Search Results for author: Mingzhi Mao

Found 3 papers, 1 papers with code

Dual Adversarial Adaptation for Cross-Device Real-World Image Super-Resolution

1 code implementation CVPR 2022 Xiaoqian Xu, Pengxu Wei, Weikai Chen, Mingzhi Mao, Liang Lin, Guanbin Li

To address this issue, we propose an unsupervised domain adaptation mechanism for real-world SR, named Dual ADversarial Adaptation (DADA), which only requires LR images in the target domain with available real paired data from a source camera.

Image Super-Resolution Unsupervised Domain Adaptation

Incorporating Graph Attention Mechanism into Knowledge Graph Reasoning Based on Deep Reinforcement Learning

no code implementations IJCNLP 2019 Heng Wang, Shuangyin Li, Rong pan, Mingzhi Mao

Meanwhile, a novel mechanism of reinforcement learning is proposed by forcing an agent to walk forward every step to avoid the agent stalling at the same entity node constantly.

Graph Attention reinforcement-learning +1

Defeats GAN: A Simpler Model Outperforms in Knowledge Representation Learning

no code implementations3 Apr 2019 Heng Wang, Mingzhi Mao

The goal of knowledge representation learning is to embed entities and relations into a low-dimensional, continuous vector space.

Link Prediction Representation Learning

Cannot find the paper you are looking for? You can Submit a new open access paper.