个人简历学术成果简介  

刘宇男，博士，研究方向为深度学习与计算机视觉，已发表高水平学术论文40余篇，授权国家发明专利4项。主持国家自然科学基金青年项目1项、博士后面上基金1项，以及山东省、江苏省重点实验室开放课题各1项，参与国家自然科学基金项目4项。担任CVPR、ICCV、NeurIPS、TIP、TMM、PR等国际期刊与会议的审稿人。代表性论文如下：

[1] From simple to complex scenes: learning robust feature representations for accurate human parsing. IEEE TPAMI, 2024. (首位, CCF A)

[2] An accurate and lightweight method for human body image super-resolution. IEEE TIP, 2021. (首位, CCF A)

[3] Learning to adapt via latent domains for adaptive semantic segmentation. In: NeurIPS, 2021. (首位, CCF A)

[4] Hierarchical information passing based noise-tolerant hybrid learning for semi-supervised human parsing. In: AAAI, 2021. (首位, CCF A)

[5] Hybrid resolution network using edge guided region mutual information loss for human parsing. In: ACM MM, 2020. (首位, CCF A)

[6] Intermediate domain based meta learning framework for adaptive object detection. IEEE TCSVT, 2024. (通讯, CCF B)

[7] A lightweight network with latent representations for UAV thermal image super-resolution. IEEE TGRS, 2024. (通讯, CAAI A/CCF B)

[8] Mask-guided mamba fusion for drone-based visible-infrared vehicle detection. IEEE TGRS, 2024. (通讯, CAAI A/CCF B)