unpaired Image-to-Image Translation

Lei Chen, Le Wu, Zhenzhen Hu +1

Generative Adversarial Networks (GANs) have been widely used for the image-to-image translation task. While these models rely heavily on the labeled image pairs, recently some GAN…

cs.CV20182 cited

Learning Symmetry Consistent Deep CNNs for Face Completion

Xiaoming Li, Ming Liu, Jieru Zhu +4

Deep convolutional networks (CNNs) have achieved great success in face completion to generate plausible facial structures. These methods, however, are limited in maintaining global…

cs.CV2018

3D PersonVLAD: Learning Deep Global Representations for Video-based Person Re-identification

Lin Wu, Yang Wang, Ling Shao +1

In this paper, we introduce a global video representation to video-based person re-identification (re-ID) that aggregates local 3D features across the entire video extent. Most of…