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

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

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

引用

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

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

Anomize: Better Open Vocabulary Video Anomaly Detection

arXiv

引用

arXiv 2025年

作者： Li, Fei Liu, Wenxuan Chen, Jingjing Zhang, Ruixu Wang, Yuran Zhong, Xian Wang, Zheng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China State Key Laboratory for Multimedia Information Processing School of Computer Science Peking University China Hubei Key Laboratory of Transportation Internet of Things Wuhan University of Technology China

Open Vocabulary Video Anomaly Detection (OVVAD) seeks to detect and classify both base and novel anomalies. However, existing methods face two specific challenges related to novel anomalies. The first challenge is detection ambiguity, where the model struggles to assign accurate anomaly scores to unfamiliar anomalies. The second challenge is categorization confusion, where novel anomalies are often misclassified as visually similar base instances. To address these challenges, we explore supplementary information from multiple sources to mitigate detection ambiguity by leveraging multiple levels of visual data alongside matching textual information. Furthermore, we propose incorporating label relations to guide the encoding of new labels, thereby improving alignment between novel videos and their corresponding labels, which helps reduce categorization confusion. The resulting Anomize framework effectively tackles these issues, achieving superior performance on UCF-CRIME and XD-VIOLENCE datasets, demonstrating its effectiveness in OVVAD. Copyright © 2025, The Authors. All rights reserved.

关键词：

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

EnergyGPT: Fine-tuning large language model for multi-energy load forecasting

引用

Renewable Energy 2025年 251卷

作者： Min Liang Yongli Hu Haoen Weng Jiayang Xi Baocai Yin Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence School of Information Science and Technology Beijing University of Technology Beijing 100124 China

Multi-energy load forecasting plays a pivotal role in strategy management and operational planning in integrated energy systems (IESs). However, the inherent complexity and high dynamicity of IESs bring significant challenges, including modeling the coupling relationships between relevant features and designing effective forecasting models. The traditional statistical methods for feature correlation analysis struggle to reveal the dynamic correlation of feature sequences, and the classic data-driven machine learning methods for multi-energy load forecasting suffer from a lack of generalization. To address these issues, inspired by the successful applications of pre-trained large models in specific tasks, this paper introduces a large language model (LLM) into the energy field and proposes a novel multi-energy load forecasting model based on GPT2, called EnergyGPT, which utilizes the knowledge and capabilities of LLMs trained on a massive text stream corpus to enhance generalization and performance in multi-energy load forecasting. Additionally, EnergyGPT adopts a dynamic self-attention module to adjust the importance of sequential features. The proposed EnergyGPT is evaluated on the real load data from the Tempe campus provided by Arizona State University’s online platform, compared with a set of the latest load forecasting methods. The experimental results show that EnergyGPT outperforms all the comparisons with the best performance in four seasons, which validates the effectiveness of EnergyGPT and shows the potential of large models for cross-domain applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Range imaging using marked structured lights

引用

Journal of Information and Computational Science 2014年第9期11卷 2993-3002页

作者： Wu, Qianjun Wang, Shaofan Kong, Dehui Yin, Baocai Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing University of Technology Beijing 100124 China

This paper proposes a range imaging method which encodes a projective image with marked structured lights and decodes a depth image with the geometry of the black-and-white stripes. We determine the incident angle of each stripe over the pattern by using a marked line of the multi-line structured light pattern, and compute the depth data of each point by using the triangulation principle. We compare our method with a color-structured-light based method and a stereo-vision based method using static models, and experimental results show that our method acquires depth data with a single-shot pattern efficiently and accurately. Copyright © 2014 Binary Information Press.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Memory Transmission Based Referring Video Object Segmentation

引用

Neural Networks 2025年 189卷 107548页

作者： Zijin Liu Lichun Wang Yongli Hu Baocai Yin Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence China School of Information Science and Technology Beijing University of Technology Beijing 100124 China

Referring Video Object Segmentation (RVOS) addresses the task of segmenting target objects described by textual descriptions from videos. In order to ensure the consistency of objects segmented from video frames, inter-frame modeling is adopted to capture the motion information of objects, which usually divides the video into several clips, and considers the association of video frames within each clip. However, the clip-level modeling cannot establish continuous motion changes of the object across the video. To address this issue, we suggest memory transmission based continuous inter-frame modeling, which uses the segmentation result of the previous frame to calculate a pseudo mask for the current frame. Based on the proposed continuous inter-frame modeling method, we propose Memory Transmission Based Referring Video Object Segmentation (MT-RVOS), which uses the transmitted pseudo mask to guide the segmentation mask inference for the current frame. Extensive experiments conducted on four referring video object segmentation benchmarks demonstrate that MT-RVOS achieves competitive performance.

关键词： Inter-frame modeling Memory transmission Referring Video Object Segmentation Text-Vision Interaction

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

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：