检索结果-内蒙古大学图书馆

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Liu, Guoshan Yin, Hailong Zhu, Bin Chen, Jingjing Ngo, Chong-Wah Jiang, Yu-Gang School of Computer Science Fudan University Shanghai Key Lab of Intelligent Information Processing China Shanghai Collaborative Innovation Center on Intelligent Visual Computing China Singapore Management University Singapore

ISBN: (纸本)9798331510831

The growing interest in generating recipes from food images has drawn substantial research attention in recent years. Existing works for recipe generation primarily utilize a two-stage training method - first predicting ingredients from a food image and then generating instructions from both the image and ingredients. Large Multi-modal Models (LMMs), which have achieved notable success across a variety of vision and language tasks, shed light on generating both ingredients and instructions directly from images. Nevertheless, LMMs still face the common issue of hallu-cinations during recipe generation, leading to suboptimal performance. To tackle this issue, we propose a retrieval augmented large multimodal model for recipe generation. We first introduce Stochastic Diversified Retrieval Augmentation (SDRA) to retrieve recipes semantically related to the image from an existing datastore as a supplement, integrating them into the prompt to add diverse and rich context to the input image. Additionally, Self-Consistency Ensemble Voting mechanism is proposed to determine the most confident prediction recipes as the final output. It calculates the consistency among generated recipe candidates, which use different retrieval recipes as context for generation. Extensive experiments validate the effectiveness of our proposed method, which demonstrates state-of-the-art (SOTA) performance in recipe generation on the Recipe1M dataset. © 2025 IEEE.

关键词： Food ingredients

来源：评论

学校读者我要写书评

暂无评论

Fusion of data dimensionality reduction algorithms baced on category representation theory 4

Fusion of data dimensionality reduction algorithms baced on ...

引用

4th International Conference on Computer Vision, Application, and Algorithm, CVAA 2024

作者： Xu, Xiaoxiang Li, Fanzhang Zhang, Li School of Computer Science and Technology Joint International Research Laboratory of Machine Learning and Neuromorphic Computing Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China

ISBN: (纸本)9781510687615

For a long time, people have believed that representation problems are one of the bottlenecks in the field of machine learning. Therefore, it is a long-term and exploratory work to study machine learning representation methods. Due to this, we use category theory to study the fusion representation of data dimensionality reduction. We propose the basic concept of category representation for data dimensionality reduction and provide a data dimensionality reduction fusion representation framework. We have conducted research and analysis on algorithms such as PCA, KPCA, and LDA, identified the essential connection between PCA, KPCA, and LDA and proposed a data dimensionality reduction fusion representation algorithm based on a data dimensionality reduction fusion representation framework. Finally, we demonstrated the feasibility of the proposed method through experiments. © 2025 SPIE.

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

AMA-Net: Adaptive Masking Attention Network for Agricultural Crop Classification From UAV Images

IEEE Transactions on AgriFood Electronics

引用

IEEE Transactions on AgriFood Electronics 2025年第1期3卷 246-253页

作者： Wang, Xu Wang, Deyi He, Zhaoshui Lin, Zhijie Xie, Shengli Guangdong Mechanical and Electrical Polytechnic School of Electronics and Communication Guangzhou510550 China Guangdong University of Technology School of Automation Guangzhou510006 China Key Laboratory for IoT Intelligent Information Processing and System Integration of Ministry of Education Guangzhou510006 China Guangdong Provincial Key Laboratory of Intelligent Systems and Optimization Integration Guangzhou510006 China

Agriculture crop classification is helpful for agricultural production. However, it is challenging to classify crops from the agriculture image suffering from these problems: 1) Crops are often masked in complex backgrounds;2) There is high similarity between crop categories. To address these problems, an adaptive masking attention network (AMA-Net) is proposed for agriculture crop identification from natural images, where the adaptive masking (AM) module is developed to distinguish the crop from the complex background by selectively eliminating redundant information of feature maps, and the fair attention module is devised to identify similar crops between categories by modeling the fine-grained features. Experiments conducted on the benchmark show the effectiveness and superiority of the proposed AMA-Net, achieving the performance of 96.65%, 96.65%, 97.13%, and 96.72% on the accuracy, precision, recall, and F1-score, respectively, which is better than other state-of-the-art methods. © 2023 IEEE.

关键词： Crops Agriculture Accuracy Visualization Training Production Autonomous aerial vehicles Attention mechanisms Adaptive systems Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Fuzzy information Quantity Measurement and Feature Selection by Macrogranular Entropy

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Zhu, Zhilin Zhang, Chucai Dai, Jianhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Changsha410081 China

Feature selection is an important data preprocessing process in artificial intelligence, which aims to eliminate redundant features while retaining essential features. Measuring feature significance and relevance between features is a significant challenge. Fuzzy information entropy is an extension of Shannon entropy. It is widely used for quantifying the information of fuzzy divisions. However, it has significant limitations, notably the lack of monotonicity in fuzzy conditional entropy measure of decision uncertainty in the feature selection process. We introduce a novel measurement Macrogranular Entropy (ME) and construct some generalized forms, such as conditional macrogranular entropy, mutual macrogranular information, and joint macrogranular entropy. The conditional macrogranular entropy exhibits monotonicity when measuring decision uncertainty. Additionally, we propose two feature selection algorithms: one based on Monotonic Conditional Macrogranular Entropy (MCME), and the other based on the Degree of Symmetric Association (ADSA). The ADSA algorithm and the MCME algorithm are compared against eight other feature selection algorithms through a series of experiments. The comparison was conducted based on classification performance using SVM and NB classifiers, as well as evaluation metrics including F1-score and Recall. In terms of all four evaluation metrics, ADSA and MCME achieved the top two rankings, respectively. Specifically, on the NB and SVM classifiers, the ADSA algorithm improves the average accuracy by 12.22% and 2.88% compared to the original feature set, while MCME improves the accuracy by 10.07% and 1.01%, respectively. Experimental comparisons demonstrate that ADSA algorithm effectively removes redundant information from the dataset during feature selection. © 2025 IEEE.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

DCT-DiffPose: A Lightweight Diffusion Model with Multi-Hypothesis for 3D Human Pose Estimation

引用

IEEE Access 2025年 13卷 73319-73331页

作者： Zhong, Linzhan Chen, Fangni Zheng, Bolun Feng, Rui Zhang, Lei Wan, Jian Zhejiang University of Science and Technology The College of Information and Electronic Engineering Hangzhou310023 China The Zhejiang Key Laboratory of Biomedical Intelligent Computing Technology Hangzhou310023 China Hangzhou Dianzi University School of Automation Hangzhou310018 China

3D human pose estimation is a crucial task in computer vision with extensive applications, yet it remains challenging due to depth ambiguity and constraints on computational efficiency. In this paper, we propose DCT-DiffPose, a novel framework that integrates a diffusion model with Confidence and Consistency-based Multi-Hypothesis Aggregation (CCMA). Moreover, it incorporate the Discrete Cosine Transform (DCT) for frequency-domain feature extraction. Specifically, the diffusion model generates diverse and plausible hypotheses, and CCMA aggregates them based on confidence and consistency, effectively addressing depth ambiguity. Additionally, we incorporate DCT into the self-attention mechanism to transform input data into the frequency domain, thereby enhancing feature extraction while significantly reducing computational complexity. To validate DCT-DiffPose, we conducted extensive experiments on the Human3.6M and MPI-INF-3DHP datasets. Our method achieves a 19% lower Mean Per Joint Position Error (MPJPE) and a 55% reduction in FLOPs compared to D3DP. The results demonstrate its excellent trade-off between accuracy and complexity. © 2013 IEEE.

关键词： Discrete cosine transforms

来源：评论

学校读者我要写书评

暂无评论

Online Multi-label Streaming Feature Selection with Missing Features by Dual-Space Consistency information Measurement

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年

作者： Dai, Jianhua Wang, Jie Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Changsha410081 China

Multi-label feature selection is critical to address the challenges of high dimensionality and computational complexity in multi-label learning. However, in some practical applications, a more complex challenge is the dynamic generation of features, known as streaming features. Although some scholars have studied multi-label streaming feature selection methods, the problem of missing features during dynamic feature generation in multi-label data is rarely considered. Hence, we propose an online multi-label streaming feature selection method for multilabel data containing missing features by dual-space consistency information measurement. Firstly, we construct the dual-space consistency information measurement, which can effectively capture the relationships between features and labels. Specifically, we consider it from the perspective of instance correlation, and propose a fuzzy α-tolerance relation in the feature space to directly deal with missing features, and introduce an improved neighbour similarity relation in the label space to capture the instance similarity between the label combinations. Secondly, based on the dual-space consistency information, we further introduce the consistency gain index to help identify those features with important information during the streaming feature selection process. Thirdly, by combining online significance analysis, online relevance analysis, and online redundancy analysis, a new streaming feature selection framework is constructed, which can comprehensively evaluate the newly arrived features in terms of strong consistency, weak consistency and irrelevance, so as to identify the most representative features in the continuously arriving feature streams. Finally, a series of comparative experiments on multiple benchmark datasets demonstrate the effectiveness and superiority of our proposed method. © 2025 IEEE.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

Security-Enhanced Data Sharing Via Efficient Sanitization for VANETs

引用

IEEE Transactions on Mobile computing 2025年第6期24卷 4925-4938页

作者： Zhong, Hong Zhou, Dan Cui, Jie Wang, Li Zhang, Jing Bolodurina, Irina He, Debiao Anhui University Key Laboratory of Intelligent Computing and Signal Processing Ministry of Education School of Computer Science and Technology Hefei230039 China Anhui University Anhui Engineering Laboratory of IoT Security Technologies Hefei230039 China Orenburg State University Faculty of Mathematics and Information Technologies Orenburg460018 Russia Wuhan University School of Cyber Science and Engineering Wuhan430072 China MatrixElements Technologies Shanghai Key Laboratory of Privacy Preserving Computation Shanghai201204 China

With the widespread deployment of vehicular ad-hoc networks (VANETs), data sharing has garnered considerable attention as a core feature of VANETs. Attribute-based proxy re-encryption (ABPRE) enables fine-grained access control and provides flexible ciphertext updates. The initially authorized vehicle generates the re-encryption key to enable ciphertext-to-ciphertext conversion in the cloud, allowing ciphertext to be shared with new recipients. However, initially authorized vehicles may not always be trustworthy and could share data with malicious receivers. In addition, the computation and communication overhead of ABPRE hinders its widespread application in VANETs. To address these issues, we propose a lightweight sanitizable scheme for edge-assisted VANETs based on ABPRE. In this scheme, the re-encryption key is verified by a sanitizer, to prevent the data from being shared with malicious data receivers. In addition, key-splitting techniques and edge computing are employed to reduce the communication and computation overhead of re-encryption. A comprehensive security analysis and performance evaluation demonstrate that the proposed scheme is efficient and practical. © 2002-2012 IEEE.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Online Multi-Label Streaming Feature Selection by Label Enhancement and Fuzzy Synergistic Discrimination information

引用

IEEE Transactions on Fuzzy Systems 2025年

作者： Zou, Ligeng Zhou, Tong Dai, Jianhua Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Changsha410081 China

Online streaming feature selection is an effective approach for handling large-scale streaming data in real-world applications. However, many existing online streaming feature selection studies do not effectively leverage the correlation and hidden information in the label space. The measures used in streaming feature selection often face challenges such as computational complexity and insufficient information exploitation. To address these issues, we propose an online streaming feature selection method based on label enhancement and fuzzy synergistic discrimination information. Firstly, we define a novel label enhancement method based on label correlation, which does not require any prior knowledge of feature space. Secondly, we propose a new measure to evaluate the discriminative ability of multiple feature subsets for labels in fuzzy environment, called fuzzy synergistic discrimination information. It is bounded and has many interesting properties. The fuzzy synergistic discrimination information is computed directly based on fuzzy similarity relations, so the calculation is relatively simple. Thirdly, based on label enhancement and proposed fuzzy synergistic discrimination information, we construct a three-stage online multi-label streaming feature selection method, including online significance analysis, online relevance analysis and online redundancy analysis. Finally, comparative experiments on 12 datasets demonstrate the effectiveness and superiority of the proposed method. The influences of different feature sequences and these components on the algorithm's performance are further analyzed. © 1993-2012 IEEE.

关键词： information hiding

来源：评论

学校读者我要写书评

暂无评论

Deep Learning and Projection Neural Network With Finite-Time Convergence for Energy Management of Multi-Energy System

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2156-2168页

作者： Liu, Xueying He, Xing Li, Chaojie Huang, Tingwen Southwest University Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Chongqing400715 China North China Electric Power University State Key Laboratory of Alternate Electrical Power System With Renewable Energy Sources Beijing102206 China Shenzhen University of Advanced Technology Faculty of Computer Science and Control Engineering Shenzhen518055 China

In this paper, an approach based on projection neural network (PNN), sliding mode control technique, and deep learning is proposed to solve the energy management problem of multi-energy systems (MES) containing dynamic parameters. First, the sliding mode technique is introduced in the PNN to design a finite-time PNN (FTPNN). The stability and finite-time convergence of the proposed FTPNN are proved by the Lyapunov method and the setting time bound is given. Then, the deep FTPNN (DFTPNN) is designed by combining deep learning with the proposed FTPNN. The dynamic parameters in the MES that change over time are used as input variables for the DFTPNN, allowing the trained DFTPNN to respond immediately to changes in the dynamic parameters and to predict the solutions of the FTPNN with different parameters directly. Simulation experiments show that FTPNN has faster convergence compared to PNN. DFTPNN significantly reduces the computation time compared to FTPNN. DFTPNN provides predicted solutions to FTPNN. Since DFTPNN can respond immediately to changes in dynamic parameters and directly provide energy management strategies under different parameters, it can adapt to changing environments and promote the economic and stable operation of MES. © 2010-2012 IEEE.

关键词： Cogeneration Heuristic algorithms Convergence Deep learning Prediction algorithms Optimization Heating systems Energy management Approximation algorithms Power system stability

来源：评论

学校读者我要写书评

暂无评论

A data representation method using distance correlation

引用

Frontiers of Computer Science 2025年第1期19卷 1-14页

作者： Xinyan LIANG Yuhua QIAN Qian GUO keyin ZHENG Institute of Big Data Science and Industry Shanxi UniversityTaiyuan 030006China Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education Shanxi UniversityTaiyuan 030006China School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 030024China Shanxi Key Laboratory of Big Data Analysis and Parallel Computing Taiyuan University of Science and TechnologyTaiyuan 030024China

Association in-between features has been demonstrated to improve the representation ability of data. However, the original association data reconstruction method may face two issues: the dimension of reconstructed data is undoubtedly higher than that of original data, and adopted association measure method does not well balance effectiveness and efficiency. To address above two issues, this paper proposes a novel association-based representation improvement method, named as AssoRep. AssoRep first obtains the association between features via distance correlation method that has some advantages than Pearson’s correlation coefficient. Then an improved matrix is formed via stacking the association value of any two features. Next, an improved feature representation is obtained by aggregating the original feature with the enhancement matrix. Finally, the improved feature representation is mapped to a low-dimensional space via principal component analysis. The effectiveness of AssoRep is validated on 120 datasets and the fruits further prefect our previous work on the association data reconstruction.

关键词： association representation distance correlation classification

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：