Get our free extension to see links to code for papers anywhere online!

Add to Chrome

Add to Firefox

Picture for Wengang Zhou

Wengang Zhou

UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Oct 15, 2022
Yonghui Wang, Wengang Zhou, Zhenbo Lu, Houqiang Li

Figure 1 for UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Figure 2 for UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Figure 3 for UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Figure 4 for UDoc-GAN: Unpaired Document Illumination Correction with Background Light Prior

Access Paper or Ask Questions

Geometric Representation Learning for Document Image Rectification

Oct 15, 2022
Hao Feng, Wengang Zhou, Jiajun Deng, Yuechen Wang, Houqiang Li

Figure 1 for Geometric Representation Learning for Document Image Rectification

* This paper has been accepted by ECCV 2022

Access Paper or Ask Questions

CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

Aug 30, 2022
Yunyao Mao, Wengang Zhou, Zhenbo Lu, Jiajun Deng, Houqiang Li

Figure 1 for CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

Figure 2 for CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

Figure 3 for CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

Figure 4 for CMD: Self-supervised 3D Action Representation Learning with Cross-modal Mutual Distillation

* To appear in ECCV 2022 (Oral)

Access Paper or Ask Questions

TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

Jun 14, 2022
Jiajun Deng, Zhengyuan Yang, Daqing Liu, Tianlang Chen, Wengang Zhou, Yanyong Zhang, Houqiang Li, Wanli Ouyang

Figure 1 for TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

Figure 2 for TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

Figure 3 for TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

Figure 4 for TransVG++: End-to-End Visual Grounding with Language Conditioned Vision Transformer

* arXiv admin note: text overlap with arXiv:2104.08541

Access Paper or Ask Questions

Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

Jun 08, 2022
Minrui Wang, Mingxiao Feng, Wengang Zhou, Houqiang Li

Figure 1 for Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

Figure 2 for Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

Figure 3 for Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

Figure 4 for Stabilizing Voltage in Power Distribution Networks via Multi-Agent Reinforcement Learning with Transformer

* Accepted by KDD 2022 Research Track

Access Paper or Ask Questions

Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

May 08, 2022
Qing Li, Wengang Zhou, Zhenbo Lu, Houqiang Li

Figure 1 for Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

Figure 2 for Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

Figure 3 for Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

Figure 4 for Simultaneous Double Q-learning with Conservative Advantage Learning for Actor-Critic Methods

Access Paper or Ask Questions