刘宇

个人信息Personal Information

副教授

硕士生导师

性别:男

毕业院校:荷兰莱顿大学

学位:博士

所在单位:国际信息与软件学院

学科:软件工程

办公地点:信息楼323B

联系方式:0411-62273233

电子邮箱:liuyu8824@dlut.edu.cn

其他联系方式Other Contact Information

邮箱 : liuyu8824@dlut.edu.cn

扫描关注

个人简介Personal Profile

"What I cannot create, I do not understand " --Richard Feynman(理查德·费曼)


刘宇,副教授,硕士生导师,主要研究方向是计算机视觉,同时涉及机器学习深度学习自然语言处理等多个前沿领域。具体研究工作包括持续学习(递增学习,终身学习,半监督学习),小样本/零样本学习(目标检测/分割,行人重识别),多模态学习(图文匹配,视频检索,视觉问答系统)等。累计发表学术论文30余篇,包括计算机学会CCF推荐A类会议CVPRICCVECCVACM MMIJCAI,以及中科院分区Top期刊论文IEEE Transactions on Image Processing (TIP), IEEE Transactions on Multimedia (TMM), Pattern Recognition (PR)等。2016年合作发表的深度学习综述论文入选ESI高被引用论文(谷歌引用1000余次)。2017年提出的卷积融合网络(CFN)荣获CCF推荐C类会议MMM最佳论文奖,ICCV 2021杰出审稿人,入选大连市2021年新引进高层次人才(青年才俊)。


我们团队致力于将人工智能算法应用到以视觉为中心的真实生活场景中,热烈欢迎有志于投身此前沿科学领域的硕士生和博士生报考咨询,同时常年招收本科生参与实验室科研项目,欢迎邮件联系 liuyu8824@dlut.edu.cn,期待你的加入,一起探索未知!


工作经历:

2021.01—至今,大连理工大学,国际信息与软件学院,副教授

2019.01—2020.12,比利时鲁汶大学,电气工程学院 (ESAT),博士后(合作导师:Tinne Tuytelaars 教授


教育经历:

2014.09—2018.10,荷兰莱顿大学,计算机学院 (LIACS), 博士(导师:Michael S. Lew 教授)

2011.09—2014.07,大连理工大学,软件学院,硕士(导师:郭禾 教授)

2007.09—2011.07,大连理工大学,软件学院,学士(指导教师:贾棋 副教授)


主持项目:

1. 国家自然科学基金青年项目,2022.01~2024.12,主持

2. 中央高校基本科研业务费资助项目,2021.04~2023.04,主持


学术服务:

国际电气与电子工程师协会(IEEE)会员

中国计算机学会(CCF)会员

中国图象图形学学会(CSIG)会员

视觉与学习青年学者研讨会(Valse)执行领域主席

期刊审稿:TPAMI, IJCV, TIP, TNNLS, TMM, etc.

会议审稿:CVPR, ICCV, ECCV, ACM MM, AAAI, etc.

共同组织(Co-organizer)学术专题研讨会(Workshop):

  •     [CVPR 2021] 2nd Continual Learning in Computer Vision Workshop.

  •     [ECCV 2020] Commands For Autonomous Vehicles Workshop.

  •     [CVPR 2020] Efficient Deep Learning in Computer Vision Workshop.

  •     [ICCV 2019] Compact and Efficient Feature Representation and Learning Workshop.


代表性学术论文:

[TNNLS 2022] Yu Liu and Tinne Tuytelaars. “Residual Tuning: Towards Novel Category Discovery without Labels”, IEEE Transactions on Neural Networks and Learning Systems, 2022. 

[TIP 2020] Yu Liu and Tinne Tuytelaars. “A Deep Multimodal Explanation Model for Zero-shot Learning”, IEEE Transactions on Image Processing, 2020. 

[ECCV 2020] Yu Liu, Sarah Parisot, Gregory Slabaugh, Xu Jia, Ales Leonardis, Tinne Tuytelaars. “More Classifiers, Less Forgetting: A Generic Multi-classifier Paradigm for Incremental Learning”, European Conference on Computer Vision, 2020. 

[PR 2019] Yu Liu, Yanming Guo, Li Liu, Erwin M. Bakker, Michael S. Lew. “CycleMatch: A Cycle-consistent Embedding Network for Image-Text Matching”, Pattern Recognition, 2019. 

[TMM 2019] Yu Liu, Wei Chen, Li Liu, Michael S. Lew. “SwapGAN: A Multistage Generative Approach for Person-to-person Fashion Style Transfer”, IEEE Transactions on Multimedia, 2019. 

[PR 2018] Yu Liu, Li Liu, Yanming Guo, Michael S. Lew. “Learning Visual and Textual Representations for Multimodal Matching and Classification”, Pattern Recognition, 2018. 

[ICCV 2017] Yu Liu, Yanming Guo, Erwin M. Bakker, Michael S. Lew. “Learning a Recurrent Residual Fusion Network for Multimodal Matching”, IEEE International Conference on Computer Vision, 2017.

[CVPR 2016] Yu Liu, Michael S. Lew. “Learning Relaxed Deep Supervision for Better Edge Detection”, IEEE Conference on Computer Vision and Pattern Recognition, 2016. 

[TMM 2021] Wei Chen, Yu Liu, Nan Pu, Weiping Wang, Li Liu, Michael S. Lew. “Feature Estimations based Correlation Distillation for Incremental Image Retrieval”, IEEE Transactions on Multimedia, 2021. 

[MM 2021] Mingrui Lao, Yanming Guo, Yu Liu, Wei Chen, Nan Pu, Michael S. Lew. “From Superficial to Deep: Language Bias driven Curriculum Learning for Visual Question Answering”,  ACM International Conference on Multimedia, 2021. 

[CVPR 2021] Nan Pu, Wei Chen, Yu Liu*, Erwin M. Bakker, Michael S. Lew. “Lifelong Person Re-Identification via Adaptive Knowledge Accumulation”, IEEE Conference on Computer Vision and Pattern Recognition, 2021.

[MM 2020] Nan Pu, Wei Chen, Yu Liu, Erwin M. Bakker, Michael S. Lew. “Dual Gaussian-based Variational Subspace Disentanglement for Visible-Infrared Person Re-Identification”, ACM International Conference on Multimedia, 2020.

更多论文参见个人英文主页 http://liuyudut.github.io/


 

  • 教育经历Education Background
  • 工作经历Work Experience
  • 研究方向Research Focus
  • 社会兼职Social Affiliations
  • 深度持续学习(增量学习,终身学习)

    跨模态内容分析与检索

    零样本/小样本学习

    半监督学习与聚类