检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Gou, Yang Ye, Yinghui Lu, Guangyue Lv, Lu Hu, Rose Qingyang The Shaanxi Key Laboratory of Information Communication Network and Security Xi’an University of Posts & Telecommunications China The School of Telecommunications Engineering Xidian University Xi’an710071 China The Department of Electrical and Computer Engineering Utah State University United States

In this paper, we consider intelligent reflecting surface (IRS) in a non-orthogonal multiple access (NOMA)aided Integrated Sensing and Multicast-Unicast Communication (ISMUC) system, where the multicast signal is used for sensing and communications while the unicast signal is used only for communications. Our goal is to depict whether the IRS improves the performance of NOMA-ISMUC system or not under the imperfect/perfect successive interference cancellation (SIC) scenario. Towards this end, we formulate a non-convex problem to maximize the unicast rate while ensuring the minimum target illumination power and multicast rate. To settle this problem, we employ the Dinkelbach method to transform this original problem into an equivalent one, which is then solved via alternating optimization algorithm and semidefinite relaxation (SDR) with Sequential Rank-One Constraint Relaxation (SROCR). Based on this, an iterative algorithm is devised to obtain a near-optimal solution. computer simulations verify the quick convergence of the devised iterative algorithm, and provide insightful results. Compared to NOMA-ISMUC without IRS, IRS-aided NOMA-ISMUC achieves a higher rate with perfect SIC but keeps the almost same rate in the case of imperfect SIC. Copyright © 2023, The Authors. All rights reserved.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

MCAF: Multi-Headed Causal Attention Fusion Approach for Multimodal Sentiment Analysis

MCAF: Multi-Headed Causal Attention Fusion Approach for Mult...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Qingao Wang Xingang Wang Jinxiao Yang Yurun Bi 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

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Multimodal sentiment analysis(MSA) aims to synthesize multiple pieces of information, including textual, visual, and auditory information, to more accurately infer sentiment polarity. Due to the existence of complex and diverse affective causal relationships between different modalities, they interact with each other and constitute a multidimensional expression of human emotions. In the face of unbalanced data, i.e., when there are significant differences in the number of samples between different categories, the attention mechanism of the model tends to focus on spurious correlations in the training data, seriously impairing the model’s generalization ability and leading to bias, unbalanced prediction, and false correlation identification problems. To address the above problems, this study proposes a new multimodal fusion method based on the "within-sample sampling" and "cross-sample sampling" front door adjustment methods in causal inference strategies: the multi-head causal attention fusion method (MCAF). This method aims to capture potential causal relationships between different modalities through different attention heads, helping the model focus more on key causal features and avoid paying too much attention to false correlations in the training data. This helps improve the generalization performance of the model, make the decision-making process of the model more interpretable, and enhance the accuracy and robustness of the model for multimodal sentiment analysis tasks, making it more suitable for practical application scenarios.

关键词： Analytical models Sentiment analysis Visualization Correlation Neural networks Training data Predictive models

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Assisted UAV Data Free-Boundary Spatial Querying and Authenticated Sharing

Blockchain-Assisted UAV Data Free-Boundary Spatial Querying ...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Ya Zhang Xi Lin Jun Wu Bei Pei Yunyun Han School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Collaborative Innovation Center of Shanghai Industrial Internet Shanghai China Graduate School of Information Production and Systems Waseda University Japan Key Lab of Information Network Security Ministry of Public Security Shanghai China Bitverse (Shanghai) Technology Co. Ltd Shanghai China

The flexibility and low cost of unmanned aerial vehicles (UAVs) offer great potential for them in areas such as disaster relief, energy line inspection, and traffic monitoring. Multiple UAVs form an airborne UAV network to share geo-tagged observation data for better collaborative missions. Blockchain can solve the security threats caused by the environment’s untrustworthiness and the UAV networks’ openness. However, the key to sharing data in blockchain-assisted UAV networks is identifying and understanding observational data and providing authentication query services in free boundary spatial. This paper proposes a blockchain-assisted UAV network data-sharing framework based on Non-Fungible Token (NFT). First, we design a marking and describing data method based on NFT to help geo-tagged data be effectively understood. Moreover, we propose a free-boundary spatial index tree to manage data and provide efficient queries. Furthermore, combined with the consensus mechanism and the blockchain transaction tree, the proposed sharing framework can provide query results authentication. Compared with the existing schemes, analysis and experiments demonstrate that our scheme could support the arbitrary expansion of UAV flight range and the random distribution of observation data in space, save at least 22% of storage overhead and reduce more than 36% of query time overhead.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TSFE: Research on Transformer and Feature Enhancement Methods for Image-Text Retrieval

TSFE: Research on Transformer and Feature Enhancement Method...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Jinxiao Yang Xingang Wang Qingao Wang 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

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

In recent years, cross-modal retrieval has a wide range of applications in fields such as information retrieval and multimedia processing, where the key is to find relevant data in another modality through one modal query. In cross-modal graphic retrieval, mutual attention mechanisms are commonly used to interact image and text features. However, this interaction mechanism makes it difficult to extract separate visual and textual features for subsequent indexing steps, especially in large-scale retrieval tasks. Furthermore, in image representation, non-semantic information in image features can lead to inaccuracies in the alignment of image and text features. Therefore this paper proposes a Transformer and Feature Enhancement Method (TSFE) for Image-Text Retrieval. The method better fuses the underlying features and the higher level features by using a hierarchical Transformer coding structure on two separate branches, image and text, to proofread and localise the final output features. The Feature Enhanced Attention (FEA) module is designed in order to infer non-semantic information in the image and enhance the features of salient regions. Channel-space attention and max pooling is introduced on top of Transformer encoder self-attention to filter redundant and interfering information from channel and spatial dimensions. Experiments on Flickr30k dataset and MS-COCO dataset in this paper show improved performance in cross-modal retrieval, thus validating the effectiveness and sophistication of the proposed method.

关键词： Visualization Semantics Pipelines Noise Image representation Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CAFI: News Recommendation with Candidate Perception of Fine-Grained Interaction information

CAFI: News Recommendation with Candidate Perception of Fine-...

引用

International Conference on computer Supported Cooperative Work in Design

作者： Yiwen Li Zhenyu Yang Xiaoyang Li Zhijun Li 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

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

The most critical task in personalized news recommendation is to perform exact matching between candidate news and users’ interests. Existing news recommendation methods usually model users’ interests from historical clicked news items without considering candidate news, which makes it difficult to precisely match candidate news with users’ interests. Moreover, it is challenging to distinguish similar news when forming a vector representation. Simply adding candidate news to the user interest modeling process without considering word-level information does not provide sufficient discrimination for recommending appropriate news. In this paper, we propose a news recommendation model with candidate-aware fine-grained interaction information (CAFI). In our approach, we propose a fine-grained interaction module that matches candidate news items and text fragments of each historical news item at each semantic granularity to achieve interaction between the two at the word level and help similar historical news form more specific and accurate representations. In addition, our proposed gated self-attention mechanism utilizes the candidate news features as channel moderation gates to implement the process of filtering out information that is irrelevant to the candidate news for learning user interest representations, thereby better matching the candidate news to specific user interests. Experiments conducted on the large real-world Microsoft News Dataset (MIND) show that our model significantly outperforms the previously developed models in terms of all metrics. Our code is published at the following URL: https://***/liyiweneven/CAFI.

关键词： Uniform resource locators Measurement Codes Filtering Federated learning Semantics Focusing

来源：评论

学校读者我要写书评

暂无评论

LLMDet: Learning Strong Open-Vocabulary Object Detectors under the Supervision of Large Language Models

arXiv

引用

arXiv 2025年

作者： Fu, Shenghao Yang, Qize Mo, Qijie Yan, Junkai Wei, Xihan Meng, Jingke Xie, Xiaohua Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University China Tongyi Lab Alibaba Group China Peng Cheng Laboratory China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security Technology China China

Recent open-vocabulary detectors achieve promising performance with abundant region-level annotated data. In this work, we show that an open-vocabulary detector co-training with a large language model by generating image-level detailed captions for each image can further improve performance. To achieve the goal, we first collect a dataset, GroundingCap-1M, wherein each image is accompanied by associated grounding labels and an image-level detailed caption. With this dataset, we finetune an open-vocabulary detector with training objectives including a standard grounding loss and a caption generation loss. We take advantage of a large language model to generate both region-level short captions for each region of interest and image-level long captions for the whole image. Under the supervision of the large language model, the resulting detector, LLMDet, outperforms the baseline by a clear margin, enjoying superior open-vocabulary ability. Further, we show that the improved LLMDet can in turn build a stronger large multi-modal model, achieving mutual benefits. The code, model, and dataset is available at https://***/iSEE-laboratory/LLMDet. Copyright © 2025, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Overcoming Data Limitations and Cross-Modal Interaction Challenges in Medical Visual Question Answering

Overcoming Data Limitations and Cross-Modal Interaction Chal...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Yurun Bi Xingang Wang Qingao Wang Jinxiao Yang 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

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Medical Visual Question Answering (Med-VQA) is a sophisticated multimodal technology within the medical domain that utilizes natural language processing and artificial intelligence techniques. It serves as a tool in the medical field to provide information and answers, aiming to correctly respond to medical questions related to specific professional medical images. The primary goal is to assist patients in understanding their physical condition and provide decision support for healthcare professionals. While Generalized Visual Question Answering has seen significant advancements, challenges persist in the medical domain. Firstly, medical data has inherent limitations, such as the scarcity of annotated medical datasets and the complexity of medical images (including factors like noise, artifacts, and low contrast). Secondly, in terms of cross-modal fusion, there exists an intricate relationship between medical images and textual information. The complexity of the relationship between medical images and medical text, as well as the incorporation of global contextual details, pose challenges. To address these issues, this paper proposes the Feature-Enhanced network with Conditional Mixing. This innovative approach aims to overcome the scarcity and complexity of medical images without the need for additional datasets. Simultaneously, to tackle the challenge of cross-modal fusion and information interaction and to address the complex relationship between medical images and text, we propose the Cross-Adaptive Fusion network. Experimental results conducted on the VQA-RAD dataset demonstrate noticeable improvements in accuracy compared to mainstream Med-VQA models.

关键词： Visualization Accuracy Noise Neural networks Medical services Question answering (information retrieval) Data models

来源：评论

学校读者我要写书评

暂无评论

LESaET: Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER

LESaET: Low-Dimensional Embedding Method for Link Prediction...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Lichao Ding Jing Zhao Kai Lu Zenghao Hao 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

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Knowledge graphs (KGs) provide a structured representation of the real world through entity-relation triples. However, current KGs are often incomplete, typically containing only a small fraction of all possible facts. This involves inferring missing content from existing information, a task known as link prediction. Existing methods in the field of link prediction struggle with controlling the dimensionality of embedding vectors or suffer from overly complex models. In order to tackle these challenges, we introduce a method in this paper, named Low-Dimensional Embedding Method for Link Prediction Combining Self-Attention and Enhanced-TuckER (LESaET). LESaET leverages both self-attention mechanisms and tensor factorization to learn expressive contextual-enhanced representations of KGs. Specifically, LESaET employs the multi-head self-attention mechanism of Transformer as an encoder to capture the mutual information between entities and relationships, and utilizes Enhanced-TuckER as a decoder, ultimately achieving expressive low-dimensional embeddings for link prediction tasks. LESaET demonstrates competitive performance compared to advanced methods on standard datasets.

关键词： Tensors Stacking Knowledge graphs Predictive models Transformers Vectors Decoding Standards Mutual information Periodic structures

来源：评论

学校读者我要写书评

暂无评论

Continuous Verification of Catastrophic Recalling in Machine Unlearning via Adversarial Testing

Continuous Verification of Catastrophic Recalling in Machine...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Y. Neil Qu Zonghao Ji Lei Cui Chong Zhang Lei Liu Zhiyi Tian 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 Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China School of IT Deakin University VIC Australia Guangzhou Institute of Technology Xidian University Guangzhou China School of Computer Science University of Technology Sydney NSW Australia

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Throughout the process of machine unlearning, in order to fulfill the requirements of machine unlearning and to comply with the rules of the right to be forgotten, it is natural to verify whether the unlearning model actually removes data points. Therefore, machine unlearning verification plays a crucial role. However, existing validation methods only perform one validation, and it is still challenging to determine whether subsequent updates of the model still maintain the unlearning effect. To address this challenge, we propose a novel continuous verification of catastrophic recalling in machine unlearning framework that aims to continuously evaluate whether a machine learning model effectively forgets specified data after an update. In this work, we first introduce adversarial testing as a crucial part of the overall framework. Verification then continues as the unlearned model is updated (adding or continuing to forget data points). We also analyzed the possibility that learning new data after unlearning may diminish the effect. Overall, our continuous unlearning verification framework provides a proactive approach to protecting individual privacy in the machine learning domain, thus facilitating the generation of more robust unlearning algorithms.

关键词： Privacy Machine learning algorithms Cyberspace Machine learning Data science Data models Testing

来源：评论

学校读者我要写书评

暂无评论

A Semantic-based Replacement for Event Image Privacy 24

A Semantic-based Replacement for Event Image Privacy

引用

24th IEEE International Conference on Computational Science and Engineering, CSE 2021

作者： Chen, Zhenfei Tianqing, Zhu Tian, Bing Wang, Yu Ren, Wei China University of Geosciences School of Computer Science Wuhan China Institute of Artificial Intelligence and Blockchain Guangzhou University Guangzhou China China University of Geosciences Guangxi Key Laboratory of Cryptography and Information Security Key Laboratory of Network Assessment Technology CAS School of Computer Science Beijing China

ISBN: (纸本)9781665416603

Thanks to the continuous development of deep learning and the updating of deep neural networks, the accuracy of various computer vision tasks continue improving. On the one hand, the accuracy of image recognition is significantly improved. On the other hand, it also poses a higher challenge of image-based privacy preservation. Although traditional privacy protection methods such as cryptography methods can provide a good privacy protection, they are extremely inconvenient to use and cannot provide good image utility. In order to obtain a balance between image privacy and utility, we propose a privacy-preserving model based on image semantic replacement. We perform semantic replacement or obfuscation to multiple information. Taking the human figures as an example, the information includes faces, scenes, and dressing style. As that information contributes the most to the recognition, we define those items as the privacy of the original image. We replace the event information of the original image, so that the figures in the image can no longer be recognized. With this strategy, the image can still be detected by various detection networks, such as scene detection, which ensures utility. The framework consists of three parts: detection network, scene replacement network, and clothing replacement network. A comprehensive and quantitative experiment set proves the effectiveness of the proposed model. © 2021 IEEE.

关键词： Semantics

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：