检索结果-内蒙古大学图书馆

3rd International Conference on Electronic Information engineering and computer Communication, EIECC 2023

作者： Zheng, Qinan Xu, Huahu Bian, Minjie School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Data Group Co. Ltd Shanghai China

ISBN: (纸本)9798350359961

Numerous studies have demonstrated the Swin Transformer performs well in image super-resolution tasks. However, Swin Transformer typically divides the input image into fixed size blocks (such as 48x48) and independently processes each block, causing it to overlook a wider area. Furthermore, many deep learning super-resolution technologies face the challenge of computationally intensive operations. To address these issues, we propose a new NSTSR model consisting of four parts: data preprocessing layer, primary feature extraction layer, advanced feature extraction layer, and image generation layer. The advanced feature extraction layer consists of multiple STNBs (Swin Transformer N-segment blocks). We have introduced a technique called N-Segments, which applies the N-Gram contextual method for natural language processing tasks to low-level visual tasks. In our work, N-Segments refers to neighboring local windows in Swin, distinct from the traditional text analysis definition where N-Segments represents a continuous picture segment. Leveraging sliding-WSA, the N-Segments interact with each other, enabling the expansion of the regions seen to restore degraded pixels effectively. The experimental results demonstrate that the NSTSR model exhibits excellent performance compared to existing advanced methods while maintaining the computational efficiency structure. © 2023 IEEE.

关键词： component data Augmentation Image Super-resolution N-Segments Swin Transformer

来源：评论

学校读者我要写书评

暂无评论

CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for Multimodal Large Language Models

CONSTRUCTURE: Benchmarking CONcept STRUCTUre REasoning for M...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Zha, Zhiwei Zhu, Xiangru Xu, Yuanyi Huang, Chenghua Liu, Jingping Li, Zhixu Wang, Xuwu Xiao, Yanghua Yang, Bei Xu, XiaoXiao Shanghai Key Laboratory of Data Science School of Computer Science Fudan University China School of Information Science and Engineering East China University of Science and Technology China Alibaba Group China School of Information Renmin University of China China Renmin University of China China

ISBN: (纸本)9798891761681

Multimodal Large Language Models (MLLMs) have shown promising results in various tasks, but their ability to perceive the visual world with deep, hierarchical understanding similar to humans remains uncertain. To address this gap, we introduce CONSTRUCTURE, a novel concept-level benchmark to assess MLLMs' hierarchical concept understanding and reasoning abilities. Our goal is to evaluate MLLMs across four key aspects: 1) Understanding atomic concepts at different levels of abstraction;2) Performing upward abstraction reasoning across concepts;3) Achieving downward concretization reasoning across concepts;and 4) Conducting multi-hop reasoning between sibling or common ancestor concepts. Our findings indicate that even state-of-the-art multimodal models struggle with concept structure reasoning (e.g., GPT-4o averages a score of 62.1%). We summarize key findings of MLLMs in concept structure reasoning evaluation. Morever, we provide key insights from experiments using CoT prompting and fine-tuning to enhance their abilities. © 2024 Association for Computational Linguistics.

关键词： Abstracting

来源：评论

学校读者我要写书评

暂无评论

Detecting the One-Shot Dummy Attack on the Power Industrial Control Processes With an Unsupervised data-Driven Approach

引用

IEEE/CAA Journal of Automatica Sinica 2023年第2期10卷 550-553页

作者： Zhenyong Zhang Yan Qin Jingpei Wang Hui Li Ruilong Deng the State Key Laboratory of Public Big Data and the College of Computer Science and Technology Guizhou UniversityGuiyang 550025China the School of Chemical and Biomedical Engineering Nanyang Technological UniversitySingapore 639798Singapore the State Key Laboratory of Industrial Control Technology and the College of Control Science and Engineering Zhejiang UniversityHangzhou 310027China IEEE

Dear Editor,Dummy attack(DA), a deep stealthy but impactful data integrity attack on power industrial control processes, is recently recognized as hiding the corrupted measurements in normal measurements. In this letter, targeting a more practical case, we aim to detect the oneshot DA, with the purpose of revealing the DA once it is ***, we first formulate an optimization problem to generate one-shot DAs. Then, an unsupervised data-driven approach based on a modified local outlier factor(MLOF) is proposed to detect them.

关键词： Dummy Power letter

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Challenges of E-government Models of Cloud Computing in Developing Countries 18

Machine Learning Challenges of E-government Models of Cloud ...

引用

18th INDIAcom;11th International Conference on Computing for Sustainable Global Development, INDIACom 2024

作者： Tamilarasi, R. Kumar, P. N. Santhosh Ghantasala, G. S. Pradeep Rao, D. Nageswara Bathla, Priyanka Gupta, Gaurav Sonia Alliance University Department of Computer Science and Engineering Bengaluru India Hyderabad India Alliance University Department of Computer Science and Engineering Bangalore India Chandigarh University Punjab India Shoolini University Solan India Shoolini University Yogananda School of AI Computer and Data Sciences Solan India

ISBN: (纸本)9789380544519

Cloud computing usage in electronic government (e-government) is developing across nations and presents a range of difficulties. Infrastructure problems, such as unreliable internet connections and insufficient devices, make it difficult to integrate cloud solutions efficiently. Concerns about data security and privacy arise when private information about citizens is stored in the cloud and could be hacked or accessed without permission. Economic limits and resource constraints could prevent cloud infrastructure installation, thereby reducing e-government service scalability and efficiency. Compliance with various regulations adds complexity to the legal and governmental aspects of managing cloud data. A scientific investigation reveals that while cloud computing-driven e-government services offer numerous advantages, factors such as IT infrastructure, internet accessibility, and confidence in emerging technologies could pose barriers to their adoption. Also, recommend trust-focused cloud computing solutions for e-government services (CCSE-GS). Finally, this study focuses on the number of obstacles that developing countries must overcome to fully realize the potential of cloud computing for e-government services. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： Challenges about e-government Cloud Computing E-Government models IT infrastructure

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Semantic Type Identification for Relational Attributes

引用

Journal of computer science & Technology 2023年第4期38卷 927-946页

作者：丁玥郭雨荷卢卫李海翔张美慧李晖潘安群杜小勇 Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education Renmin University of China Beijing 100872China School of Information Renmin University of ChinaBeijing 100872China Tencent(Beijing)Technology Company Limited Beijing 100080China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Computer Science and Technology Guizhou UniversityGuiyang 550025China Tencent(Shenzhen)Technology Company Limited Shenzhen 518057China

Identifying semantic types for attributes in relations,known as attribute semantic type(AST)identification,plays an important role in many data analysis tasks,such as data cleaning,schema matching,and keyword search in ***,due to a lack of unified naming standards across prevalent information systems(*** islands),AST identification still remains as an open *** tackle this problem,we propose a context-aware method to figure out the ASTs for relations in this *** transform the AST identification into a multi-class classification problem and propose a schema context aware(SCA)model to learn the representation from a collection of relations associated with attribute values and schema *** on the learned representation,we predict the AST for a given attribute from an underlying relation,wherein the predicted AST is mapped to one of the labeled *** improve the performance for AST identification,especially for the case that the predicted semantic types of attributes are not included in the labeled ASTs,we then introduce knowledge base embeddings(***)to enhance the above representation and construct a schema context aware model with knowledge base enhanced(SCA-KB)to get a stable and robust *** experiments based on real datasets demonstrate that our context-aware method outperforms the state-of-the-art approaches by a large margin,up to 6.14%and 25.17%in terms of macro average F1 score,and up to 0.28%and 9.56%in terms of weighted F1 score over high-quality and low-quality datasets respectively.

关键词： attribute semantic type(AST)identification context-aware semantic embedding knowledge base embedding

来源：评论

学校读者我要写书评

暂无评论

Towards Safer Roads: A Comprehensive Review of Object Detection Techniques for Autonomous Vehicles

引用

SN computer science 2025年第5期6卷 1-20页

作者： Parisapogu, Samson Anosh Babu Narla, Nitya Juryala, Aarthi Ramavath, Siddhu Department of Computer Science and Engineering School of Computing Amrita Vishwa Vidyapeetham Amaravati Campus Andhra Pradesh Amaravati 522 503 India Department of Artificial Intelligence and Data Science Chaitanya Bharathi Institute of Technology Hyderabad 500075 India

Nowadays, people spend a lot of time in travel, and road safety has become an important area of research. As a result, self-driving cars have been gaining popularity in recent years because they have a lot of benefits in terms of reducing traffic congestion and improving road safety, thereby reducing accidents. They also have an environmental benefit as they reduce travel times and hence reduce the usage of fuel. Though a lot of research has already been done in this field, there are always new problems being created and new solutions being found. Apart from self-driving cars, automated navigation also has a huge number of applications. Therefore, it is important to stay up to date about the latest developments in this field. This research is a comprehensive survey that explores and evaluates the different object-detecting algorithms that have been used throughout the years, their advantages, disadvantages, and trade-offs. It also analyses the datasets and benchmarks that have been used for evaluating the models. It aims to identify the gaps in research in this growing field so that it can act as a roadmap for researchers to focus their study on. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Deep learning Object detection Road safety Self-driving YOLO

来源：评论

学校读者我要写书评

暂无评论

A Case Study on Context-Aware Neural Machine Translation with Multi-Task Learning 25

A Case Study on Context-Aware Neural Machine Translation wit...

引用

25th Annual Conference of the European Association for Machine Translation, EAMT 2024

作者： Appicharla, Ramakrishna Gain, Baban Pal, Santanu Ekbal, Asif Bhattacharyya, Pushpak Department of Computer Science and Engineering Indian Institute of Technology Patna India Wipro AI Lab45 London United Kingdom School of AI and Data Science Indian Institute of Technology Jodhpur India Department of Computer Science and Engineering Indian Institute of Technology Bombay India

ISBN: (纸本)9781068690709

In document-level neural machine translation (DocNMT), multi-encoder approaches are common in encoding context and source sentences. Recent studies (Li et al., 2020) have shown that the context encoder generates noise and makes the model robust to the choice of context. This paper further investigates this observation by explicitly modelling context encoding through multi-task learning (MTL) to make the model sensitive to the choice of context. We conduct experiments on cascade MTL architecture, which consists of one encoder and two decoders. Generation of the source from the context is considered an auxiliary task, and generation of the target from the source is the main task. We experimented with German-English language pairs on News, TED, and Europarl corpora. Evaluation results show that the proposed MTL approach performs better than concatenation-based and multi-encoder DocNMT models in low-resource settings and is sensitive to the choice of context. However, we observe that the MTL models are failing to generate the source from the context. These observations align with the previous studies, and this might suggest that the available document-level parallel corpora are not context-aware, and a robust sentence-level model can outperform the context-aware models. © 2024 The authors, © 2024 European Association for Machine Translation.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

BATON: symphony of random testing and concolic testing through machine learning and taint analysis

引用

science China(Information sciences) 2023年第3期66卷 97-117页

作者： Bihuan CHEN Yang LIU Xin PENG Yijian WU Shengchao QIN School of Computer Science Fudan University Shanghai Key Laboratory of Data Science Fudan University School of Computer Science and Engineering Nanyang Technological University School of Computing Teesside University

Random testing is scalable but often fails to hit corner program behaviors,while systematic testing （e.g.,concolic execution） is promising to cover corner program behaviors but is not scalable to explore all program *** attempts to integrate random testing with systematic testing lack targeted *** this paper,we propose a guided hybrid testing approach,named BATON,to synergize random testing with concolic *** integrates the knowledge inside test cases and their executions into a conditional execution graph,and uses such knowledge to guide test case ***,we learn classification models for some conditionals in the conditional execution graph in a demand-driven *** models are used to guide random testing to reach and cover partially-covered *** further employ targeted concolic testing to cover conditionals that cannot be fully covered by guided random *** implemented BATONfor Java and evaluated it on three *** results show that BATONimproved branch coverage and mutation score over random testing by 16.2%–29.4%and 19.0%–30.0%,over adaptive random testing by 16.8%–33.8%and 19.4%–34.2%,over concolic testing by 2.3%–29.9%and 2.9%–30.1%,and over simple hybrid testing by 1.6%–14.5%and 1.4%–18.7%.

关键词： system testing random testing concolic testing

来源：评论

学校读者我要写书评

暂无评论

Fusing Image and Text Features for Scene Sentiment Analysis Using Whale-Honey Badger Optimization Algorithm (WHBOA) 27th

Fusing Image and Text Features for Scene Sentiment Analysi...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Yadav, Prem Shanker Tyagi, Dinesh Kumar Vipparthi, Santosh Kumar Department of Computer Science and Engineering Malaviya National Institute of Technology Rajasthan Jaipur302017 India School of Artificial Intelligence and Data Engineering Indian Institute of Technology Ropar Punjab Rupnagar140001 India

ISBN: (纸本)9783031781650

Developing a real-time sentiment analysis application that relies solely on features extracted from images or textual content falls short of capturing human emotions’ nuanced and multifaceted nature. The unlabeled dataset, though useful, has limitations for sentiment analysis due to its general image descriptions, which lack emotional depth and do not include direct sentiment labels. Finding scene sentiment is a challenging task. To address this, combining textual descriptions with visual features is crucial. Important parameters include entropy, bag of words, and parts of speech (nouns, adjectives, and verbs) for textual analysis, alongside visual features like SIFT, SURF, and color histograms. These features are integrated to capture a comprehensive range of sentiment cues, enhancing the accuracy and depth of sentiment insights. This paper proposes an optimized adaptive neuro-fuzzy inference system for a compelling feature enhancement using the Whale-Honey Badger Optimization Algorithm (WHBOA). The proposed method identifies the most relevant and effective features from both textual and visual data. It captures visual-specific attributes to provide a richer and more detailed representation of visual content, addressing the limitations of general image descriptions and paving the way for the development of predictive models. Additionally, text pre-processing cleans and normalizes the textual data. We conducted an extensive comparative performance evaluation to assess the effectiveness and accuracy of the proposed model. The model is compared with the Nearest Neighbor, Support Vector Machine (SVM), and Decision Tree classification algorithms for the performance *** results demonstrate that the optimized model performs better, achieving an accuracy of approximately 91.2%, compared to the other models. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Predicting Protein-Protein Interactions Using Self-Attention-Based Deep Neural Networks and FastText Embeddings 15

Predicting Protein-Protein Interactions Using Self-Attention...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Oviya, I.R. Shanmukha Sravya, N. Raja, Kalpana Amrita Vishwa Vidyapeetham Amrita School Of Computing Department of Computer Science Engineering Chennai601103 India Yale University Section for Biomedical Informatics and Data Science School of Medicine New HavenCT United States

ISBN: (纸本)9798350370249

Predicting Protein-protein interactions are central to understanding the intricate mechanisms governing cellular functions, as proteins seldom act in isolation. While current machine learning and deep learning models focus on encoding protein sequences based on residue composition or physicochemical properties, they often overlook the complex relationships between amino acid segments within lengthy sequences. To address these limitations, we propose a novel hybrid model that combines a self-attention to enhance Deep neural network feature extraction with an with FastText Protein embeddings for predicting PPI. Utilizing transfer learning via the unsupervised FastText embedding technique to derive statistical representations of protein sequences, offers advantages over traditional protein encoding techniques in the context of analysing k-Mer sequences. Our model's performance is assessed through 5-fold cross-validation on datasets of *** and Human-Bacillus Anthracis protein interactions, resulting in accuracies of 92.28% and 94.08%, respectively. Compared to existing machine learning models, our model demonstrates superior performance on both datasets. © 2024 IEEE.

关键词： Adversarial machine learning

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：