检索结果-内蒙古大学图书馆

A difference vector angle dominance relation for expensive multi-objective optimization

Swarm and Evolutionary Computation 2025年 95卷

作者： Yang, Cuicui Chen, Jing Ji, Junzhong Zhang, Xiaoyu Hao, Kangning Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science Beijing University of Technology Beijing China

For the latest two years, relation classification-based surrogate assisted evolutionary algorithms show good potential for solving expensive multi-objective optimization problems (EMOPs). However, the existing studies are still at the initial stage and lack specific research on the dominance relation. This paper proposes a difference vector angle dominance relation for EMOPs, which uses an angle threshold φ to control the selection pressure and is called DVAD-φ. The proposed DVAD-φ has adaptive selection pressure and considers the convergence and diversity of solutions when picking out superior solutions, which makes it beneficial to pick out promising solutions for expensive real FEs and reduce expensive real FEs. To be specific, we firstly give the definition of DVAD-φ that measures the superiority from one solution to another solution according to the angle threshold φ. Then, we deduce that there is monotonicity between the angle threshold φ and the number of non-dominated solutions in the sense of DVAD-φ. At last, we propose an adaptive determination strategy of angle threshold based on bisection to set proper pressure for picking out promising solutions for expensive real FEs. Experiments have been conducted on 23 test functions from two benchmark sets and one real-world problem. The experimental results have verified the effectiveness of DVAD-φ. © 2025

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

GCLNet: Generalized Contrastive Learning for Weakly Supervised Temporal Action Localization

引用

IEEE Transactions on Big Data 2025年

作者： Wang, Jing Kong, Dehui Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Faculty of Information Technology Beijing100124 China

Weakly supervised temporal action localization (WTAL) aims to precisely locate action instances in given videos by video-level classification supervision, which is partly related to action classification. Most existing localization works directly utilize feature encoders pre-trained for video classification tasks to extract video features, resulting in nontargeted features that lead to incomplete or overcomplete action localization. Therefore, we propose Generalized Contrast Learning Network (GCLNet), in which two novel strategies are proposed to improve the pre-trained features. First, to address the issue of over-completeness, GCLNet introduces text information with good context independence and category separability to enrich the expression of video features, as well as proposes a novel generalized contrastive learning approach for similarity metrics, which facilitates pulling closer the features belonging to the same category while pushing farther apart those from different categories. Consequently, it enables more compact intra-class feature learning and ensures accurate action localization. Secondly, to tackle the problem of incomplete, we exploit the respective advantages of RGB and Flow features in scene appearance and temporal motion expression, designing a hybrid attention strategy in GCLNet to enhance each channel features mutually. This process greatly improves the features through establishing cross-channel consensus. Finally, we conduct extensive experiments on THUMOS14 and ActivityNet1.2, respectively, and the results show that our proposed GCLNet can produce more representative action localization features. © 2015 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Student academic performance prediction via hypergraph and TabNet

引用

Journal of Big Data 2025年第1期12卷 1-24页

作者： Yang, Yisheng Zhao, Shiyu An, Sufang Li, Xiaoyong Zhang, Yong Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing China Academic Affairs Office Beijing Open University Beijing China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences Beijing China

Student academic performance prediction plays a very important role in student management. With the development of deep learning, there has been some related research work on predicting student academic performance. Although many factors influence students’ academic performance, students at the same university tend to have similar intellectual levels and learning environments. Therefore, learning behaviors can significantly impact their academic performance. Thus, modeling students’ behavior can enable the prediction of their academic performance. However, existing methods mostly focus on modeling individual student behaviors, neglecting the complex associations among students hidden within campus behavioral data. In reality, the associations between students often involve higher-order, multi-to-multi relationships, rather than simple, pairwise connections. At the same time, most data-driven deep learning models are not interpretable. But in fact, the analysis of behaviors that affect student academic performance is more useful in many cases. To address these issues, this paper proposes a student academic performance prediction model that combines hypergraphs and TabNet. This method first processes and extracts usable behavior features from collected multi-source campus behavior data; secondly, it utilizes K-Nearest Neighbors (KNN) to construct a hypergraph to describe the higher-order associations among students; then, it uses hypergraph convolution to aggregate neighborhood features to learn sample embedding representations; finally, the academic performance of students are predicted by the TabNet model. Experimental results on real student behavior datasets indicate that the precision, recall, and F1 score of the method proposed in this paper are improved compared to baseline methods. Additionally, using hypergraphs and TabNet can help to explain the relationship between student behavior and performance at the feature level.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Particle swarm optimization algorithm based 3D face reconstruction

引用

Journal of Information and Computational Science 2009年第6期6卷 2215-2222页

作者： Ge, Yun Yin, Baocai Sun, Yanfeng Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing 100000 China

This paper presents a novel matching method based on particle swarm optimization (PSO) algorithm for 3D face reconstruction. The new model-matching algorithm can make the reconstruction has faster convergent speed and better result than before. Having constructed the morphable model, PSO algorithm is proposed to tackle model matching problem. PSO algorithm is a swarm intelligence-based optimization algorithm which is independent of initial values and the gradient information of object function. In the course of optimization each individual has their own memory about the optimal position they have arrived and the information among individuals can be exchange with each other. This will be great helpful to improve precision and convergence speed of the algorithm. The Experimental results show that the proposed matching method has good performance on 3D face reconstruction. © 2009 Binary Information Press.

关键词： Particle swarm optimization (PSO)

来源：评论

学校读者我要写书评

暂无评论

3D face correspondence based on uniform mesh re-sampling combined with mesh simplification

引用

Journal of Computational Information Systems 2005年第2期1卷 343-350页

作者： Wang, Chengzhang Yin, Baocai Shi, Qin Sun, Yanfeng Multimedia and Intelligent Software Technology Beijing Municipal Key Laboratory Beijing University of Technology Beijing 100022 China

This present study, proposes a new 3D face correspondence method. A uniform mesh re-sampling algorithm is combined with mesh simplification algorithm to make correspondence between vertices of prototypical 3D faces. Uniform mesh re-sampling algorithm is developed to obtain the same topology between 3D faces with different structures. A global error metrics is proposed and mesh simplification is implemented on 3D faces with same topologies simultaneously. The new method overcomes the limitation of conventional uniform mesh re-sampling and optical flow algorithm, decreases the vertices, and triangles that need to represent 3D face while preserving correspondence between vertices of the prototypes. The experimental results show the new method gives good performance on computing 3D face correspondence.

关键词： Face recognition

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

A semantic matching algorithm of web services based on Google distance

引用

Journal of Computational Information Systems 2011年第8期7卷 2624-2633页

作者： Yang, Huirong Yin, Baocai Fu, Pengbin Sun, Yanfeng Qu, Liang Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing 100124 China

In order to get a better semantic matching degree for web services, in this paper, we try to deal with the problems of semantic web services matching through calculating the Normalized Google Distance (NGD) between concepts, based on the semantic description of web service's input and output. This technique takes advantage of the Google massive terms and open Google search engine to compute the NGD, and calculates the similarity between concepts. Compared with the existing algorithm, we adopt Google terms which present merits of more abundance and updating in a relatively faster speed. This method is simpler and greatly decreases the complexity of calculation because there is no ontology and taxonomy tree, no need to judge the foliatory order, path length, depth and local density. The preliminary results have shown that our algorithm can highly improve the recall and precision of the web services. © 2005 by Binary Information Press.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Tackling Real-world Complexity: Hierarchical Modeling and Dynamic Prompting for Multimodal Long Document Classification

引用

IEEE Transactions on Circuits and Systems for Video technology 2025年

作者： Liu, Tengfei Hu, Yongli Li, Mingjie Yi, Junfei Chang, Xiaojun Gao, Junbin Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing100124 China Stanford University Department of Radiation Oncology StanfordCA94305 United States Hunan University National Engineering Laboratory of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha410082 China University of Technology Sydney ReLER Laboratory Australian Artificial Intelligence Institute Faculty of Engineering and Information Technology UltimoNSW2007 Australia The University of Sydney Business School The University of Sydney Discipline of Business Analytics CamperdownNSW2006 Australia

With the rapid growth of internet content, multimodal long document data has become increasingly prominent, drawing significant attention from researchers. However, most existing methods primarily focus on scenarios where all modalities are present, often overlooking more challenging and realistic cases involving missing image modality. To address this limitation, we propose a robust multimodal long document classification (MLDC) framework that integrates hierarchical modeling and dynamic prompting to handle complex multimodal long document data. Our approach begins by leveraging hierarchical modeling combined with an Adaptive Correlation Multimodal Transformer (ACMT) to effectively capture relationships between text and images at both section and sentence levels. We also introduce a Dynamic Prompt Generation (DPG) module at both levels to enhance the model's robustness in handling missing image data. By evaluating sample uncertainty, the DPG module dynamically adjusts both the number of prompts and the prompts themselves, allowing the model to better adapt to the varying needs of different samples. Finally, a Hierarchical Heterogeneous Graph (HHG) is introduced to enhance feature interactions across levels, further improving the coherence and accuracy of the model. Extensive experiments on four multi-modal long document datasets demonstrate that our model shows superior performance compared to existing state-of-the-art MLDC classification methods in various conditions. © 1991-2012 IEEE.

关键词： dynamic prompt generation hierarchical heterogeneous graph Multimodal long document classification

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

Interpolating subdivision surface based on radial basis function

引用

Journal of Information and Computational Science 2009年第5期6卷 2105-2112页

作者： Zhang, Yong Yin, Baocai Kong, Dehui Wen, Wen Beijing Municipal Key Laboratory of Multimedia and Intelligent Software Technology College of Computer Science Beijing University of Technology Beijing 100124 China

Subdivision scheme is a powerful method for the definition of sub-surface smooth, continuous, seamless surface. This paper presents a new method to obtain interpolating subdivision limit surfaces from approximating subdivision, based on local RBF (radial basis function). The method is composed of two steps. First, the control mesh will be refined by a specified approximating subdivision scheme. Then, all the vertices of the refined mesh will be displaced to interpolate the original mesh. The displacements of the new edge vertices are computed by RBF defined locally. The results show that the proposed method integrates the features of both approximation subdivision and interpolation subdivision. © 2009 Binary Information Press.

关键词： Interpolation

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：