多媒体信息计算组
韦世奎
教授,博士生导师
电话:010-51683695
邮箱:shkwei@bjtu.edu.cn

依托项目

项目来源 项目名称 开始时间 结束时间 项目负责人
某单位 复杂环境下高效能弱小目标跟踪系统研发 2017.01 2017.12 韦世奎
某单位预研领域基金 基于深度学习的信号特征提取技术研究 2017.01 2017.12 韦世奎
中国移动通信有限公司研究院 面向眼科领域应用的医疗大数据平台及新业务研发 2017.01 2017.12 韦世奎
教育部-中国移动联合基金 多媒体数字取证技术与语义实时处理技术在新型不良信息治理中的应用 2017.01 2018.12 韦世奎
某公司 汽车全自动泊车系统 2016.07 2017.12 韦世奎
某公司 汽车高级驾驶辅助系统(ADAS) 2016.07 2017.06 韦世奎
国家自然科学基金“重点” 混杂数据的模式识别及敏感内容挖掘理论与方法 2016.01 2020.12 赵耀
国家自然科学基金“面上” 跨媒体协同计算及近邻可逆性问题研究 2016.01 2019.12 韦世奎
湖北省水电工程智能视觉监测重点实验室 水电工程安全监测中异构信息智能分析与理解 2015.01 2016.01 韦世奎
基本科研业务费 基于深度结构的街景元信息检测与识别问题研究 2015.01 2016.12 韦世奎
中国中医科学研究院 基于图论的艾滋病辩证论治辅助决策模型研究 2013.09 2014.10 韦世奎
中国中医科学研究院 中药量效关系的自适应设计―贝叶斯 预测模型优化研究 2013.09 2015.03 韦世奎
教育部“创新团队” “数字媒体信息处理”教育部创新团队 2013.01 2015.12 赵耀
国家自然科学基金“青年” 社交网络中数字媒体的扩散跟踪及关联建模 2013.01 2015.12 韦世奎
中国科学院国家重点实验室开放基金 基于视频拷贝检测的关联建模研究社交媒体信息扩散及 2013.01 2015.01 韦世奎
基本科研业务费 基于可视媒体重复检测的信息扩散及关联建模研究 2013.01 2014.12 韦世奎
人才基金 大规模社会网络媒体的增量整合及关联建模 2012.01 2013.12 韦世奎
科技部“973”课题 跨媒体数据统一表示和建模机制 2012.01 2016.12 赵耀

主要论著

2017:

Two-stream Attentive CNNs for Image Retrieval      
Fei Yang ,Jia Li, Shikui Wei, QinjieZheng,Ting Liu, Yao Zhao, Two-stream Attentive CNNs for Image Retrieval, ACM Multimedia, (1513-1521)2017.
Abstract:  Fei Yang ,Jia Li, Shikui Wei, QinjieZheng,Ting Liu, Yao Zhao, Two-stream Attentive CNNs for Image Retrieval, ACM Multimedia, (1513-1521)2017.

Magic-wall: Visualizing Room Decoration      
Ting Liu, Yunchao Wei,Yao Zhao,Si Liu, Shikui Wei, Magic-wall: Visualizing Room Decoration, ACM Multimedia,(429-437)2017.
Abstract:  Ting Liu, Yunchao Wei,Yao Zhao,Si Liu, Shikui Wei, Magic-wall: Visualizing Room Decoration, ACM Multimedia,(429-437)2017.

Finding the Secret of CNN Parameter Layout under Strict Size Constraint      
Lixin Liao,Yao Zhao,Shikui Wei, Jingdong Wang,Ruoyu Liu, Finding the Secret of CNN Parameter Layout under Strict Size Constraint, ACM Multimedia , (997-1005)2017.
Abstract:  Lixin Liao,Yao Zhao,Shikui Wei, Jingdong Wang,Ruoyu Liu, Finding the Secret of CNN Parameter Layout under Strict Size Constraint, ACM Multimedia , (997-1005)2017.

Enhanced isomorphic semantic representation for cross-media retrieval      
Ting Liu, Yao Zhao,Shikui Wei,Yunchao Wei, Lixin Liao, Enhanced isomorphic semantic representation for cross-media retrieval,2017 IEEE International Conference on Multimedia and Expo (ICME), (967-972)2017.
Abstract: Ting Liu, Yao Zhao,Shikui Wei,Yunchao Wei, Lixin Liao, Enhanced isomorphic semantic representation for cross-media retrieval,2017 IEEE International Conference on Multimedia and Expo (ICME), (967-972)2017.

Enhancing heterogeneous similarity estimation via neighborhood reversibility      
Wei S, Zhao Y, Yang T, et al. Enhancing heterogeneous similarity estimation via neighborhood reversibility[J]. 2017.
Abstract: Enhancing heterogeneous similarity estimation via neighborhood reversibility

Multi-view Cross-media Hashing with Semantic Consistency      
Ruoyu Liu,Yao Zhao, Liang Zheng, Shikui Wei,Yi Yang, Multi-view Cross-media Hashing with Semantic Consistency[J], IEEE Multimedia, 2017.
Abstract: Ruoyu Liu,Yao Zhao, Liang Zheng, Shikui Wei,Yi Yang, Multi-view Cross-media Hashing with Semantic Consistency[J], IEEE Multimedia, 2017.

Stabilizing Object Tracking Trajectory on the Basis of Kalman Filter      
Tao,Ruan, Shikui Wei,Xuetao Du, Yao Zhao,Stabilizing Object Tracking Trajectory on the Basis of Kalman Filter.2017 IEEE Third International Conference on Multimedia Big Data(BigMM), (370-375)2017.
Abstract: Tao,Ruan, Shikui Wei,Xuetao Du, Yao Zhao,Stabilizing Object Tracking Trajectory on the Basis of Kalman Filter.2017 IEEE Third International Conference on Multimedia Big Data(BigMM), (370-375)2017.

A Vehicle-Mounted Multi-Camera 3D Panoramic Imaging Algorithm Based on Ship-Shaped Mode    
Xin Wang, Chunyu Lin, Yi Gao, Yaru Li, Shikui Wei, Yao Zhao, A Vehicle-Mounted Multi-Camera 3D Panoramic Imaging Algorithm Based on Ship-Shaped Mode, International Conference on Image and Graphics
Abstract: Xin Wang, Chunyu Lin, Yi Gao, Yaru Li, Shikui Wei, Yao Zhao, A Vehicle-Mounted Multi-Camera 3D Panoramic Imaging Algorithm Based on Ship-Shaped Mode, International Conference on Image and Graphics

基于多尺度区域块的糖尿病性视网膜病变级联检测    
马文婷,赵 耀8,韦世奎,张诗吟,廖理心, 基于多尺度区域块的糖尿病性视网膜病变级联检测, 北京交通大学学报,2017
Abstract: 马文婷,赵 耀8,韦世奎,张诗吟,廖理心, 基于多尺度区域块的糖尿病性视网膜病变级联检测, 北京交通大学学报,2017

3D Surround View for Advanced Driver Assistance Systems    
Yi Gao, Chunyu Lin, Yao Zhao, Xin Wang, Shikui Wei, Qi Huang, 3D Surround View for Advanced Driver Assistance Systems, IEEE Transactions on Intelligent Transportation Systems, vol. PP, no. 99, pp. 1-9.doi: 10.1109/TITS.2017.2750087
Abstract: Yi Gao, Chunyu Lin, Yao Zhao, Xin Wang, Shikui Wei, Qi Huang, 3D Surround View for Advanced Driver Assistance Systems, IEEE Transactions on Intelligent Transportation Systems, vol. PP, no. 99, pp. 1-9.doi: 10.1109/TITS.2017.2750087

Creating video summarization from emotion perspective    
LanYijie, Shikui Wei, Ruoyu Liu,Yao Zhao,Creating video summarization from emotion perspective. International Conference on Signal Processing IEEE, (1112-1117)2017.
Abstract: LanYijie, Shikui Wei, Ruoyu Liu,Yao Zhao,Creating video summarization from emotion perspective. International Conference on Signal Processing IEEE, (1112-1117)2017.

2016:

Modality-dependent Cross-media Retrieval      
Yunchao Wei, Yao Zhao, Zhenfeng Zhu, Yanhui Xiao, Shikui Wei, Jiashi Feng and Shuicheng Yan. Modality-dependent Cross-media Retrieval. ACM Transactions on Intelligent Systems and Technology (TIST), 2015.
Abstract: Modality-dependent Cross-media Retrieval.

Cross-modal Retrieval with CNN Visual Features: A New Baseline.    
Yunchao Wei, Yao Zhao, Canyi Lu, Luoqi Liu, Zhenfeng Zhu, Shikui Wei, and Shuicheng Yan. Cross-modal Retrieval with CNN Visual Features: A New Baseline. IEEE Transactions on Cybernetics (TCYB), 2015.(minor)
Abstract: Cross-modal Retrieval with CNN Visual Features: A New Baseline.

Light-weight Binary Code Embedding of Local Feature Distribution in Image Search      
Shikui Wei, Yao Zhao, Jia Li, Yan Zhang. Light-weight Binary Code Embedding of Local Feature Distribution in Image Search, Neurocomputing, 2015.
Abstract:  Light-weight Binary Code Embedding of Local Feature Distribution in Image Search

2015:

Kernel Reconstruction ICA for Sparse Representation      
Yanhui Xiao, Zhu Zhenfeng, and Yao Zhao, Yunchao Wei, Shikui Wei. Kernel Reconstruction ICA for Sparse Representation, IEEE Transactions on Neural Networks and Learning Systems, vol.26, no. 6, pp.1222-1232, 2015.
Abstract: Kernel Reconstruction ICA for Sparse Representation

Heterogeneous data alignment for cross-media computing      
Shikui Wei, Lei Zhang, Zhenfeng Zhu, Yao Zhao. Heterogeneous data alignment for cross-media computing. In Proceedings of the 7th International Conference on Internet Multimedia Computing and Service, 2015
Abstract:  Heterogeneous data alignment for cross-media computing

Redundancy filtering and fusion verification for video copy detection      
Shikui Wei , Su Jiang, Wenxian Jin, Yao Zhao, Rongrong Ni, Zhenfeng Zhu, Redundancy filtering and fusion verification for video copy detection, vol.21, no.2, pp.207-216, 2015.
Abstract:  Redundancy filtering and fusion verification for video copy detection

基于近邻可逆性验证的异构数据相似性度量方法    
杨涛,韦世奎,朱振峰, 赵耀, 基于近邻可逆性验证的异构数据相似性度量方法, 计算机科学与探索, 2015.
Abstract:  基于近邻可逆性验证的异构数据相似性度量方法

Photo linker: a system for finding your old photos based on fragmentary memories.      
Shikui Wei, Fan Yang, Tao Ruan, Ruoyu Liu, Zhenfeng Zhu, Yao Zhao. Photo linker: a system for finding your old photos based on fragmentary memories. In Proceedings of the 7th International Conference on Internet Multimedia Computing and Service, 2015.
Abstract: Photo linker: a system for finding your old photos based on fragmentary memories.

Light-Weight Spatial Distribution Embedding of Adjacent Features for Image Search      
Yan Zhang, Yao Zhao, Shikui Wei, Zhenfeng Zhu, Light-Weight Spatial Distribution Embedding of Adjacent Features for Image Search, Computer Vision. Springer Berlin Heidelberg, 387-397, 2015.
Abstract: Light-Weight Spatial Distribution Embedding of Adjacent Features for Image Search

Cross-media hashing with Centroid Approaching      
Ruoyu Liu, Yao Zhao, Shikui Wei, Zhenfeng Zhu. Cross-media hashing with Centroid Approaching. IEEE International Conference on Multimedia and Expo (ICME), pp. 1-6, 2015.
Abstract: Cross-media hashing with Centroid Approaching

2014:

Topographic NMF for Data Representation      
Yanhui Xiao, Zhenfeng Zhu, Yao Zhao, Yunchao Wei, Shikui Wei, Xuelong Li, “Topographic NMF for Data Representation”, IEEE Transactions on Cybernetics, vol.44, no.10, pp.1762-1771, 2014..
Abstract:  Topographic NMF for Data Representation

Mining Semantically Consistent Patterns for Cross-View Data      
Lei Zhang,Yao Zhao, Zhenfeng Zhu,Shikui Wei,Xindong Wu, “Mining Semantically Consistent Patterns for Cross-View Data”. IEEE Transactions Knowledge and Data Engineering, vol.26, no.1, pp.2745-2758, 2014.
Abstract: Mining Semantically Consistent Patterns for Cross-View Data

Accumulated Reconstruction Error Vector: A Semantic Representation for Cross-Media Retrieval      
Kai Liu, Shikui Wei, Yao Zhao, Zhenfeng Zhu, Y. Wei, C. Xu, Accumulated Reconstruction Error Vector: A Semantic Representation for Cross-Media Retrieval, Multimedia Tools and Applications, 2014
Abstract: Accumulated Reconstruction Error Vector: A Semantic Representation for Cross-Media Retrieval

Learning a Mid-level Feature Space for Cross-media Regularization,      
Yunchao Wei, Yao Zhao, Zhenfeng Zhu,Yanhui Xiao, Shikui Wei, “Learning a Mid-level Feature Space for Cross-media Regularization,” IEEE International Conference on Multimedia Expo, 2014.
Abstract: Learning a Mid-level Feature Space for Cross-media Regularization,

2013:

Joint Optimization towards Effective and Efficient Image Search      
Shikui Wei, Dong Xu, Xuelong Li, Yao Zhao, “Joint Optimization towards Effective and Efficient Image Search,” IEEE Transactions on Cybernetics, vol. 43, no. 6, pp. 2216-2227, 2013.
Abstract:  Joint Optimization towards Effective and Efficient Image Search

Neighborhood Reversibility Verifying for Image Search      
Zhong Zheng, Yao Zhao, Shikui Wei, Zhenfeng Zhu, “Neighborhood Reversibility Verifying for Image Search,” IEEE International Conference on Multimedia Expo, 2013(Oral Paper).
Abstract:  Neighborhood Reversibility Verifying for Image Search

Orthogonal Graph-Regularized Factorization and its Application for Recommendation      
Zhenfeng Zhu, Peilu Xin, Shikui Wei, Yao Zhao , “Orthogonal Graph-Regularized Factorization and its Application for Recommendation”, IEEE International Conference on Multimedia Expo, 2013(Oral Paper).
Abstract:  Orthogonal Graph-Regularized Factorization and its Application for Recommendation

Multiple PiPs Detection in Unbounded Video System      
Chengdong Cui, Yao Zhao, Shikui Wei, Zhenfeng Zhu, “Multiple PiPs Detection in Unbounded Video System,” IEEE International Conference on Multimedia Expo, 2013(Workshop Paper).
Abstract:  Multiple PiPs Detection in Unbounded Video System

Frame Filtering and Path Verification for Improving Video Copy Detection      
Su Jiang, Yao Zhao, Shikui Wei, Rongrong Ni, Zhenfeng Zhu, “Frame Filtering and Path Verification for Improving Video Copy Detection,” International Conference on Internet Multimedia Computing and Service, 2013.
Abstract:  Frame Filtering and Path Verification for Improving Video Copy Detection

2012:

Copy Detection Using Graphical Model: HMM for Frame Fusion    
Shikui Wei, Yao Zhao and Zhenfeng Zhu, “Copy Detection Using Graphical Model: HMM for Frame Fusion,” Chapter 14 in Book “Graph-Based Methods in Computer Vision:Developments and Applications”, IGI Global, USA, 2012.
Abstract:  Copy Detection Using Graphical Model: HMM for Frame Fusion

Key Factors for Large Scale Visual Vocabulary      
Shikui Wei and Yao Zhao, Zhenfeng Zhu, “Key Factors for Large Scale Visual Vocabulary,” IEEE International Conference on Computer Science & Education, 2012.
Abstract:  Copy Detection Using Graphical Model: HMM for Frame Fusion

Discriminative ICA Model with Reconstruction Constraint for Image Classification      
Yanhui Xiao, Zhenfeng Zhu, Shikui Wei and Yao Zhao, “Discriminative ICA Model with Reconstruction Constraint for Image Classification,” ACM Conference on Multimedia, 2012.
Abstract:  Discriminative ICA Model with Reconstruction Constraint for Image Classification

2011:

Frame Fusion for Video Copy Detection      
Shikui Wei, Yao Zhao, Ce Zhu, Changsheng Xu and Zhenfeng Zhu, “Frame Fusion for Video Copy Detection,” IEEE Transactions on Circuits and Systems for Video Technology , vol.21, no.1, pp.15-28, 2011.
Abstract:  Frame Fusion for Video Copy Detection

Copy Detection towards Semantic Mining for Video Retrieval      
Shikui Wei, Yao Zhao, Changsheng Xu and Dong Xu, “Copy Detection towards Semantic Mining for Video Retrieval,” International Conference on Image Processing(ICIP2011,oral), 2011 .
Abstract:  Copy Detection towards Semantic Mining for Video Retrieval

Partitioned K-Means Clustering for Fast Construction of Unbiased Visual Vocabulary      
Shikui Wei and Dong Xu, “Partitioned K-Means Clustering for Fast Construction of Unbiased Visual Vocabulary,” the 12th Pacific Rim Conference on Multimedia, 2011.
Abstract:  Partitioned K-Means Clustering for Fast Construction of Unbiased Visual Vocabulary

Design of Representation Scheme towards Better Image Search      
Shikui Wei and Yao Zhao, “Design of Representation Scheme towards Better Image Search,”IEEE International Conference on Computer Science & Education, 2011.
Abstract:  Design of Representation Scheme towards Better Image Search

2010:

Multimodal Fusion for Video Search Reranking      
Shikui Wei, Yao Zhao, Zhenfeng Zhu and Nan Liu, “ Multimodal Fusion for Video Search Reranking,” IEEE Transactions on Knowledge and Data Engineering, vol. 22, no. 8, pp. 1191-1199, 2010.
Abstract:  Multimodal Fusion for Video Search Reranking

A Cooperative Learning Scheme for Interactive Video Search      
Shikui Wei, Yao Zhao, Zhenfeng Zhu and Nan Liu, “A Cooperative Learning Scheme for Interactive Video Search,” The Journal of Signal Processing Systems, Spring, vol. 59, no. 2, pp. 189-199, 2010 .
Abstract:  A Cooperative Learning Scheme for Interactive Video Search

基于多证据融合的视频排序方法    
韦世奎, 赵耀, 朱振峰, “基于多证据融合的视频排序方法”, 电子学报, vol.38, no.1, pp.1-6, 2010 .
Abstract: 基于多证据融合的视频排序方法

Semi-Supervised Learning with Density-Sensitive Manifold Graph      
Zheng Wang, Yao Zhao and Shikui Wei, “Semi-Supervised Learning with Density-Sensitive Manifold Graph,” IEEE International Conference on Signal Processing, 2010.
Abstract:  Semi-Supervised Learning with Density-Sensitive Manifold Graph

2008:

Ontology-Based Inter-Concept Relation Fusion for Concept Detection      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, “Ontology-Based Inter-Concept Relation Fusion for Concept Detection,” the 9th Pacific Rim Conference on Multimedia, 2008.
Abstract:  Ontology-Based Inter-Concept Relation Fusion for Concept Detection

2007:

A Cooperative Learning Strategy for Interactive Video Search      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, “A Cooperative Learning Strategy for Interactive Video Search,” IEEE International Conference on Information, Communications and Signal Processing, 2007 .
Abstract:  A Cooperative Learning Strategy for Interactive Video Search

BJTU TRECVID 2007 Video Search      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, Nan Liu, Yufeng Zhao, Liang Zhang and Fang Wang, “BJTU TRECVID 2007 Video Search,” TREC Video Retrieval Evaluation Online Proceedings, 2007.
Abstract:  BJTU TRECVID 2007 Video Search

2006:

Multilevel Indexing Structure for Object Based Image Retrieval      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, “Multilevel Indexing Structure for Object Based Image Retrieval,” IEEE International Conference on Signal Processing, 2006 .
Abstract:  BJTU TRECVID 2007 Video Search

BJTU TRECVID 2006 Video Retrieval System      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, Nan Liu, Yufeng Zhao, Liang Zhang and Fang Wang, “BJTU TRECVID 2006 Video Retrieval System,” TREC Video Retrieval Evaluation Online Proceedings, 2006.
Abstract: BJTU TRECVID 2006 Video Retrieval System

2005:

Meaningful Regions Segmentation in CBIR      
Shikui Wei, Yao Zhao and Zhenfeng Zhu, “Meaningful Regions Segmentation in CBIR,” IEEE International Conference on VLSI Design and Video Technology, 2005.
Abstract:  Meaningful Regions Segmentation in CBIR


主要专利

  • 一种基于视频重构的重复片段定位方法,   韦世奎,赵耀,朱振峰,   ZL 201210182770.3
  • 基于相机指纹特征的社交网络用户的识别方法和系统,   韦世奎;蒋翔;赵瑞珍;赵耀;,   CN201510756440.4
  • 视觉词典构建及应用方法和装置,   韦世奎;赵耀;朱振峰;杜雪涛;张晨;杜刚;朱艳云;,   CN201210182770.3
  • 一种基于多视角的交互式视频搜索方法,   赵耀;韦世奎;朱振峰;,   CN200710099532.5