检索结果-内蒙古大学图书馆

International Joint Conference on Neural networks (IJCNN)

作者： Qingyu Xu Jiguo Yu Anming Dong Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China School of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Big Data Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

YOLOv5s is a classic deep learning target detection framework with balanced speed and performance in recognition, which is widely used in industrial defect inspections. YOLOv5s relies on the residual structure in the C3 module for feature extraction, but due to its simple structure and the small, fixed convolution kernel, it is difficult to accurately and completely extract target features when applied to the detection of defects with inconspicuous features and irregular shapes, which results in a decrease in recognition accuracy. To solve this problem, this paper proposes an improved YOLO architecture based on receptive field enhancement and redundant feature reuse. Firstly, the method designs a redundant feature reuse module (RFRM) to replace the residual structure in the C3 module for feature extraction. This module can deepen the network with a smaller cost and enhance the network’s ability to extract features. Furthermore, the feature reuse process allows the network to deepen while retaining detailed information, enabling the network to classify and localize more accurately. Secondly, a simplified convolutional block attention module (SCBAM) is designed and embedded into the neck of the detection network. This module directs the detection network to focus more on inconspicuous defect features and reduce interference from background noise in the feature map, thereby improving the accuracy of defect classification and localization. Finally, a receptive field enhancement module (RFEM) is designed and inserted between the neck and head of the detection network. This module adds only a small computational cost to expand the receptive field of the network, enabling it to further extract and comb irregular features from the neck in a comprehensive manner, making the features reaching the detection head more complete. Applying the above improvements to defect detection, the experimental results show that the improved YOLO architecture based on receptive field enhancem

关键词： YOLO Head Accuracy Target recognition Shape Computer architecture Feature extraction

来源：评论

学校读者我要写书评

暂无评论

EMO: An Ontology for Supporting the Management of Epidemic

EMO: An Ontology for Supporting the Management of Epidemic

引用

Applied Physics and Computing (ICAPC), International Conference on

作者： Yongchao Gao Qiuyue Wang Mark S. Fox Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Qilu University of Technology (Shandong Academy of Sciences) Jinan China Standard Institute of Emerging Technologies and Innovations Jinan China Urban Data Centre University of Toronto Toronto Canada

In order to improve the coverage of concepts in epidemic management, this paper constructs an epidemic management ontology EMO to help manage and analyse epidemic data. First, based on the ISO/lEC 5087 city data model series of standards and TOVE method, EMO is constructed using Protégé. Secondly, the data types and their relationships required in the epidemic management use cases are defined. Finally, the instance data help to verify the ability of EMO to represent the city epidemic management data. Results show that EMO provides a clear, accurate and unified definition of epidemic management data, improves the efficiency of data sharing and integration, and reduces the difficulty of developing epidemic management tools.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Semantic Information Reasoning and Multi-Step Cross-Modal Interaction network for Image-Text Retrieval

Semantic Information Reasoning and Multi-Step Cross-Modal In...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Xishan Ma Yushui Geng Jing Zhao Huanxiao Zhou Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Image-text retrieval is a basic cross-modal task, and the basic idea is to learn image-text matching. The key to this task is to accurately measure the similarity between these two modalities. However, most existing methods tend to measure image-text similarity based on highly correlated region-word pairs, which lacks the ability to capture complex cross-modal semantic associations, thereby resulting in failure to distinguish hard negative examples that are similar in semantic content. Furthermore, existing methods focus more on alignment of different modal features, thus neglecting deep reasoning about the semantic concepts within the modality. In this paper, we propose a new semantic information reasoning and multi-step cross-modal interaction (SRMCI) network to simultaneously explore intra-modal and inter-modal relationships. Specifically, we first propose a semantic information reasoning module to fully explore potential semantic relationships within modalities and focus on fragments with important semantic information. Then, we design a multi-step cross-modal interaction module that utilizes two different inter-modal interactive attentions and an effective gated fusion strategy to capture fragment-level and fragment-instance-level cross-modal semantic associations. In particular, this gated fusion strategy is used to learn better fine-grained feature representations to aid in understanding and establishing semantic associations between different modalities. Experiments on the benchmark datasets MS-COCO and Flickr30K demonstrate the effectiveness of our method.

关键词： Correlation Semantics Neural networks Logic gates Benchmark testing Cognition

来源：评论

学校读者我要写书评

暂无评论

Accuracy Indoor Localization Based on Fuzzy Transfer Learning Model

Accuracy Indoor Localization Based on Fuzzy Transfer Learnin...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Sheng Wu Yanhui Ji Licai Zhu Liang Zhao Hao Yang Nanjing Tech University Yancheng Teachers University Nanjing China Yancheng Teachers University Nanjing Tech University Yancheng China Shenyang Aerospace University Shenyang China Yancheng Teachers University Yancheng China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China

Location-based services greatly facilitate people’s daily life, which puts forward higher requirements for the location calculation of target objects in different environments. Since the fingerprint positioning method does not require additional special equipment and easy to implement, it has become one of the most attractive solutions. In order to ensure the positioning accuracy, this method requires complete sampling of the fingerprints of the positioning area, so a lot of sampling costs are required. In particular, when sampling buildings with multiple floors, the labor and time of the entire sampling process will increase dramatically. At the same time, certain floors or rooms may not be allowed to open, so their fingerprints cannot be sampled. In fact, the floor structures of buildings are mostly similar or the same, such as office buildings, hotels. Therefore, this paper proposes a fuzzy transfer learning model and builds the corresponding prototype system FTLoc. On the premise of ensuring the positioning accuracy of different floors, the system greatly reduces the sampling cost of the entire building. First, for the complete fingerprint data (source domain) of a certain floor, we mine the fingerprint features fine-grained to generate a short-term feature set for each sampling point. Then, according to the sparsity and timing of short-term features, we design an optimized SELSTM, and obtain an effective localization model as the PreModel for transfer learning. Finally, fuzzy clustering is used to add category labels to the source domain data and target domain data, and input them into PreModel to realize the localization model transfer, so as to avoid their data distribution differences affecting the transfer effect as much as possible. FTLoc is fully validated in a multi-storey building. According to the experimental results, when using the first floor sampling data as the source domain, the errors of the FTLoc system on the adjacent floor (second floor) are

关键词：

来源：评论

学校读者我要写书评

暂无评论

LampMark: Proactive Deepfake Detection via Training-Free Landmark Perceptual Watermarks

arXiv

引用

arXiv 2024年

作者： Wang, Tianyi Huang, Mengxiao Cheng, Harry Zhang, Xiao Shen, Zhiqi Nanyang Technological University Singapore Singapore Qilu University of Technology Jinan China Shandong University Qingdao China Joint NTU-WeBank Research Centre on Fintech Nanyang Technological University Singapore Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology China College of Computing and Data Science Nanyang Technological University Singapore

Deepfake facial manipulation has garnered significant public attention due to its impacts on enhancing human experiences and posing privacy threats. Despite numerous passive algorithms that have been attempted to thwart malicious Deepfake attacks, they mostly struggle with the generalizability challenge when confronted with hyper-realistic synthetic facial images. To tackle the problem, this paper proposes a proactive Deepfake detection approach by introducing a novel training-free landmark perceptual watermark, LampMark for short. We first analyze the structure-sensitive characteristics of Deepfake manipulations and devise a secure and confidential transformation pipeline from the structural representations, i.e. facial landmarks, to binary landmark perceptual watermarks. Subsequently, we present an end-to-end watermarking framework that imperceptibly and robustly embeds and extracts watermarks concerning the images to be protected. Relying on promising watermark recovery accuracies, Deepfake detection is accomplished by assessing the consistency between the content-matched landmark perceptual watermark and the robustly recovered watermark of the suspect image. Experimental results demonstrate the superior performance of our approach in watermark recovery and Deepfake detection compared to state-of-the-art methods across in-dataset, cross-dataset, and cross-manipulation scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： Watermarking

来源：评论

学校读者我要写书评

暂无评论

Semantic Relation-Based Cross Attention network for Image-Text Retrieval

Semantic Relation-Based Cross Attention Network for Image-Te...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Huanxiao Zhou Yushui Geng Jing Zhao Xishan Ma Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Image-text retrieval refers to querying the text or image of another modality given an image or text, and its key lies in the ability to accurately measure the similarity between text and image. Most of the existing retrieval methods only utilize the intramodal relations of each modality or the intermodal relations of the two modalities to perform the retrieval task. To address the above problems, we integrate the intra-modal and inter-modal relations and propose a Semantic Relation-based Cross Attention network(SRCAN). In our proposed method, we first mine the possible intra-modal associations between regions in an image and between words in a text to obtain features with semantic relationships, and then capture the fine-grained associations between segments through the cross-attention mechanism. Finally, we balance the intra-modal and inter-modal relationships to improve the performance of the model. Our proposed method is experimentally validated on two datasets, Flickr30K and MS-COCO, and the experimental results show that our method achieves superior results.

关键词： Image segmentation Semantics Bidirectional control Feature extraction Cognition Feeds Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Constructing Efficient Set of APs Via Spatial Discrimination and Localization Difference

Constructing Efficient Set of APs Via Spatial Discrimination...

引用

Symposia and Workshops on Ubiquitous, Autonomic and Trusted Computing, UIC-ATC

作者： Yanhui Ji Sheng Wu Licai Zhu Liang Zhao Hao Yang Nanjing Tech University Yancheng Teachers University Nanjing China Yancheng Teachers University Nanjing Tech University Yancheng China Shenyang Aerospace University Shenyang China Yancheng Teachers University Yancheng China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Chengdu China

RSSI fingerprint-based localization has been one of the most attractive solutions, since it is free of extra infrastructure and specialized hardware. As wireless networks become more widely used, however, the number of APs for localization has been increasing and then results in "invalid APs", nearly APs that are redundant or have a negative impact on locating, and raises the computational overhead in the process of localization. To solve these problems, the previous literatures focused on selecting some efficient APs for localization. These approaches could remove a few of redundant APs and reduce the localization overhead to a certain extent, but the performance of locating will fluctuate significantly. In this paper, we propose a constructing efficient set of APs via spatial discrimination and localization difference, ESAP. First, for a single AP, we use the information gain rate to evaluate its spatial resolution ability, which effectively reflects the difference between the maps constructed by the fingerprints of each AP at different sampling points, and shows the AP’s discrimination of spatial locations. Moreover, we calculate the localization capability of APs at different sampling points, and design an incremental clustering algorithm based on the information gain rate of APs by using the localization differences of each AP at each sampling point. The algorithm generates various candidate sets according to the geographical diversity of AP’s fingerprint map, and is more robust in actual applications. Finally, an effective set of APs algorithm based on the minimum-maximum principle is proposed. In the process of constructing the effective set, suitable APs are chosen on the basis of the clustering results and the predefined requirements. Extensive experiments in real large-scale environment validates that the performance of our ESAP outperforms the existing AP selection methods, Info-Gain, ESC and SDN. When reducing APs by 40%, the accuracy of ESAP is better t

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cross-modal retrieval based on Attention Embedded Variational Auto-Encoder

Cross-modal retrieval based on Attention Embedded Variationa...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Kaili Zhou Yiyun Xing Yushui Geng Jing Zhao Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Graduate School Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

This study proposes a cross-modal retrieval technique, which employs an Attention Embedded Variational AutoEncoder (AE-VAE) to tackle the problem of reduced retrieval accuracy resulting from data noise and data absence in cross-modal retrieval tasks. First, the variational auto-encoder(VAE) is used as an infrastructure to transform modal data into latent variables by encoding and decoding different modal features, thus preserving the semantic structure of the raw modal data and suppressing noise and missing information in the data. Secondly, to better capture the important semantic features of image and text modalities, an improved multi-attention module is introduced in the encoder. In addition, a cross-modal alignment module is designed to further align the latent variables of different modalities in the latent space to solve the confusion problem and improve the accuracy and robustness of cross-modal retrieval. Finally, experiments are conducted on four public datasets, CUB, SUN, AwA1 and AwA2, and the experimental results show that our proposed model is effective in improving the accuracy and robustness of retrieval.

关键词： Accuracy Uncertainty Noise Semantics Transforms Probabilistic logic Robustness

来源：评论

学校读者我要写书评

暂无评论

PrintListener: Uncovering the Vulnerability of Fingerprint Authentication via the Finger Friction Sound

arXiv

引用

arXiv 2024年

作者： Zhou, Man Su, Shuao Wang, Qian Li, Qi Zhou, Yuting Ma, Xiaojing Li, Zhengxiong School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Wuhan University China Institute for Network Sciences and Cyberspace Tsinghua University China Department of Computer Science and Engineering University of Colorado Denver United States Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China

Fingerprint authentication has been extensively employed in contemporary identity verification systems owing to its rapidity and cost-effectiveness. Due to its widespread use, fingerprint leakage may cause sensitive information theft, enormous economic and personnel losses, and even a potential compromise of national security. As a fingerprint that can coincidentally match a specific proportion of the overall fingerprint population, MasterPrint rings the alarm bells for the security of fingerprint authentication. In this paper, we propose a new side-channel attack on the minutiae-based Automatic Fingerprint Identification System (AFIS), called PrintListener, which leverages users’ fingertip swiping actions on the screen to extract fingerprint pattern features (the first-level features) and synthesizes a stronger targeted PatternMasterPrint with potential second-level features. The attack scenario of PrintListener is extensive and covert. It only needs to record users’ fingertip friction sound and can be launched by leveraging a large number of social media platforms. Extensive experimental results in real-world scenarios show that Printlistener can significantly improve the attack potency of MasterPrint. © 2024, CC0.

关键词： Friction

来源：评论

学校读者我要写书评

暂无评论

Semantic-Enhanced Attention network for Image-Text Matching

Semantic-Enhanced Attention Network for Image-Text Matching

引用

International Conference on Computer Supported Cooperative Work in Design

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Image-text matching is an important task in cross-modal information processing, which consists of evaluating the similarity between images and text. However, the data of the two modalities have different distributions and representations, which cannot be directly compared. Therefore, the two modalities need to be processed separately. Most existing image-text matching methods extract image fragments and text fragments separately, using an attention mechanism to establish relationships between regions in the image and words in the text. Subsequently, they aggregate the similarity of these images and text fragments. Regardless, not all fragment alignment is meaningful, and irrelevant fragment alignment will bring redundancy and reduce retrieval accuracy. In addition to that, there are contextual relationships between image regions and between text words, which should also be taken into account. In this paper, we simultaneously consider these two aspects and propose a Semantic-Enhanced Attention network (SEAN). It first focuses on each modality, mining contextual relationships between fragments within each modality and aggregating contextual information into visual and textual embeddings. Then, we compute the similarity between all image regions and text fragments, focusing all attention on the region-word pairs with the highest similarity. Finally, we summarize these to infer the similarity between the image and text. Our method achieves competitive results on two generalized image text retrieval datasets, Flickr30K and MS-COCO.

关键词： Visualization Attention mechanisms Federated learning Computational modeling Aggregates Semantics Redundancy

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：