检索结果-内蒙古大学图书馆

Heterogeneous Image Knowledge Driven Visual Perception

IEEE/CAA Journal of Automatica Sinica 2024年第1期11卷 255-257页

作者： Lan Yan Wenbo Zheng Fei-Yue Wang IEEE the College of Computer Science and Electronic Engineering Hunan UniversityChangsha 410082China the School of Computer Science and Artificial Intelligence Wuhan University of TechnologyWuhan 430070China the State Key Laboratory for Management and Control of Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China

Dear Editor,This letter is concerned with visual perception closely related to heterogeneous *** the huge challenge brought by different image modalities,we propose a visual perception framework based on heterogeneous image knowledge,i.e.,the domain knowledge associated with specific vision tasks,to better address the corresponding visual perception problems.

关键词： Visual visual knowledge

来源：评论

学校读者我要写书评

暂无评论

Improvement Methods for Medical Image Segmentation Based on Attention U-Net Networks 5

Improvement Methods for Medical Image Segmentation Based on ...

引用

5th International Seminar on artificial intelligence, Networking and Information technology, AINIT 2024

作者： Shen, Fengqiao Jiangnan University School of Artificial Intelligence and Computer Science Jiangsu Wuxi1191210 China

ISBN: (纸本)9798350385557

Deep learning techniques are widely employed in the medical field. Among these, the Attention If-Net, proposed in 2018, has garnered significant attention in medical image segmentation. This method combines the strengths of U -Net with attention mechanisms, substantially enhancing the recognition of key features and consequently improving the effectiveness of image segmentation. With the continuous advancement of medical image segmentation performance, many scholars have further refined and extended the structure of the Attention U-N et, including optimizations of the encoder-decoder and the introduction of external feature pyramids. Through research on medical image segmentation techniques based on the Attention U-N et structure, we introduce various attention mechanisms in this paper. We propose a novel network structure that incorporates mixed attention on top of Attention If-Net, which performs well in brain tumor segmentation tasks. © 2024 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Semantic-Based Detection of Ponzi Smart Contracts: Enhancing Bytecode Analysis with Source Code 4

Semantic-Based Detection of Ponzi Smart Contracts: Enhancing...

引用

4th International Conference on Electronic Information Engineering and computer technology, EIECT 2024

作者： Weng, Bingjie Ma, Jianhui University of Science and Technology of China Faculty of Artificial Intelligence and Data Science Anhui Hefei China University of Science and Technology of China Faculty of Computer Science and Technology Anhui Hefei China

ISBN: (纸本)9798331528850

The rapid development of blockchain technology has led to many innovations, with the widespread use of smart contracts being particularly notable. However, this trend has spawned diverse blockchain scams, including the Ponzi scheme, which takes the form of Ponzi contracts. Due to blockchain users' misunderstanding of blockchain transparency, this scam can often result in significant financial losses. To complicate matters further, the vast majority of smart contracts deployed on blockchain networks are not open source, and users can only see the contract's bytecode. This situation makes Ponzi contracts even more challenging to identify, making it difficult for users to judge the security and legitimacy of a contract beforehand, thus increasing the risk of being defrauded. Most existing work uses only bytecode for detection and cannot fully utilize the corresponding source code information. In this paper, we propose a novel bimodal learning-fusion framework for enhancing Ponzi contract detection only in the presence of bytecode. Firstly, we employ the semantic-aware neural network to extract semantic feature from source code and bytecode. Then, we propose a modal transformation strategy to learn the relationship between source code and bytecode. Finally, a modal attention mechanism is introduced to construct a fusion representation to detect the contract even in the absence of source code modality. Experimental results show that the method performs better than existing methods that use machine learning for detection of Ponzi contracts. © 2024 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Realtime Emotion Recognition from Images to Understand Facial Expressions

Realtime Emotion Recognition from Images to Understand Facia...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Shaik, Mohammed Ali Sahithi, Yamsani Nishitha, Mandala Reethika, Rekulapelli Teja, Kondabathula Sumanth Reddy, Chinthala Pradhyumn SR University School of Computer Science & Artificial Intelligence Telangana State Warangal India

ISBN: (纸本)9798350361537

Emotion recognition from images plays an important role in various industries, including healthcare, education and marketing, as well as in human-computer interactions. This paper aims to build a real-time emotion recognition system using deep learning to understand facial expressions and accurately infer emotional states. This system will use deep learning to extract features from facial images using Convolutional Neural Networks (CNNs). The results of this paper will help advance emotion recognition technologies and their applications in various industries, ultimately improving human-machine interactions and user experience. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

NLP-based Sentiment Analysis on Twitter using Machine Learning Approaches 2

NLP-based Sentiment Analysis on Twitter using Machine Learni...

引用

2nd International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2024

作者： Satyam, Yedlla Rajchandar, K. School of Computer Science and Artificial Intelligence SR University Hasanparthy Hanumakonda506371 India

ISBN: (纸本)9798331541217

Internet services are generating a huge number of data that is increasing significantly every day. The exchange of ideas and information has exponentially risen with the usage of social media. Web users share more details with their friends and spend most time on social media, and the information obtained from their chat has been used in various applications. Social networking platforms, such as Twitter, Facebook, and Google+ are becoming increasingly popular, enabling users to share opinions on various topics, engage in discussions with diverse communities, and post messages globally. Sentiment Analysis (SA) is applied to Twitter data set for identifying the emotions of users and based on these, several issues can be solved. Twitter is a microblogging site that provides a good environment for SA. Sentiment classification done on Twitter data classifies the emotions in the tweets as neutral, negative, or positive. In this survey, 25 research papers on SA are reviewed. The methods of SA on Twitter are classified as Deep Learning, supervised methods, Hybrid, and other methods. For a reliable evaluation, research papers on SA published between 2015 and 2023 are collected. Finally, the evaluation is achieved based on the datasets, publication year, performance metrics, programming languages, and category analysis. Also, the programming language widely used for execution is Python. © 2024 IEEE.

关键词： Machine learning Natural Language Processing Sentiment Analysis Sentiment classification Social media Text analysis Twitter

来源：评论

学校读者我要写书评

暂无评论

Phoneme-Level Feature Discrepancies: A Key to Detecting Sophisticated Speech Deepfakes 39

Phoneme-Level Feature Discrepancies: A Key to Detecting Soph...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Zhang, Kuiyuan Hua, Zhongyun Lan, Rushi Zhang, Yushu Guo, Yifang School of Computer Science and Technology Harbin Institute of Technology Shenzhen China School of Computer Science and Information Security Guilin University of Electronic Technology China School of Computing and Artificial Intelligence Jiangxi University of Finance and Economics China Alibaba Group China

ISBN: (纸本)157735897X

Recent advancements in text-to-speech and speech conversion technologies have enabled the creation of highly convincing synthetic speech. While these innovations offer numerous practical benefits, they also cause significant security challenges when maliciously misused. Therefore, there is an urgent need to detect these synthetic speech signals. Phoneme features provide a powerful speech representation for deepfake detection. However, previous phoneme-based detection approaches typically focused on specific phonemes, overlooking temporal inconsistencies across the entire phoneme sequence. In this paper, we develop a new mechanism for detecting speech deepfakes by identifying the inconsistencies of phoneme-level speech features. We design an adaptive phoneme pooling technique that extracts sample-specific phoneme-level features from frame-level speech data. By applying this technique to features extracted by pre-trained audio models on previously unseen deepfake datasets, we demonstrate that deepfake samples often exhibit phoneme-level inconsistencies when compared to genuine speech. To further enhance detection accuracy, we propose a deepfake detector that uses a graph attention network to model the temporal dependencies of phoneme-level features. Additionally, we introduce a random phoneme substitution augmentation technique to increase feature diversity during training. Extensive experiments on four benchmark datasets demonstrate the superior performance of our method over existing state-ofthe-art detection methods. © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Speech enhancement

来源：评论

学校读者我要写书评

暂无评论

CMDM: A Control Motion Diffusion Model for 2D Digital Human Motion Video Generation 7

CMDM: A Control Motion Diffusion Model for 2D Digital Human ...

引用

7th International Conference on Pattern Recognition and artificial intelligence, PRAI 2024

作者： Wu, Tong Zhao, Sirui Jin, Siyuan Xu, Tong Chen, Enhong School of Data Science University of Science and Technology of China Hefei China School of Computer Science and Technology University of Science and Technology of China Hefei China

ISBN: (纸本)9798350350890

In recent years, 2D digital human motion generation (DHMG) is becoming increasingly crucial for many areas such as virtual live broadcasting and film production. Although a lot of effort has been invested in DHMG, the complexity and diversity of human movements make it difficult to generate motions for arbitrary poses, and it is challenging to avoid distortion in the generated hand regions. To address these challenges, in this paper, we propose Control Motion Diffusion Model (CMDM), a diffusion based method for generating 2D digital human motion videos with arbitrary given poses. In CMDM, a novel Pose Control Module (PCM) is customized to fully encode pose and character information, generating multi-level and multi-resolution embedding, thereby ensuring that the model can learn more precise human motion features. In addition, data augmentation and VAE fine-tuning training strategies are adopted to decouple character and pose features, improving the model's ability to generate unseen poses. Finally, comprehensive experiments have been completed to demonstrate the effectiveness of the proposed method, and the proposed CMDM has achieved significant improvement in both subjective and objective evaluations. © 2024 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Supervised Satellite Image Retrieval using Defined Patterned with ASMC 2

Supervised Satellite Image Retrieval using Defined Patterned...

引用

2nd Edition of IEEE Delhi Section Owned Conference, DELCON 2023

作者： Gaikwad, Rohini Siddiqui, Rizwana Sies Graduate School of Technology Artificial Intelligence & Data Science Navi Mumbai India Sies Graduate School of Technology Computer Engineering Navi Mumbai India

ISBN: (纸本)9798350322064

It is suggested to use remotely sensed image retrieval with query-by-example approach. This often entails using query techniques that permit descriptive semantics, queries that incorporate user feedback, machine learning-capable systems, and systems that can gauge user satisfaction. This study uses the Advanced Split and Merge Clustering approach to extract features from the textures of similar grayscale images and the spectral distribution using two-dimensional Gabor functions. The resulting pattern will be the concatenation of texture features and Spectral Distribution (SD). Modified Earth Mover's Distance (EMD) is used to limit how much of each vector can be predefined in pieces. EMD technique for establishing center correspondence between the patterns uses interactive search. © 2023 IEEE.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

Quantum Algorithms and Lower Bounds for Finite-Sum Optimization 41

Quantum Algorithms and Lower Bounds for Finite-Sum Optimizat...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Zhang, Yexin Zhang, Chenyi Fang, Cong Wang, Liwei Li, Tongyang School of Electronics Engineering and Computer Science Peking University China Computer Science Department Stanford University United States National Key Lab of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Institute for Artificial Intelligence Peking University China Center on Frontiers of Computing Studies Peking University China School of Computer Science Peking University China

Finite-sum optimization has wide applications in machine learning, covering important problems such as support vector machines, regression, *** this paper, we initiate the study of solving finite-sum optimization problems by quantum ***, let f1, ..., fn : d → be -smooth convex functions and ψ: d → be a µ-strongly convex proximal *** goal is to find an ϵ-optimal point for F(x) = n1 Pni=1 fi(x) + ψ(x).We give a quantum algorithm with complexity Õ(Equation presented) 1 improving the classical tight bound (Equation presented).We also prove a quantum lower bound Ω˜(n + n3/4(/µ)1/4) when d is large *** our quantum upper and lower bounds can extend to the cases where ψ is not necessarily strongly convex, or each fi is Lipschitz but not necessarily *** addition, when F is nonconvex, our quantum algorithm can find_an ϵ-critial point using (Equation presented) queries. Copyright 2024 by the author(s)

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Enhancing Offensive Language Detection with data Augmentation and Knowledge Distillation

引用

Research 2024年第2期6卷 29-40页

作者： Jiawen Deng Zhuang Chen Hao Sun Zhexin Zhang Jincenzi Wu Satoshi Nakagawa Fuji Ren Minlie Huang The CoAl group DCSTInstitute for Artificial InteligenceState Key Lab of Intelligent Technology and SystemsBeijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Graduate School of Information Science&Technology The University of Tokyo.Tokyo 1138654Japan School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengduSichuan611731China

Offensive language detection has received important attention and plays a crucial role in promoting healthy communication on social platforms,as well as promoting the safe deployment of large language *** data is the basis for developing detectors;however,the available offense-related dataset in Chinese is severely limited in terms of data scale and coverage when compared to English *** significantly affects the accuracy of Chinese offensive language detectors in practical applications,especially when dealing with hard cases or out-of-domain *** alleviate the limitations posed by available datasets,we introduce AugCOLD(Augmented Chinese Offensive Language dataset),a large-scale unsupervised dataset containing 1 million samples gathered by data crawling and model ***,we employ a multiteacher distillation framework to enhance detection performance with unsupervised *** is,we build multiple teachers with publicly accessible datasets and use them to assign soft labels to *** soft labels serve as a bridge for knowledge to be distilled from both AugCOLD and multiteacher to the student network,i.e.,the final offensive *** conduct experiments on multiple public test sets and our well-designed hard tests,demonstrating that our proposal can effectively improve the generalization and robustness of the offensive language detector.

关键词： COLD dealing limitations

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：