检索结果-内蒙古大学图书馆

Multi-Order Neighborhood Fusion Based Multi-View Deep Subspace Clustering

Computers, Materials & Continua 2025年第3期82卷 3873-3890页

作者： Kai Zhou Yanan Bai Yongli Hu Boyue Wang Department of Automation Tsinghua UniversityBeijing100084China National Center of Technology Innovation for Intelligentization of Politics and Law Beijing100000China Beijing Key Lab of Intelligent Telecommunication Software and Multimedia Beijing University of TechnologyBeijing100124China

Existing multi-view deep subspace clustering methods aim to learn a unified representation from multi-view data,while the learned representation is difficult to maintain the underlying structure hidden in the origin samples,especially the high-order neighbor relationship between *** overcome the above challenges,this paper proposes a novel multi-order neighborhood fusion based multi-view deep subspace clustering *** creatively integrate the multi-order proximity graph structures of different views into the self-expressive layer by a multi-order neighborhood fusion *** this design,the multi-order Laplacian matrix supervises the learning of the view-consistent self-representation affinity matrix;then,we can obtain an optimal global affinity matrix where each connected node belongs to one *** addition,the discriminative constraint between views is designed to further improve the clustering performance.A range of experiments on six public datasets demonstrates that the method performs better than other advanced multi-view clustering *** code is available at https://***/songzuolong/MNF-MDSC(accessed on 25 December 2024).

关键词： Multi-view subspace clustering subspace clustering deep clustering multi-order graph structure

来源：评论

学校读者我要写书评

暂无评论

CSBNC-PAL: Consistency Semi-supervised Brain Network Classification Framework with Prototypical-Adversarial Learning

引用

IEEE Journal of Biomedical and Health Informatics 2025年 PP卷 PP页

作者： Ji, Junzhong Liu, Gan Wang, Xingyu Beijing University of Technology Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science Beijing Artificial Intelligence Institute Beijing100124 China

In recent years, semi-supervised learning (SSL) for functional brain network (FBN) classification has gained considerable attention due to its potential to leverage large amounts of unlabeled data from multisite. However, existing SSL methods often struggle to address the distributional differences across different sites, which limits their ability to extract discriminative features from the unlabeled data, thus hindering classification performance. To overcome this challenge, we propose a novel consistency semi-supervised FBN classification framework with prototypical-adversarial learning, termed CSBNC-PAL. Specifically, we first design a contrastive consistency module (CCM) that utilizes contrastive learning to more effectively exploit unlabeled data and learn preliminary feature representations. Then, we introduce a prototype alignment module (PAM) that computes site-aware prototypes through weighted feature clustering to guide inter-site feature alignment, and achieve inter-site equilibrium feature representations. Finally, we develop an adversarial alignment module (AAM) that employs site-discriminative adversarial training based on a gradient reversal layer to guide intra-site feature alignment, and learn site-invariant features. The three modules above are optimized collectively in an end-to-end manner, ensuring effective learning from both labeled and unlabeled data while alleviating the distribution differences of multisite data. Experiments on the ABIDE I, ABIDE II, and ADHD-200 datasets demonstrate that the CSBNC-PAL outperforms many state-of-the-art SSL methods in FBN classification. © 2013 IEEE.

关键词： Semi-supervised learning

来源：评论

学校读者我要写书评

暂无评论

An improved description method of the bumpy texture

引用

Science in China(Series F) 2009年第3期52卷 523-528页

作者： GAO RongHua KONG DeHui YIN BaoCai Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Beijing University of Technology Beijing 100124 China

Bump mapping is a texture-based rendering approach for simulating surface details to make its illumination results have three-dimensional effects. The bumpy properties of an object are determined by height maps. But in the process of generating height maps, a problem arises, i.e. to get a correct value of the pixel height, empirical data should be calculated repeatedly, which proves very complicated, and meanwhile the realistic rendering effect is reduced, because the bumpy property is exaggerated in the height map. Therefore, in this paper, we present a method for describing the details of the bumpy texture, where a new concept ＂bumpy map＂ is introduced to replace the height map. Experimental results demonstrate that the bumpy details produced by the ＂bumpy map＂ are more consistent with the original bumpy texture than by the method of height map.

关键词： bump mapping bumpy texture height map bumpy map

来源：评论

学校读者我要写书评

暂无评论

Inferring causal protein signalling networks from single-cell data based on parallel discrete artificial bee colony algorithm

引用

CAAI Transactions on Intelligence technology 2024年第6期9卷 1587-1604页

作者： Jinduo Liu Jihao Zhai Junzhong Ji Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial IntelligenceFaculty of Information TechnologyBeijing University of TechnologyBeijingChina

Inferring causal protein signalling networks from human immune system cell data is a promising approach to unravel the underlying tissue signalling biology and dysfunction in diseased cells,which has attracted considerable attention within the bioinformatics ***,Bayesian network(BN)techniques have gained significant popularity in inferring causal protein signalling networks from multiparameter single-cell ***,current BN methods may exhibit high computational complexity and ignore interactions among protein signalling molecules from different single cells.A novel BN method is presented for learning causal protein signalling networks based on parallel discrete artificial bee colony(PDABC),named ***,PDABC is a score-based BN method that utilises the parallel artificial bee colony to search for the global optimal causal protein signalling networks with the highest discrete K2 *** experimental results on several simulated datasets,as well as a previously published multi-parameter fluorescence-activated cell sorter dataset,indicate that PDABC surpasses the existing state-of-the-art methods in terms of performance and computational efficiency.

关键词： Bayesian network causal protein signaling networks parallel discrete artificial bee colony single-cell data

来源：评论

学校读者我要写书评

暂无评论

File format for storage of scalable video

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2006年第5期7卷 706-712页

作者： BAI Gang SUN Xiao-yan WU Feng YIN Bao-cai LI Shi-peng Beijing Municipal Multimedia and Intelligent Software Key Laboratory Beijing University of Technology Beijing 100022 China Microsoft Research Asia Beijing 100086 China Microsoft Research Asia Beijing 100086 China Beijing Municipal Multimedia and Intelligent Software Key Laboratory Beijing University of Technology Beijing 100022 China Microsoft Research Asia Beijing 100086 China

A file format for storage of scalable video is proposed. A generic model is presented to enable a codec independent description of scalable video stream. The relationships, especially the dependencies, among sub-streams in a scalable video stream are specified sufficiently and effectively in the proposed model. Complying with the presented scalable video stream model, the file format for scalable video is proposed based on ISO Base Media File Format, which is simple and flexible enough to address the demands of scalable video application as well as the non-scalable ones.

关键词： Codes (standards) Data structures Digital storage Internet Mathematical models multimedia systems

来源：评论

学校读者我要写书评

暂无评论

A novel hybrid apporach based on normalized color spaces and 2DPCA for color face recognition

A novel hybrid apporach based on normalized color spaces and...

引用

2010 3rd International Congress on Image and Signal Processing, CISP 2010

作者： Chen, Shangyou Sun, Yanfeng Yin, Baocai Song, Caifang Beijing Municipal Key Lab. of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing China

ISBN: (纸本)9781424465149

Recently, in a task of face recognition, some researchers proposed a novel method called color space normalization (CSN) which can enhance the discriminating power of color spaces for color face recognition. This method can significantly reduce the correlation between the three color components RGB and thus can enhance the discriminating power of the concatenated color component RGB. This offers an intrinsic (or internal) reason for why the CSN techniques can improve the face recognition performance. The three color component images of normalized color spaces are concatenated into one pattern vector, then PCA+FLD is performed on the concatenated pattern vector. But the concatenated pattern vector based on PCA destroyed the overall structure of each pixel in image. Some local structure information may be ignored. While 2DPCA preserves the overall structure information well and eliminates the small sample problem on a certain extent. Therefore, in this paper, color space normalization was combined with 2DPCA for color face recognition. This CSN based 2DPCA was performed and compared with PCA, 2DPCA for color face recognition. Numerous experiments show that the proposed approach has better recognition performance than other traditional PCA-based methods for color face recognition. ©2010 IEEE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Color face recognition based on color space normalization and quaternion matrix representation

Color face recognition based on color space normalization an...

引用

4th International Conference on Digital Home, ICDH 2012

作者： Jia, Huajie Wang, Lichun Sun, Yanfeng Hu, Yongli Beijing Municipal Key Lab. of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing China

The color face recognition method using quaternion matrix representation is based on RGB color space which is a fundamental and widely used space. However, the RGB color space is a relatively weak color space for face recognition due to the strong correlation between the three color channels. A technique named color space normalization (CSN) technique can reduce the correlation between the three channels of the RGB color space, and enhance the discriminating power of the normalized color space RGB-N. Therefore, in this paper, a method based on normalized color space RGB-N and quaternion matrix representation is firstly proposed. The proposed method not only has the advantage of quaternion matrix representation model, but also has the strong discriminating power due to CSN. The experiments in this paper are performed on the FERET color face database. Compared with the method based on RGB color space and quaternion matrix representation, the proposed approach in this paper can enhance the recognition rate. © 2012 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Cross-media Hot Topic Auto-tracking Model Based on Semantics and Temporal Context

引用

Chinese Journal of Electronics 2015年第3期24卷 529-534页

作者： LIANG Meiyu DU Junping ZHOU Yipeng Beijing Key Lab of Intelligent Telecommunication Software and Multimedia School of Computer ScienceBeijing University of Posts and Telecommunications School of Computer and Information Engineering Beijing Technology and Business University

As the Internet multimedia information grows explosively, seeking an automatic technology to realize the effective organization and management of crossmedia emergency information is significantly necessary. A novel cross-media hot topic auto-tracking model based on semantics and temporal context is proposed in this paper. According to the semantic correlations of cross-media information, we learn the image visual semantics by the text semantics based on the Latent Dirichlet Allocation probability model, and establish the unified cross-media information description on the same semantic level. Also a semantics-based two-step feature dimension-reduction scheme is proposed to establish the efficient semantic feature space. The self-adaptive learning of topic model is realized to track the dynamic changes in the topic. Experimental results demonstrate that the proposed method outperforms the existing methods, which further improves the effect of hot topic auto-tracking.

关键词： Cross-media data mining Topic autotracking Semantic model Latent dirichlet allocation(LDA) Temporal context

来源：评论

学校读者我要写书评

暂无评论

Webmath: A web-based ITS system 1

引用

1st International Conference on Web-Based Learning, ICWL 2002

作者： Liu, Chunnian Zheng, Lei Ji, Junzhong Jia, Dong Jiang, Chuan Yang, Wensheng Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology Beijing100022 China

ISBN: (纸本)3540440410

We have been developing a Web-based intelligent Tutoring System (ITS) WebMath. In this paper, after describing the conceptual model of the system and its novel features, we present its network architecture and supporting techniques, reasoning about our choices. We also give an application session of the system that shows the present status of the system. © Springer-Verlag Berlin Heidelberg 2002.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Representation of speaking mouth image for visual speech synthesis system

Representation of speaking mouth image for visual speech syn...

引用

1st International Conference on Information Science and Engineering, ICISE2009

作者： Jia, Xibin Yin, Baocai Sun, Yanfeng Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory Beijing University of Technology Beijing China

ISBN: (纸本)9780769538877

The paper proposes a kind of joint feature with the geometric parameters and the color moment to represent the speaking-mouth image frames for the image-based visual speech synthesis system. The experiment results show the proposed joint feature can effectively provide the basis for classify the speaking-mouth images to distinguish the different speaking state according to the lip shape and the tooth visibility. In order to derive the geometric feature, a kind of step-by-step point feature localization is proposed here is introduced to get the feature points. Comparing the localization results by this automatic localization algorithm with that by hand, the paper proves the localization result can meet the need of geometric feature representation. ©2009 IEEE.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：