Personal Profile
黄丹蓝,信息与通信工程学院特聘副研究员、博士生导师。入选博士后创新人才支持计划(2020年本学科全国9人入选),主持国家自然科学基金青年基金项目1项。主要研究方向为多媒体计算通信、语义通信、计算机视觉。相关成果在本领域权威期刊/会议上发表论文十余篇。
2020年1月获得清华大学电子系博士学位,师从陆建华院士。2018年1月-2018年7月于美国伊利诺伊大学香槟分校进行博士生访学。2014年7月获得西安交通大学信息工程专业学士学位。2020年1月-2022年7月于清华大学电子系从事博士后研究。2022年加盟北京邮电大学从事教学科研工作。
招生信息:
诚招2024级博士研究生1~2人!
如果你有较好的动手能力,且对多媒体计算通信、语义通信、计算机视觉与深度学习等研究方向感兴趣,欢迎和我一起探索学术前沿,提供耐心、细致、全方位的学术指导和人才培养。
联系方式:huangdl@bupt.edu.cn。
Good News:
指导学生参加2023“华为杯”无线通信算法菁英赛获得前10名!
研究方向:
1)面向6G的语义通信关键技术研究;
2)通信、感知、计算一体化研究。
所在团队:
泛网无线通信教育部重点实验室
基金项目:
[1] 2020年度博士后创新人才支持计划,BX20200194,基于语义的多媒体表征模型研究,2020.1–2022.1,主持
[2] 国自然青年基金项目,NSFC62101307,面向智慧交通的基于语义的图像信息表征方法研究,2022.1–2024.12,主持
[3] 清华大学-中国移动联合研究院6G研究中心,面向6G的智能网络信息服务架构,2020.11–2023.12,参与
[4] 国家重点研发计划子课题,数据与模型协同驱动的网络智能服务,2018YFB1800804,2019.7–2023.6,参与
[5] 国自然重大研究计划,基于贝叶斯统计的遥感影像在轨特征提取与压缩传输,NSFC91538107,2016.1–2018.12,参与
[6] 国自然面上项目,面向QoE的协同计算通信关键技术研究,NSFC61471220,2015.1–2018.12,参与
特邀报告:
“Semantic Image Representation in Multimedia Communications”, Chinese Academy of Sciences, The Frontier Forum of the China National Postdoctoral Program for Innovative Talents, Beijing, China, 2020.
审稿:
担任TPC Member: ICC Workshop on Semantic Communications 2022。
担任IEEE VTC 2022, 2023 Session Chair。
担任期刊/会议审稿人:IEEE TCOM, IEEE Communications Magazine, IEEE JSTSP, IEEE ACCESS, IEEE China Communications, IEEE Globecom, IEEE ICC, IEEE WCSP, IEEE ICNC等。
论文:
[1] S. Sun, D. Huang, X. Tao, C. Pan, G. Liu, and C. Chen. "Boosting Scene Graph Generation with Contextual Information", ACM Transactions on Multimedia Computing Communications and Applications, Accepted, 2023.
[2] S. Sun, D. Huang, Z. Qin, et. al.. "USGG: Union Message Based Scene Graph Generation", IEEE ICIP, Accepted, 2023.
[3] D. Huang, F. Gao, X. Tao and J. Lu. “Towards Semantic Communications: Deep Learning-Based Image Semantic Coding.” IEEE Journal on Selected Areas in Communications, Accepted, 2022. (IF: 13.081)
[4] D. Huang, X. Tao, C. Jiang, S. Cui and J. Lu. “Trace-Driven QoE-Aware Proactive Caching for Mobile Video Streaming in Metropolis.” in IEEE Transactions on Wireless Communications, vol. 19, no. 1, pp.62-76, Jan. 2020. (IF: 6.394)
[5] D. Huang, X. Tao, J. Lu and M. N. Do. “Geometry-Aware GAN for Face Attribute Transfer.” in IEEE ACCESS, vol. 7, pp. 145953-145969, 2019. (IF: 4.098)
[6] X. Tao, Y. You, M. Xu, Y. Duan, D. Huang and W. Liu. “Quality of Experience Oriented Multimedia Computing Communications.” Journal of Image and Graphics, 26(06): 1201-1215, 2021. (Invited)
[7] Z. Wang, Y. Li, D. Huang*, N. Ge*, and J. Lu. “DeformSg2im: Scene Graph Based Multi-Instance Image Generation with Deformable Geometric Layouts” Neurocomputing, Accepted. 2023. (co-corresponding author) (IF: 5.779)
[8] Z. Wang, Y. Luo, D. Huang, N. Ge and J. Lu. “Category-Adaptive Domain Adaptation for Semantic Segmentation.” ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Singapore, 2022.
[9] X. Peng, Z. Qin, D. Huang, X. Tao, and J. Lu, “A Robust Deep Learning Enabled Semantic Communication System for Text” , GLOBECOM 2022-2022 IEEE Global Communications Conference, 2022, Accepted
[10] D. Huang, X. Tao, F. Gao and J. Lu. “Deep Learning-Based Image Semantic Coding for Semantic Communications.” GLOBECOM 2021-2021 IEEE Global Communications Conference, Spain, 2021.
[11] Z. Wang, Y. Li, D. Huang, Y. Luo, N. Ge and J. Lu. “Deformable Geometry based Semantic Reconstruction from Scene Graphs.” GLOBECOM 2021 - 2021 IEEE Global Communications Conference, Spain, 2021.
[12] D. Huang, X. Tao, J. Lu and M. N. Do. “Geometry-Aware GAN for Face Attribute Transfer.” 2019 IEEE International Conference on Image Processing (ICIP), Taipei, Taiwan, 2019, pp. 729-733.
[13] D. Huang, X. Tao, C. Jiang, Y. Li and J. Lu. “Latency-Efficient Video Streaming in Metropolis: A Caching Framework.” GLOBECOM 2017 - 2017 IEEE Global Communications Conference, Singapore, 2017, pp. 1-6.
[14] D. Huang, X. Tao, M. Xu, S. Gao and J. Lu. “Image Compression via Multiple Learned Geometric Dictionaries.” 2016 IEEE Global Conference on Signal and Information Processing (GlobalSIP), Washington, DC, USA, 2016, pp. 1373-1377.