检索结果-内蒙古大学图书馆

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

Collaborative Teams Recruitment Based on Dual Constraints of Willingness and Trust for Crowd Sensing 25

Collaborative Teams Recruitment Based on Dual Constraints of...

引用

25th IEEE International Conference on computer Supported Cooperative Work in Design, CSCWD 2022

作者： Song, Nianyun Lu, Dianjie Shi, Yepeng Zhang, Guijuan Liu, Hong School of Information Science and Engineering Shandong Normal University Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology State Key Laboratory of High-end Server and Storage Technology Shandong Jinan China

ISBN: (纸本)9781665405270

As crowd sensing tasks become more complex, it is increasingly needed for participants to form teams to collaborate interactively in order to complete tasks more efficiently. It is valuable to fully understand user behavior, the organizational principles of crowd collaboration teams and incorporate them into the user recruitment process. In fact, there is a two-way process of subjective and objective selection for building a team in crowd sensing. From the participant's perspective, the willingness of users to participate in the task is a subjective factor;from the platform's perspective, the trust relationship between users is an objective factor. However, existing work has not well recognized the value of including collaborative teams in the crowd sensing recruitment process and has not considered the willingness and trust relationships between participants simultaneously, which results in poor quality of service (QoS) among recruited users. To address this problem, we propose a willingness and trust-based collaborative team recruitment method (WT-CTRM). First, we construct a willingness network (WN) and a trust network (TN) to describe the interaction of willingness and trust among the collaborated users respectively. Based on these networks, we then predict the unknown willingness and trust relationships between users for collaboration by using graph convolutional networks (GCNs). Finally, we build collaborative teams for the user recruitment process of crowd sensing based on the consensus constraints of the predicted willingness network and trust network. Simulation results show that the recruitment scheme significantly improves the QoS in task scenarios with collaborative requirements. © 2022 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Delving into the reversal curse: how far can large language models generalize? 24

Delving into the reversal curse: how far can large language ...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhengkai Lin Zhihang Fu Kai Liu Liang Xie Binbin Lin Wenxiao Wang Deng Cai Yue Wu Jieping Ye State Key Lab of CAD & CG Zhejiang University and Alibaba Cloud Alibaba Cloud Alibaba Cloud and College of Biomedical Engineering & Instrument Science Zhejiang University College of Computer Science and Technology Zhejiang University of Technology School of Software Technology Zhejiang University and Fullong Inc. School of Software Technology Zhejiang University State Key Lab of CAD & CG Zhejiang University

ISBN: (纸本)9798331314385

While large language models (LLMs) showcase unprecedented capabilities, they also exhibit certain inherent limitations when facing seemingly trivial tasks. A prime example is the recently debated "reversal curse", which surfaces when models, having been trained on the fact "A is B", struggle to generalize this knowledge to infer that "B is A". In this paper, we examine the manifestation of the reversal curse across various tasks and delve into both the generalization abilities and the problem-solving mechanisms of LLMs. This investigation leads to a series of significant insights: (1) LLMs are able to generalize to "B is A" when both A and B are presented in the context as in the case of a multiple-choice question. (2) This generalization ability is highly correlated to the structure of the fact "A is B" in the training documents. For example, this generalization only applies to biographies structured in "[Name] is [Description]" but not to "[Description] is [Name]". (3) We propose and verify the hypothesis that LLMs possess an inherent bias in fact recalling during knowledge application, which explains and underscores the importance of the document structure to successful learning. (4) The negative impact of this bias on the downstream performance of LLMs can hardly be mitigated through training alone. These findings offer a novel perspective on interpreting LLMs' generalization through their intrinsic mechanisms and provide insights for developing more effective learning methods. https://***/alibaba/thinking_***

关键词：

来源：评论

学校读者我要写书评

暂无评论

Identification of Microservices through Processed Dynamic Traces and Static Calls 3

Identification of Microservices through Processed Dynamic Tr...

引用

3rd International Conference on computer Science and Management Technology, ICCSMT 2022

作者： Wu, Sijie Zhang, Cheng Anhui Provincial Key Laboratory of Multimodal Cognitive Computation Anhui University China Anhui University School of Computer Science and Technology China Nanjing University State Key Lab for Novel Software Technology Hefei China

ISBN: (纸本)9798350320404

As the complexity of software systems continues to increase, traditional monolithic software architectures will become difficult to scale and maintain. Microservices as an emerging software architecture it advocates decentralized management, service autonomy, and distinct module boundaries. These features of microservices make software systems easy to maintain, deploy, and modify. However, microservice identification is still not well addressed due to the lack of an effective approach. The existing work on microservice identification mainly starts from the system functionality perspective and does not take into account the actual business rules, which leads to microservice candidates not conforming to the concept of microservices. To address this challenge, we propose an automated approach to microservice identification that combines dynamic and static analysis and takes into account the actual business. Our proposed approach starts with a dynamic and static analysis of the monolithic system. Once the behavioral data of the system is collected, the behavioral data will be further processed according to our proposed guidelines. Then, the proposed approach calculates the degree of the correlation between classes in a monolithic system. Finally, we propose an improved clustering algorithm based on K-means to classify the classes in a monolithic system into different microservices. The proposed approach is validated by comparison with other approaches on open source projects. © 2022 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Data Reconstruction from Gradient Updates in Federated Learning 4th

Data Reconstruction from Gradient Updates in Federated Lea...

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Li, Junhao Zhang, Jianjie Yan, Jijie Zhu, Enmin Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (纸本)9783031200953

Federated learning has become an emerging technology to protect data privacy in the distributed learning area, by keeping each client user’s data locally. However, recent work shows that client users’ data might still be stolen (or reconstructed) directly from gradient updates. After exploring the attack and defense techniques of these data reconstruction methods, we discover that the attacker cannot steal the victim’s data unless it has prior knowledge about the victim’s data size. Thus, the attacker can hardly reconstruct any useful information without these prior knowledge. In this paper, we provide a novel data reconstruction method to obtain a high-dimensional compressed data from the gradient updates, without these prior knowledge. Experiment results show that our reconstructed data can be used to attack the model, with high attack accuracy. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Data Leakage with label Reconstruction in Distributed Learning Environments 1

引用

4th International Conference on Machine Learning for Cyber Security, ML4CS 2022

作者： Zhang, Xiaoxue Zhou, Xiuhua Chen, Kongyang School of Computer Science and Cyber Engineering Guangzhou University Guangzhou China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China Pazhou Lab Guangzhou China Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Wuxi China

ISBN: (数字)9783031200960

ISBN: (纸本)9783031200953

Distributed learning is commonly applied for the high demands of computation resources while training models with large-scale data. However, existing solutions revealed that it may lead to information leakage of private data. Attackers are able to reconstruct data via minimizing the difference between shared gradients and fake gradients that are produced by themselves. This is so-called data leakage attack from gradients. We find that, in many cases, such attack can only obtain random noises or extreme fuzzy information, which are quite different from the raw data. To deal with this problem, we exploit the gradient updates as well as their labels during the parameter-server training, and discover significant information losses during the label coding. Thus, in our method, we reconstruct the labels of samples with a fine-grained method, and we recover the raw inputs with these processed labels. We test our method on different datasets (i.e. CIFAR100 dataset and solid color images) and obtained the reconstructed results which are obviously clearer than the ones of the state-of-the-arts. The results prove the effectiveness of our algorithm in fixing defects to some extent as well. Extensive experiments are also conducted to explore defense strategies against data leakage. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

A comprehensive survey on shadow removal from document images: datasets, methods, and opportunities

引用

Vicinagearth 2025年第1期2卷 1-18页

作者： Wang, Bingshu Li, Changping Zou, Wenbin Zhang, Yongjun Chen, Xuhang Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing & Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing College of Electronics and Information Engineering Shenzhen University Shenzhen China Yongjun Zhang is with the State Key Laboratory of Public Big Data College of Computer Science and Technology Guizhou University Guiyang China School of Computer Science and Engineering Huizhou University Huizhou China School of Computer Science and Engineering South China University of Technology and Pazhou Lab Guangzhou China

With the rapid development of document digitization, people have become accustomed to capturing and processing documents using electronic devices such as smartphones. However, the captured document images often suffer from issues like shadows and noise due to environmental factors, which can affect their readability. To improve the quality of captured document images, researchers have proposed a series of models or frameworks and applied them in distinct scenarios such as image enhancement, and document information extraction. In this paper, we primarily focus on shadow removal methods and open-source datasets. We concentrate on recent advancements in this area, first organizing and analyzing nine available datasets. Then, the methods are categorized into conventional methods and neural network-based methods. Conventional methods use manually designed features and include shadow map-based approaches and illumination-based approaches. Neural network-based methods automatically generate features from data and are divided into single-stage approaches and multi-stage approaches. We detail representative algorithms and briefly describe some typical techniques. Finally, we analyze and discuss experimental results, identifying the limitations of datasets and methods. Future research directions are discussed, and nine suggestions for shadow removal from document images are proposed. To our knowledge, this is the first survey of shadow removal methods and related datasets from document images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Knowledge-aware Multi-view Cross Learning for Edge-based Collaborative Recommendation 29

Knowledge-aware Multi-view Cross Learning for Edge-based Col...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Dai, Yang Meng, Shunmei Gu, Huanhuan Liu, Nan Tu, Longchuan NanJing University of Science and Technology School of Cyberspace Security Nanjing China NanJing University State Key Lab. for Novel Software Technology Nanjing China NanJing University of Science and Technology Department of Computer Science and Engineering Nanjing China Nanjing Sinovatio Technology Co. Ltd. Nanjing China

ISBN: (纸本)9798350330717

In order to effectively overcome the sparsity and cold start challenges of collaborative filtering in actual scenarios, and provide more accurate suggestions, knowledge graphs are commonly utilized in recommender systems. Graph neural networks are increasingly used in knowledge graph-based recommender systems. Nevertheless, conventional recommender systems overlook the relationship information between items and entities as well as the sparse supervision signal, potentially leading to a decline in the actual recommendation performance. In this investigation, we propose KMCL, a Knowledge-aware Multi-view Cross-learning framework for edge-based collaborative recommendation. In contrast to the typical manner of dealing with knowledge graphs, our approach investigates three different graph views to improve users' and items' embedding representations, respectively. Firstly, the merged user-item KG graph is utilized to integrate the multi-hop neighbor information of each user, with the Graph Attention Network assigning various weights to different neighbors. Secondly, Graph Neural Network collects the top-x neighbor nodes for learning in the collaborative view of user-item graph and item-entity graph. Finally, a cross module is developed to share high-level information between embeddings with the same features. In addition, we also introduce the idea of edge computing, which preprocesses and calculates the locally obtained user preferences first, and then inputs them into different views to improve the recommendation efficiency. Experimental results demonstrate that KMCL delivers better suggestions than state-of-the-art baseline models in delivering superior recommendations. Furthermore, our approach maintains higher accuracy in predicting outcomes in less familiar interaction scenarios. © 2023 IEEE.

关键词： Edge Computing Graph Attention Network Knowledge Graph Multi-view Cross Learning Recommender System

来源：评论

学校读者我要写书评

暂无评论

CAT: a coarse-to-fine attention tree for semantic change detection

引用

Visual Intelligence 2023年第1期1卷 1-12页

作者： Wei, Xiu-Shen Xu, Yu-Yan Zhang, Chen-Lin Xia, Gui-Song Peng, Yu-Xin School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China State Key Laboratory of Integrated Services Networks Xidian University Xi’an China Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education and Jiangsu Key Lab of Image and Video Understanding for Social Security Nanjing China 4Paradigm Inc Beijing China School of Computer Science and Institute of Artificial Intelligence Wuhan University Wuhan China Wangxuan Institute of Computer Technology Peking University Beijing China

Semantic change detection (SCD) and land cover mapping (LCM) are always treated as a dual task in the field of remote sensing. However, due to diverse real-world scenarios, many SCD categories are not easy to be clearly recognized, such as “water-vegetation” and “water-tree”, which can be regarded as fine-grained differences. In addition, even a single LCM category is usually difficult to define. For instance, some “vegetation” categories with litter vegetation coverage are easily confused with the general “ground” category. SCD/LCM becomes challenging under both challenges of its fine-grained nature and label ambiguity. In this paper, we tackle the SCD and LCM tasks simultaneously by proposing a coarse-to-fine attention tree (CAT) model. Specifically, it consists of an encoder, a decoder and a coarse-to-fine attention tree module. The encoder-decoder structure extracts the high-level features from input multi-temporal images first and then reconstructs them to return SCD and LCM predictions. Our coarse-to-fine attention tree, on the one hand, utilizes the tree structure to better model a hierarchy of categories by predicting the coarse-grained labels first and then predicting the fine-grained labels later. On the other hand, it applies the attention mechanism to capture discriminative pixel regions. Furthermore, to address label ambiguity in SCD/LCM, we also equip a label distribution learning loss upon our model. Experiments on the large-scale SECOND dataset justify that the proposed CAT model outperforms state-of-the-art models. Moreover, various ablation studies have demonstrated the effectiveness of tailored designs in the CAT model for solving semantic change detection problems. © The Author(s) 2023.

关键词： Attention tree Coarse-to-fine Fine-grained recognition label ambiguity Semantic change detection

来源：评论

学校读者我要写书评

暂无评论

A Fast Test Compaction Method for Commercial DFT Flow Using Dedicated Pure-MaxSAT Solver

A Fast Test Compaction Method for Commercial DFT Flow Using ...

引用

Asia and South Pacific Design Automation Conference

作者： Zhiteng Chao Xindi Zhang Junying Huang Jing Ye Shaowei Cai Huawei Li Xiaowei Li State Key Lab of Processors Institute of Computing Technology Chinese Academy of Sciences School of Computer Science and Technology University of Chinese Academy of Sciences CASTEST Co. Ltd State Key Lab of Computer Science Institute of Software Chinese Academy of Sciences

Minimizing the testing cost is crucial in the context of the design for test (DFT) flow. In our observation, the test patterns generated by commercial ATPG tools in test compression mode still contain redundancy. To tackle this obstacle, we propose a post-flow static test compaction method that utilizes a partial fault dictionary instead of a full fault dictionary, and leverages a dedicated Pure-MaxSAT solver to re-compact the test patterns generated by commercial ATPG tools. We also observe that commercial ATPG tools offer a more comprehensive selection of candidate patterns for compaction in the “n-detect” mode, leading to superior compaction efficacy. In experiments on ISCAS89, ITC99, and open-source RISC-V CPU benchmarks, our method achieves an average reduction of 21.58% and a maximum of 29.93% in test cycles evaluated by commercial tools while maintaining fault coverage. Furthermore, our approach demonstrates improved performance compared with existing methods.

关键词：

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：