检索结果-内蒙古大学图书馆

Distributional constraint discovery for intelligent auditing

KNOWLEDGE AND INFORMATION SYSTEMS 2023年第12期65卷 5195-5229页

作者： Hu, Wentao Jiang, Dawei Wu, Sai Chen, Ke Chen, Gang Zhejiang Police Coll Hangzhou Peoples R China Zhejiang Univ Key Lab Big Data Intelligent Comp Zhejiang Prov Hangzhou Peoples R China

Constraint discovery in relational databases aims to find constraints that express dependency relationships among a set of attributes and has witnessed remarkable success in the applications of data cleaning, detecting data errors, and enhancing police and security operations. In this paper, we propose a new type of constraint, called distributional constraints (DCs), which leverages the attribute value distribution feature for intelligent auditing and security analysis. The constraint, which specifies the range of attribute values that most data follow, enables financial auditors, law enforcement, and security analysts to identify data with anomalous distributions and explain the reasons for such data anomalies. In the context of police and security applications, distributional constraints can help detect potential criminal activities, fraud, and other security threats by identifying unusual patterns in data. To efficiently discover distributional constraints, we propose an inference system to find the minimum coverage of a set of DCs. The efficient optimization technique BitVector indexing is also proposed to further speed up the distributional constraint discovery. We conduct experiments on 12 real datasets such as medical bills and credit card statements to validate the efficiency and effectiveness of our solution. We show the performance of the discovery DCs and the effectiveness of using DCs for detecting abnormal data in different audit datasets.

关键词： Distributional constraint intelligent auditing data discovery Inference system

来源：评论

学校读者我要写书评

暂无评论

Bidirectional interactive alignment network for image captioning

引用

MULTIMEDIA SYSTEMS 2024年第6期30卷 1-13页

作者： Cao, Xinrong Yan, Peixin Hu, Rong Li, Zuoyong Minjiang Univ Sch Comp & Big Data Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China Fujian Univ Technol Sch Comp Sci & Math Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Peoples R China

In recent years, many researchers have improved image captioning performance by fusing region features and grid features. However, the semantic gap between the two features is often overlooked during fusion, and the exploration of multimodal feature interaction remains insufficient. In this paper, we propose a Bidirectional Interactive Alignment Network (BIANet) to achieve more multi-feature and multi-modal fusion in both the encoder and decoder. We propose a bidirectional interactive encoder that utilizes cross-interaction to complement the advantages of both image features, enriching their visual information. In the decoder, we propose a cross-alignment module. This module enables the text features to interact in two sequences: "region feature-grid feature" and "grid feature-region feature", resulting in two new text features. By improving the similarity between these two text features, the semantic gap between region features and grid features is indirectly alleviated. Extensive experiments on the MS COCO dataset demonstrate that the proposed model achieves competitive results on the Karpathy test split.

关键词： Image captioning Bidirectional interaction Cross-alignment module Semantic gap

来源：评论

学校读者我要写书评

暂无评论

Learning a multi-cluster memory prototype for unsupervised video anomaly detection

引用

INFORMATION SCIENCES 2025年 686卷

作者： Wu, Yuntao Zeng, Kun Li, Zuoyong Peng, Zhonghua Chen, Xiaobo Hu, Rong Fujian Univ Technol Sch Comp Sci & Math Fujian Prov Key Lab Big Data Min & Applicat Fuzhou 350118 Peoples R China Minjiang Univ Sch Comp & Big Data Fujian Prov Key Lab Informat Proc & Intelligent Co Fuzhou 350121 Peoples R China Shandong Technol & Business Univ Sch Comp Sci & Technol Yantai 264005 Peoples R China Wuyi Univ Key Lab Cognit Comp & Intelligent Informat Proc Fu Wuyishan 354300 Peoples R China

In recent years, there has been rapid development in video anomaly detection (VAD). The previous methods ignored the differences between normal videos and only emphasized learning the commonalities of normal videos. In order to improve the performance of anomaly detection, we delve into the spatial distribution of normal video features and utilize their differences for clustering, leading to more minor reconstruction errors for normal videos and more significant reconstruction errors for abnormal videos. To achieve this goal, we introduce a Multi-Cluster Memory Prototype framework (MCMP) for VAD, which explores the coarse-grained and finegrained information from video snippet features simultaneously to learn a memory prototype, thereby significantly improving the ability to discriminate abnormal events in complex scenes. First, a video feature clustering method that employs contrastive learning is introduced to group samples sharing similar fine-grained features. Second, the memory mechanism is used to capture the feature distribution of normal samples. Lastly, the Gaussian filter feature transformation method is introduced to make normal and abnormal features more distinguishable. The frame level AUC of MCMP on ShanghaiTech and UCF-Crime benchmark datasets has increased by 1.26% and 0.45% compared to state-of-the-art methods. Our code is publicly available at https:// github .com /WuIkun5658 /MCMP.

关键词： Video anomaly detection Contrastive learning Memory mechanism Clustering Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Language-Image Consistency Augmentation and Distillation Network for visual grounding

引用

PATTERN RECOGNITION 2025年 166卷

作者： Ke, Xiao Xu, Peirong Guo, Wenzhong Fuzhou Univ Coll Comp & Data Sci Fujian Prov Key Lab Networking Comp & Intelligent Fuzhou 350116 Peoples R China Minist Educ Engn Res Ctr Big Data Intelligence Fuzhou 350116 Peoples R China

With the advancement of Vision-Language Pretraining, unified multimodal models have exhibited promising performance in various downstream tasks. However, existing models, which relied on a generic structure for knowledge extraction in Visual Grounding task, did not fully leverage the consistency information between modalities, leading to challenges in generalization. To address this, we proposed a Language-Image Consistency Augmentation and Distillation Network (CADN) based on CLIP model. CADN balanced task loss to alleviate overfitting by allocating weights based on consistency information within CLIP features to penalize task loss. Furthermore, to retain consistency information from the pretrained model during training, we designed Consistency-Aware Self-Distillation Module (CASD), utilized as a converter after feature encoding. This module introduced additional loss functions supervised by CLIP similarity matrix and self-attention weights to ensure the restoration of consistency information in features. Additionally, we proposed Language-Enhanced Masked Attention (LEMA) to generate Spatial-Channel masks, guiding cross-modal attention to adaptively select regions and intensities of multimodal features. This enhanced the quality of decoding features, enabling query vectors to focus on semantic features relevant to textual descriptions, thus improving model performance in VG task. Experimental results not only demonstrated that our proposed model can achieve superior performance on REC datasets, but also demonstrated the distribution changes of feature consistency information through visualization experiments. These results may offer new insights and methodologies for the study and application of cross-modal consistency.

关键词： Visual grounding Referring expression comprehension Self-distillation

来源：评论

学校读者我要写书评

暂无评论

SRMamba-T: Exploring the hybrid Mamba-Transformer network for Single Image Super-Resolution

引用

NEUROcompUTING 2025年 624卷

作者： Liu, Cencen Zhang, Dongyang Lu, Guoming Yin, Wen Wang, Jielei Luo, Guangchun Univ Elect Sci & Technol China UESTC Inst Intelligent Comp Chengdu 611731 Peoples R China Trusted Cloud Comp & Big Data Key Lab Sichuan Prov Chengdu 611731 Peoples R China

Single Image Super-Resolution (SISR) has made significant advancements with both CNN-based and Transformer-based models. However, CNNs often struggle to capture long-range dependencies effectively, and Transformers, though powerful, are hindered by quadratic computational complexity. In recent years, state space models (SSMs), such as Mamba, have emerged as promising alternatives due to their ability to model long-range dependencies with linear time complexity. In light of this, we propose SRMamba-T, a hybrid model that strategically combines Mamba and Transformer architectures to balance computational efficiency with high performance. Specifically, we employ Transformer layers following Mamba layers to further enhance the model's capability to handle long-range spatial information and expand its effective receptive fields. To design a lightweight network, we propose a multi-directional selective scanning module to reduce parameter count and improve computational efficiency. Additionally, a feature fusion module serves as a bottleneck to effectively integrate hierarchical features and enhance the model's representational ability. comprehensive experimental evaluations across five widely recognized benchmarks underscore our model's effectiveness, demonstrating its superiority over existing state-of-the-art (SOTA) methods. For example, our model achieved a significant PSNR improvement of 0.28 dB for x2 lightweight super-resolution on Urban100, with a reduction in MACs by 38.7% (from 198.1G to 121.5G) compared to the SOTA model, MambaIR.

关键词： Single image super-resolution Mamba Transformer Lightweight model

来源：评论

学校读者我要写书评

暂无评论

Transmission Continuous Meta-Grating for Generating Wide-Band Low-to-High Order OAM With Extremely High Mode Purity

引用

IEEE TRANSACTIONS ON ANTENNAS AND PROPAGATION 2024年第7期72卷 5767-5781页

作者： Wang, Chao Yu, Hang Wu, Jie Xu, Guanghui Sun, Qing-An Li, Minquan Yang, Lixia Huang, Zhixiang Anhui Univ Minist Educ Ctr Big Data & Populat Hlth IHM Key Lab Intelligent Comp & Signal Proc Hefei 230601 Peoples R China Anhui Univ Ctr Big Data & Populat Hlth IHM Informat Mat & Intelligent Sensing Lab Anhui Prov Hefei 230601 Peoples R China

This article presents a novel continuous dielectric meta-grating array (DMGA) for generating wide-band, high-performance transmission orbital angular momentum (OAM) vortex beams with high mode purity. A broadband meta-grating unit (MGU) was designed and modeled theoretically, including a detailed analysis of its design process. Simulations and theoretical calculations show that, in the 26-39 GHz (40%), the unit achieves a 180 degrees transmission phase and a transmission coefficient over 0.9. The array patterning was determined using a grating function. The DMGA is composed of continuously spatially varying grating strips, effectively preventing issues caused by array discontinuity such as interatom coupling and discontinuous step phase changes, which could lead to vortex beam distortion and low purity. Simulations show that the DMGA generates broadband, high-performance vortex beams with high mode purity for mode orders l =2 , 3, 4, 5, 6, 7, 8, 9, and 10, exhibiting advantages in generating high-quality, high-order OAM beams. Additionally, it exhibits frequency-aperture size insensitivity, enabling miniaturization and customization of aperture sizes. Finally, the measurement confirms the effectiveness.

关键词： Metasurfaces Broadband communication Broadband antennas Gratings Dielectrics Antennas and propagation Phased arrays Continuous grating high purity orbital angular momentum (OAM) transmission wide-band

来源：评论

学校读者我要写书评

暂无评论

Group Coding Location Privacy Protection Method Based on Differential Privacy in Crowdsensing

引用

IEEE INTERNET OF THINGS JOURNAL 2024年第17期11卷 28398-28408页

作者： Wang, Taochun Tao, Yuan Zhang, Qiong Xu, Nuo Chen, Fulong Zhao, Chuanxin Anhui Normal Univ Anhui Engn Res Ctr Med Big Data Intelligent Syst Sch Comp & Informat Anhui Prov Key Lab Ind Intelligence Data Secur Wuhu 241003 Peoples R China

With the proliferation of mobile smart devices, such as smartphones, mobile crowdsensing (MCS) has gained significant attention and widespread application. However, the increasing risk of personal privacy breaches has become a significant concern in MCS. Typically, workers are required to disclose their location information to participate in task assignments, making the protection of sensitive data, like location, a crucial factor influencing worker engagement. To address the issue of location privacy leakage in the task allocation process, this article proposes a location privacy protection method (VGDP) based on local differential privacy. In VGDP, the server utilizes a clustering algorithm to construct a task map based on the Voronoi diagram using task locations. Each task location is then mapped to its corresponding task area to ensure the privacy of the location information. Encoding technology is employed to encode the relative locations of all workers within the area, while a double random response mechanism is utilized to obfuscate the relative location codes, thereby safeguarding their location privacy. Furthermore, a personalized privacy budget allocation mechanism is employed to enhance the effectiveness of privacy protection. Once workers upload their perturbed location information to the server, the server selects winners based on the perturbed locations to facilitate task allocation. Additionally, this article proposes a high-reward payment method to augment workers' enthusiasm for participation. Experimental results demonstrate that the proposed method exhibits promising performance in terms of data availability and location privacy.

关键词： Task analysis Privacy Protection Differential privacy Resource management Sensors Servers location privacy mobile crowdsensing task allocation

来源：评论

学校读者我要写书评

暂无评论

FEDBFPT: An Efficient Federated Learning Framework for BERT Further Pre-training 32

FEDBFPT: An Efficient Federated Learning Framework for BERT ...

引用

32nd International Joint Conference on Artificial Intelligence (IJCAI)

作者： Wang, Xin'ao Li, Huan Chen, Ke Shou, Lidan Zhejiang Univ Key Lab Intelligent Comp Based Big Data Zhejiang Hangzhou Peoples R China

ISBN: (纸本)9781956792034

This study proposes FEDBFPT (Federated BERT Further Pre-Training), a Federated Learning (FL) framework for further pre-training the BERT language model in specialized domains while addressing privacy concerns. FEDBFPT enables multiple clients to collaboratively train the shallower layers of BERT, which are crucial in the pre-training stage, without the need to share private data. To achieve this, FEDBFPT involves building a local model for each client, progressively training the shallower layers of local models while sampling deeper layers, and aggregating trained parameters on a server to create the final global model. This approach utilizes multiple smaller local models to further pre-train a global model targeted at specific tasks via fine-tuning, resulting in a reduction in resource usage while maintaining model accuracy. Theoretical analysis is conducted to support the efficiency of FEDBFPT, and experiments are conducted on corpora across domains such as medicine, biology, and computer science. Results indicate that FEDBFPT achieves performance levels comparable to traditional FL methods while reducing computation and communication costs by 46.70% and 7.04%, respectively, even approaching the performance of centralized training models. The Source code is released at https://***/Hanzhouu/FedBFPT.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Zero-shot 3D anomaly detection via online voter mechanism

引用

NEURAL NETWORKS 2025年 187卷 107398页

作者： Zheng, Wukun Ke, Xiao Guo, Wenzhong Fuzhou Univ Coll Comp & Data Sci Fujian Prov Key Lab Networking Comp & Intelligent Fuzhou 350116 Fujian Peoples R China Fuzhou Univ Engn Res Ctr Big Data Intelligence Minist Educ Fuzhou 350116 Peoples R China

3D anomaly detection aims to solve the problem that image anomaly detection is greatly affected by lighting conditions. As commercial confidentiality and personal privacy become increasingly paramount, access to training samples is often restricted. To address these challenges, we propose a zero-shot 3D anomaly detection method. Unlike previous CLIP-based methods, the proposed method does not require any prompt and is capable of detecting anomalies on the depth modality. Furthermore, we also propose a pre-trained structural rerouting strategy, which modifies the transformer without retraining or fine-tuning for the anomaly detection task. Most importantly, this paper proposes an online voter mechanism that registers voters and performs majority voter scoring in a one-stage, zero-start and growth-oriented manner, enabling direct anomaly detection on unlabeled test sets. Finally, we also propose a confirmatory judge credibility assessment mechanism, which provides an efficient adaptation for possible few-shot conditions. Results on datasets such as MVTec3D-AD demonstrate that the proposed method can achieve superior zero-shot 3D anomaly detection performance, indicating its pioneering contributions within the pertinent domain.

关键词： Anomaly detection Zero-shot Multimodal Pretrained model Online voter mechanism

来源：评论

学校读者我要写书评

暂无评论

Dynamic multi-label feature selection algorithm based on label importance and label correlation

引用

INTERNATIONAL JOURNAL OF MACHINE LEARNING AND CYBERNETICS 2024年第8期15卷 3379-3396页

作者： Chen, Weiliang Sun, Xiao Hefei Univ Technol Sch Comp Sci & Informat Engn AnHui Prov Key Lab Affect Comp & Adv Intelligent M Key Lab Knowledge Engn Big DataMinist Educ Feicui Rd Hefei 230009 Anhui Peoples R China

Multi-label distribution is a popular direction in current machine learning research and is relevant to many practical problems. In multi-label learning, samples are usually described by high-dimensional features, many of which are redundant or invalid. This paper proposes a multi-label static feature selection algorithm to solve the problems caused by high-dimensional features of multi-label learning samples. This algorithm is based on label importance and label relevance, and improves the neighborhood rough set model. One reason for using neighborhood rough sets is that feature selection using neighborhood rough sets does not require any prior knowledge of the feature space structure. Another reason is that it does not destroy the neighborhood and order structure of the data when processing multi-label data. The method of mutual information is used to achieve the extension from single labels to multiple labels in the multi-label neighborhood;through this method, the label importance and label relevance of multi-label data are connected. In addition, in the multi-label task scenario, features may be interdependent and interrelated, and features often arrive incrementally or can be extracted continuously;we call these flow features. Traditional static feature selection algorithms do not handle flow features well. Therefore, this paper proposes a dynamic feature selection algorithm for flow features, which is based on previous static feature selection algorithms. The proposed static and dynamic algorithms have been tested on a multi-label learning task set and the experimental results show the effectiveness of both algorithms.

关键词： Flow feature label correlation label importance Multi-label distribution Neighborhood rough set

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：