检索结果-内蒙古大学图书馆

Modality Unified Attack for Omni-Modality Person Re-Identification

IEEE Transactions on Information Forensics and Security 2025年 20卷 5577-5587页

作者： Bian, Yuan Liu, Min Yi, Yunqi Wang, Xueping Ma, Yunfeng Wang, Yaonan Hunan University National Engineering Research Center of Robot Visual Perception and Control Technology College of Electrical and Information Engineering Hunan Changsha China Hunan Normal University Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing College of Information Science and Engineering Hunan Changsha China

Deep learning based person re-identification (re-id) models have been widely employed in surveillance systems. Recent studies have demonstrated that black-box single-modality and cross-modality re-id models are vulnerable to adversarial examples (AEs), leaving the robustness of multi-modality re-id models unexplored. Due to the lack of knowledge about the specific type of model deployed in the target black-box surveillance system, we aim to generate modality unified AEs for omni-modality (single-, cross- and multi-modality) re-id models. Specifically, we propose a novel Modality Unified Attack method to train modality-specific adversarial generators to generate AEs that effectively attack different omni-modality models. A multi-modality model is adopted as the surrogate model, wherein the features of each modality are perturbed by metric disruption loss before fusion. To collapse the common features of omnimodality models, Cross Modality Simulated Disruption approach is introduced to mimic the cross-modality feature embeddings by intentionally feeding images to non-corresponding modality-specific subnetworks of the surrogate model. Moreover, Multi Modality Collaborative Disruption strategy is devised to facilitate the attacker to comprehensively corrupt the informative content of person images by leveraging a multi modality feature collaborative metric disruption loss. Extensive experiments show that our MUA method can effectively attack the omni-modality re-id models, achieving 55.9%, 24.4%, 49.0% and 62.7% mean mAP Drop Rate, respectively. © 2005-2012 IEEE.

关键词： Feature extraction Perturbation methods Measurement Generators Collaboration Robustness Identification of persons Data mining Closed box Training

来源：评论

学校读者我要写书评

暂无评论

Deep Broad Learning for Emotion Classification in Textual Conversations

引用

Tsinghua Science and Technology 2024年第2期29卷 481-491页

作者： Sancheng Peng Rong Zeng Hongzhan Liu Lihong Cao Guojun Wang Jianguo Xie Center for Linguistics and Applied Linguistics and Laboratory of Language Engineering and ComputingGuangdong University of Foreign StudiesGuangzhou 510006China Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices South China Normal UniversityGuangzhou 510006China School of Computer Science and Cyber Engineering Guangzhou UniversityGuangzhou 510006China Modern Education Technology Center Guangdong University of Foreign StudiesGuangzhou 510006China

Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual *** is becoming one of the most important tasks for natural language processing in recent ***,it is a challenging task for machines to conduct emotion classification in textual conversations because emotions rely heavily on textual *** address the challenge,we propose a method to classify emotion in textual conversations,by integrating the advantages of deep learning and broad learning,namely *** aims to provide a more effective solution to capture local contextual information(i.e.,utterance-level)in an utterance,as well as global contextual information(i.e.,speaker-level)in a conversation,based on Convolutional Neural Network(CNN),Bidirectional Long Short-Term Memory(Bi-LSTM),and broad *** experiments have been conducted on three public textual conversation datasets,which show that the context in both utterance-level and speaker-level is consistently beneficial to the performance of emotion *** addition,the results show that our proposed method outperforms the baseline methods on most of the testing datasets in weighted-average F1.

关键词： emotion classification textual conversation Convolutional Neural Network(CNN) Bidirectional Long Short-Term Memory(Bi-LSTM) broad learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal language Data and Platform Construction for LCTLs Teaching 23

Multimodal Language Data and Platform Construction for LCTLs...

引用

15th International Conference on Machine Learning and computing, ICMLC 2023

作者： Wang, Yuan Jin, Kai Liu, Wuying Shandong Key Laboratory of Language Resources Development and Application Ludong University China School of Foreign Languages Qilu University of Technology China Laboratory of Language Engineering and Computing Guangdong University of Foreign Studies China

ISBN: (纸本)9781450398411

The progress of artificial intelligence technology has brought great opportunities for the development of Less Commonly Taught languages (LCTLs) teaching. However, the scarcity of LCTLs resources still plagues the current teaching platform. This paper is committed to building multimodal language data including foreign language vocabulary and translation, bilingual example sentences, phonetic symbols and audio, morphological similarity recommendation, semantic similarity recommendation, etc., and using full-text index and Web Service technology to build a new LCTLs teaching platform. The detailed steps are: (1) acquiring and processing multimodal language data through web pages such as TED and Opensubtitles;(2) constructing the inverted indexes used the HashMap and storing the index files in the cache of the platform, which avoids the heavy database intervention;(3) using the classical Levenshtein distance in the morphological similar words and semantic similar words recommendation algorithm. The platform implemented based on the above data and technology finally supports Japanese, Italian, Indonesian, Malaysian, Vietnamese, Filipino, and Myanmar seven languages. © 2023 ACM.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Scheduling optimization for upstream dataflows in edge computing

引用

Digital Communications and Networks 2023年第6期9卷 1448-1457页

作者： Haohao Wang Mengmeng Sun Lianming Zhang Pingping Dong Yehua Wei Jing Mei College of Information Science and Engineering Hunan Normal UniversityChangsha410081China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal UniversityChangsha410081China Hunan Xiangjiang Artificial Intelligence Academy Hunan Normal UniversityChangsha410081China

Edge computing can alleviate the problem of insufficient computational resources for the user equipment,improve the network processing environment,and promote the user *** computing is well known as a prospective method for the development of the Internet of Things(IoT).However,with the development of smart terminals,much more time is required for scheduling the terminal high-intensity upstream dataflow in the edge server than for scheduling that in the downstream *** this paper,we study the scheduling strategy for upstream dataflows in edge computing networks and introduce a three-tier edge computing network *** propose a Time-Slicing Self-Adaptive Scheduling(TSAS)algorithm based on the hierarchical queue,which can reduce the queuing delay of the dataflow,improve the timeliness of dataflow processing and achieve an efficient and reasonable performance of dataflow *** experimental results show that the TSAS algorithm can reduce latency,minimize energy consumption,and increase system throughput.

关键词： Edge computing Time-slicing Dataflow scheduling Dynamic analysis

来源：评论

学校读者我要写书评

暂无评论

Byzantine-Robust Federated Learning on Non-IID Data via Inversing Artificial Gradients

Byzantine-Robust Federated Learning on Non-IID Data via Inve...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Li, Minyang Tang, Xiangyun Zhang, Tao Liu, Guangyuan Weng, Yu Minzu University of China Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance China Beijing Jiaotong University School of Software Engineering China Nanyang Technological University College of Computing and Data Science Singapore

ISBN: (纸本)9798350351255

Federated Learning (FL) is a distributed machine learning framework that enhances privacy by enabling multiple participants to train a global model without sharing their raw data. However, FL still faces the threat posed by data and Byzantine attacks (e.g., data poisoning and model poisoning attacks) from malicious clients aimed to decrease the FL global training accuracy. Previous studies have proposed solutions to improve the robustness of FL systems. However, these robust approaches have not effectively defended against Byzantine attacks from malicious clients in non-Independent and Identically Distributed (non-IID) environments, decreasing overall training accuracy. In this work to address this issues, we propose a new defence framework that aims to enhance model accuracy against Byzantine attacks from malicious clients in non-IID environments. In our approach, the central server performs the Inverse Deep Learning Gradient attack using the gradient data submitted by users in each round, obtaining an inversed artificial gradient. We then assess the squared L2 norm difference between this inversed gradient and the actual gradients to detect malicious clients. Simultaneously, we assign weights to each client involved in the aggregation based on differences in the squared L2 norm, aiming to minimize the impact of malicious actors on the overall model. We have experimentally evaluated our method and demonstrated its ability to maintain training accuracy under attack in non-IID environments using standard datasets. © 2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Para-social Interaction among Multiple Luxury Brands 4

Comparative Analysis of Para-social Interaction among Multip...

引用

4th International Conference on Natural language Processing, ICNLP 2022

作者： Yu, Dandan Liu, Wuying Ludong University Shandong Key Laboratory of Language Resources Development and Application Yantai264025 China Guangdong University of Foreign Studies Laboratory of Language Engineering and Computing Guangzhou510420 China

ISBN: (数字)9781665495448

ISBN: (纸本)9781665495448

The luxury industry is good at using the most advanced science and technology to promote product sales. With the recent rise of virtual spokespersons, more and more virtual spokespersons are widely used in luxury marketing. We studied the new advertising mode based on virtual spokespersons, and analyzed how luxury brands use virtual spokespersons to establish para-social interactions with their audiences. We also analyzed the data of likes, reposts and comments on the official Weibo of luxury brands such as Valentino, Dior, Ferragamo, Louis Vuitton, and March Jacobs that have published advertising Weibos which contain virtual spokespersons and do not include celebrity spokespersons and various marketing campaign. Finally, according to the conclusion of our analysis, we propose development suggestions for the promotion strategy of luxury brands' virtual spokespersons in Weibo or other media, and the way to establish para-social interaction between luxury brands and their audiences. © 2022 IEEE.

关键词： Marketing

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Broad Learning for Cross-Domain Emotion Classification

引用

Tsinghua Science and Technology 2023年第2期28卷 360-369页

作者： Rong Zeng Hongzhan Liu Sancheng Peng Lihong Cao Aimin Yang Chengqing Zong Guodong Zhou Guangdong Provincial Key Laboratory of Nanophotonic Functional Materials and Devices South China Normal UniversityGuangzhou 511400China Laboratory of Language Engineering and Computing Guangdong University of Foreign StudiesGuangzhou 510006China School of Computer Science and Intelligence Education Lingnan Normal UniversityGuangzhou 510006China National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology Soochow UniversitySuzhou 215031China

Cross-domain emotion classification aims to leverage useful information in a source domain to help predict emotion polarity in a target domain in a unsupervised or semi-supervised *** to the domain discrepancy,an emotion classifier trained on source domain may not work well on target *** researchers have focused on traditional cross-domain sentiment classification,which is coarse-grained emotion ***,the problem of emotion classification for cross-domain is rarely *** this paper,we propose a method,called convolutional neural network(CNN)based broad learning,for cross-domain emotion classification by combining the strength of CNN and broad *** first utilized CNN to extract domain-invariant and domain-specific features simultaneously,so as to train two more efficient classifiers by employing broad ***,to take advantage of these two classifiers,we designed a co-training model to boost together for ***,we conducted comparative experiments on four datasets for verifying the effectiveness of our proposed *** experimental results show that the proposed method can improve the performance of emotion classification more effectively than those baseline methods.

关键词： cross-domain emotion classification CNN broad learning classifier co-training

来源：评论

学校读者我要写书评

暂无评论

A Faster Parameterized Algorithm for Bipartite 1-Sided Vertex Explosion 16th

A Faster Parameterized Algorithm for Bipartite 1-Sided Vert...

引用

16th Annual International Conference on Combinatorial Optimization and Applications, COCOA 2023

作者： Liu, Yunlong Xiao, Guang Liu, Ao Wu, Di Huang, Jingui College of Information Science and Engineering Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410081 China Xiangtan University Xiangtan411101 China School of Computer Science and Engineering Central South University Changsha410083 China

ISBN: (纸本)9783031496134

Given a bipartite graph G = (T∪ B, E), the problem bipartite 1-sided vertex explosion is to decide whether there exists a planar 2-layer embedding of G after exploding at most k vertices of B. For this problem, which is known to be NP-complete, parameterized algorithms have received increasing attention more recently. In this paper, we focus on the problem parameterized by the number k of allowed exploded vertices of B and develop a faster algorithm for it. More specifically, we show that this parameterized problem admits a kernel of at most 10.5k vertices, and present a fixed-parameter tractable algorithm running in time O(2. 31 k· m), where m is the number of edges of G. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Embeddings

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

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

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

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

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：