葡京3522新地址

余宙 

副教授

硕士生导师

计算机科学与技术

人工智能、多媒体内容分析

Email
yuz@hdu.edu.cn
Address
杭州电子科技大学下沙校区3教417
Phone
17767264310

余宙,副教授,杭州电子科技大学计算机学院,教育部“复杂系统建模与仿真”实验室与“媒体智能”创新团队成员。研究方向包括人工智能、机器学习、跨媒体内容理解与知识推理等。发表ACM/IEEE  Transactions以及CCF  A类会议论文近20篇;是权威期刊如IEEE T-PAMI、T-NNLS、T-IP、T-MM, T-CSVT、Information Sciences、Neurocomputing 的审稿人和顶级会议如IJCAI(2018/19/20)、AAAI(2019/20)的程序委员会成员;带领团队获得视觉问答挑战赛VQA Challenge 17/18/19年1次冠军2次亚军,指导的硕士研究生2人获得国家奖学金。

期刊论文 († 通讯作者)
1. Jun Yu, Jinghan Yao, Jian Zhang
†, Zhou Yu, Dacheng Tao,

SPRNet: Single Pixel Reconstruction for One

stage Instance Segmentation

, IEEE Transactions on Cybernetics (T

CYB), 51(4), 1731

1742, 2021.
(ESI 热
点论文)
2. Ting Yu, Jun Yu†, Zhou Yu, Qingming Huang, Qi Tian,

Long

Term Video Question Answering via Mul

timodal Hierarchical Memory Attentive Networks

, IEEE Transactions on Circuits and Systems for Video
Technology (T

CSVT), 31(3): 931

944, 2020.
3. Jun Yu, Jing Li, Zhou Yu† , Qingming Huang,

Multimodal Transformer with Multi

View Visual Represen

tation for Image Captioning

, IEEE Transactions on Circuits and Systems for Video Technology (T

CSVT),
30(12), 4467

4480, 2020.
(MSCOCO Image Captioning 挑战赛实施排行榜第

名,ESI 高被引论文)
4. Ting Yu, Jun Yu†, Zhou Yu, Dacheng Tao,

Compositional Attention Networks with Two

Stream Fusion for
Video Question Answering

, IEEE Transactions on Image Processing (T

IP), 29, 1204

1218, 2019.
5. Zhou Yu, Jun Yu† , Chenchao Xiang, Jianping Fan, Dacheng Tao,

Beyond Bilinear: Generalized Multimodal
Factorized High

order Pooling for Visual Question Answering

, IEEE Transactions on Neural Networks and
Learning Systems (T

NNLS), 29(12): 5947

5959, 2018.
(VQA Challenge 2017/2018 亚军方法,当年冠军
分别为微软和 Facebook 研究院)
6.
俞俊, 汪亮, 余宙† ,

视觉问答技术研究

, 计算机研究与发展, 55(9): 1946

1958, 2018.
7. Min Tan, Jun Yu†, Zhou Yu, Fei Gao, Yong Rui, Dacheng Tao,

User

Click

Data

Based Fine

Grained Image
Recognition via Weakly Supervised Metric Learning

, ACM Transactions on Multimedia Computing, Commu

nications, and Applications (ToMM), 14(3): 70, 2018.
8. Fei Wu, Zhou Yu, Yi Yang, Siliang Tang, Yin Zhang, Yueting Zhuang,

Sparse Multi

Modal Hashing

, IEEE
Transactions on Multimedia (T

MM), 16(2): 427

439, 2014.
会议论文
1. Yuhao Cui, Zhou Yu† , Chunqi Wang, Zhongzhou Zhao, Ji Zhang, Meng Wang, Jun Yu,

ROSITA: Enhancing
vision

and

language semantic alignments via cross

and intra

modal knowledge integration

, ACM Internation

al Conference on Multimedia (ACM MM), Chengdu, China, 2021.
2. Zhou Yu, Yuhao Cui, Jun Yu† , Dacheng Tao, Qi Tian,

Deep Multimodal Neural Architecture Search

, ACM
International Conference on Multimedia (ACM MM), Seattle, USA, 2020.
3. Zhou Yu, Jun Yu† , Yuhao Cui, Dacheng Tao, Qi Tian,

Deep Modular Co

Attention Networks for Visual
Question Answering

, IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Long Beach,
USA, 2019.
(VQA Challenge 2019 冠军方法,当年亚军为微软亚洲研究院)
4. Zhou Yu, Dejing Xu, Jun Yu† , Ting Yu, Zhou Zhao, Yueting Zhuang, Dacheng Tao,

ActivityNet

QA: A
Dataset for Understanding Complex Web Videos via Question Answering

, AAAI Conference on Artifificial
Intelligence (AAAI), Honolulu, USA, 2019.
5. Zhou Yu, Jun Yu† , Chenchao Xiang, Zhou Zhao, Qi Tian, Dacheng Tao,

Rethinking Diversifified and Discrim

inative Proposal Generation for Visual Grounding

, International Joint Conference on Artifificial Intelligence
(IJCAI), Stockholm, Sweden, 2018.
6. Zhou Zhao, Zhu Zhang, Shuwen Xiao, Zhou Yu, Jun Yu, Deng Cai, Fei Wu, Yueting Zhuang,

Open

Ended
Long

form Video Question Answering via Adaptive Hierarchical Reinforced Networks

, International Joint
Conference on Artifificial Intelligence (IJCAI), Stockholm, Sweden, 2018.
7. Yibing Zhan, Jun Yu†, Zhou Yu, Rong Zhang, Dacheng Tao, Qi Tian,

Comprehensive Distance

Preserving
Autoencoders for Cross

Modal Retrieval

, ACM Conference on Multimedia (ACM MM), Seoul, Korea, 2018.
8. Zhou Yu, Jun Yu† , Jianping Fan, Dacheng Tao,

Multi

modal Factorized Bilinear Pooling with Co

attention
Learning for Visual Question Answering

, International Conference on Computer Vision (ICCV), Venice, Italy,
2017.
9. Zhou Yu, Fei Wu, Yi Yang, Qi Tian, Jiebo Luo, Yueting Zhuang,

Discriminative Coupled Dictionary Hashing
for Fast Cross

Media Retrieval

, ACM Special Interest Group on Information Retrieval (SIGIR), Gold Coast,
Australia, 2014.
10. Zhou Yu, Fei Wu, Yin Zhang, Siliang Tang, Jian Shao, Yueting Zhuang,

Hashing with List

wise Learning to
Rank

, ACM Special Interest Group on Information Retrieval (SIGIR), Gold Coast, Australia, 2014.
11. Yueting Zhuang, Zhou Yu, Wei Wang, Fei Wu, Siliang Tang, Jian Shao,

Cross

media hashing with neural
networks

, ACM Conference on Multimedia (ACM MM), Orlando, USA, 2014.

  1. 可信跨媒体分析推理,浙江省自然科学基金杰青项目,LR22F020001,2022-2024,80 万,主持
  1. 外部“数据-知识”联合增强的视觉问答方法研究,国家自然科学基金面上项目,62072147,2021-2024,68.4 万,主持
  1. 基于端到端统一建模的图像内容问答算法研究,国家自然科学基金青年项目,61702143,2018-2020,33.6 万,主持
  1. 基于新闻报道场景的 AI 辅助写稿机器人系统研发,国家重点研发计划,61702143,2021-2023,1398 万,子课题负责人(7/139
  1. 跨媒体因果推断理论与方法,科技创新 2030-“新一代人工智能”

重大项目课题,2018AAA0100603,2019-2022,168 万,参与 (3/29)

  1. 基于大规模跨媒体知识网络的复杂视频问答方法研究,国家自然科学基金重点项目,61836002,2019-2023,344.4 万,参与(4/10
  1. 面向海量 Web 图像的层次式多任务物体识别方法研究,国家自然科学基金面上项目,61772161,2018-2021,79.2 万,参与(3/10
  1. 基于层次深度网络混合模型的图像识别技术研究,国家自然科学基金青年项目,61806063,2019-2021,33.6 万,参与(2/9
  1. 基于多模态表征学习的时尚数据检索与推荐算法研究,国家自然科学基金青年项目,61806063,2019-2021,32.4 万,参与(2/10
  1. 基于跨平台多模态深度迁移网络的目标分类方法研究,浙江省自然科学基金探索项目,Y19F020117,2019-2021,10 万,参与(3/10)
  1. 图像异构模态计算理论与方法,浙江省自然科学一等奖,2020 年度,个人排名:2/4
  1. 第五届中国科协青年人才托举工程,2019 年度
  1. ACM 杭州新星奖,2021 年度
  2. 第一届浙江省高校领军人才培养计划(青年优秀人才),2020 年度
  1. 全球视觉问答挑战赛 VQA Challenge 2019冠军、2018 亚军、2017 亚军