检索结果-内蒙古大学图书馆

How far are we to GPT-4V?Closing the gap to commercial multimodal models with open-source suites

science China(Information sciences) 2024年第12期67卷 5-22页

作者： Zhe CHEN Weiyun WANG Hao TIAN Shenglong YE Zhangwei GAO Erfei CUI Wenwen TONG Kongzhi HU Jiapeng LUO Zheng MA Ji MA Jiaqi WANG Xiaoyi DONG Hang YAN Hewei GUO Conghui HE Botian SHI Zhenjiang JIN Chao XU Bin WANG Xingjian WEI Wei LI Wenjian ZHANG Bo ZHANG Pinlong CAI Licheng WEN Xiangchao YAN Min DOU Lewei LU Xizhou ZHU Tong LU Dahua LIN Yu QIAO Jifeng DAI Wenhai WANG State Key Laboratory for Novel Software Technology Nanjing University Shanghai AI Laboratory School of Computer Science Fudan University SenseTime Research Department of Information Engineering The Chinese University of Hong Kong Department of Electronic Engineering Tsinghua University

In this paper, we introduce InternVL 1.5, an open-source multimodal large language model(MLLM) to bridge the capability gap between open-source and proprietary commercial models in multimodal understanding. We introduce three simple improvements.(1) Strong vision encoder: we explored a continuous learning strategy for the large-scale vision foundation model — InternViT-6B, boosting its visual understanding capabilities, and making it can be transferred and reused in different LLMs.(2) Dynamic high-resolution: we divide images into tiles ranging from 1 to 40 of 448×448 pixels according to the aspect ratio and resolution of the input images, which supports up to 4K resolution input.(3) High-quality bilingual dataset: we carefully collected a high-quality bilingual dataset that covers common scenes, document images,and annotated them with English and Chinese question-answer pairs, significantly enhancing performance in optical character recognition(OCR) and Chinese-related tasks. We evaluate InternVL 1.5 through a series of benchmarks and comparative studies. Compared to both open-source and proprietary commercial models, InternVL 1.5 shows competitive performance, achieving state-of-the-art results in 8 of 18 multimodal benchmarks. Code and models are available at https://***/OpenGVLab/InternVL.

关键词： multimodal model open-source vision encoder dynamic resolution bilingual dataset

来源：评论

学校读者我要写书评

暂无评论

Cluster-Based Stable BSM Dissemination System for Safe Autonomous Platooning

引用

computers, Materials & Continua 2022年第4期71卷 321-338页

作者： Jaehwan Lee Suhwan Kwak Seungwoo Park Sangoh Park School of Computer Science and Engineering Chung-Ang UniversityDongjak-guSeoul06974Korea

Recently,the importance of vehicle safety supporting system has been highlighted as autonomous driving and platooning has attracted the *** ensure driving safety,each vehicle must broadcast a basic safety message(BSM)every 100 ***,stable BSM exchange is difficult because of the changing environment and limited bandwidth of vehicular wireless *** increasing number of vehicles on the road increases the competition to access wireless networks for BSM exchange;this increases the packet collision *** increased packet collision rate impairs the transmission and reception of BSM information,which can easily cause a traffic *** propose a solution,the vehicular safety support system(V3S),which exchanges BSMs reliably even when many vehicles are on the *** V3S uses a clustering scheme to decrease network traffic by reducing the amount of data exchanged between a vehicle and the roadside unit(RSU).In addition,the V3S reduces the collision rate of wireless network packets by broadcasting the vehicle’s BSM in an allocated timeslot using the time division multiple access(TDMA)MAC *** V3S also deals with insufficient bandwidth for dedicated short-range communications(DSRC)by changing DSRC channels according to traffic *** evaluating the packet error rate for stable BSM packet delivery,the V3S demonstrates an excellent packet error rate of less than 1%,compared to the 802.11p with its packet error rate of 82%.

关键词： Road vehicles communication systems clustering methods vehicular networks basic safety message dedicated short-range communication

来源：评论

学校读者我要写书评

暂无评论

Multiclass Classification of Insect Bites Using Deep Learning Techniques 3rd

Multiclass Classification of Insect Bites Using Deep Learnin...

引用

3rd International Conference on Machine Vision and Augmented Intelligence, MAI 2023

作者： Sushma, K.V.N.D. Pande, Sagar Dhanraj School of Computer Science and Engineering VIT-AP University Andhra Pradesh Amaravati India Pune India

ISBN: (纸本)9789819743582

Many people suffer due to insect bites every year and it may even be life-threatening sometimes. Insect bites and stings come in different shapes and sizes and itchy red colors, and it might be a difficult task to accurately identify which bite is caused by which insect. On different skin, it may be in different colors or textures. This task may be even challenging for researchers and doctors. Analysis of insect bites is crucial for treatment and disease prevention. Deep learning (DL) algorithms have demonstrated promising gains in a variety of image identification applications in recent years. To enable automatic identification and classification of insect species, this study explores the use of DL algorithms for multi-class classification of insect bites. The main purpose of the paper is to propose a model that classifies insect bites on human skin using deep learning algorithms aiming to classify the insect bites more accurately. This paper first tried to classify whether the given image is a skin or any type of object and received an accuracy of 95% using pre-trained inception-v3 and for insect bite classification a proposed VINMOBCONCAT (hybrid model) received an accuracy of 93%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Characterization of Exact One-Query Quantum Algorithms for Partial Boolean Functions

引用

Journal of computer science & Technology 2023年第6期38卷 1423-1430页

作者：叶泽坤李绿周 Institute of Quantum Computing and Computer Theory School of Computer Science and EngineeringSun Yat-sen UniversityGuangzhou 510006China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Sun Yat-sen UniversityGuangzhou 510006China

The query model(or black-box model)has attracted much attention from the communities of both classical and quantum ***,quantum advantages are revealed by presenting a quantum algorithm that has a better query complexity than its classical *** the history of quantum algorithms,the Deutsch algorithm and the Deutsch-Jozsa algorithm play a fundamental role and both are exact one-query quantum *** leads us to con-sider the problem:what functions can be computed by exact one-query quantum algorithms?This problem has been ad-dressed in the literature for total Boolean functions and symmetric partial Boolean functions,but is still open for general partial Boolean ***,in this paper,we continue to characterize the computational power of exact one-query quantum algorithms for general partial Boolean ***,we present several necessary and sufficient conditions for a partial Boolean function to be computed by exact one-query quantum ***,inspired by these conditions,we discover some new representative functions that can be computed by exact one-query quantum algorithms but have an essential difference from the already known ***,it is worth pointing out that before our work,the known func-tions that can be computed by exact one-query quantum algorithms are all symmetric functions and the quantum algo-rithm used is essentially the Deutsch-Jozsa algorithm,whereas the functions discovered in this paper are generally asym-metric and new algorithms to compute these functions are ***,this expands the class of functions that can be computed by exact one-query quantum algorithms.

关键词： quantum computing quantum query complexity quantum algorithm

来源：评论

学校读者我要写书评

暂无评论

Assessing Degradation Levels of Palm Leaf Manuscripts with Random Forest Using Gabor Features 8th

Assessing Degradation Levels of Palm Leaf Manuscripts with R...

引用

8th IFIP TC 12 International Conference on computer, Communication and Signal Processing, ICCCSP 2024

作者： Kowshik, Achyuta Siva Sai Sindhur, Ambati Sai Reddy, Annem Gnaneswara Ganesh, Manasa Sivan, Remya Pati, Peeta Basa Department of Computer Science and Engineering Amrita School of Computing Bengaluru Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9783031736162

This experiment focuses on employing machine learning techniques to create an automated system for classifying palm leaf manuscripts into three distinct categories based on their degradation levels: good, bad, and medium. The study collects a wide range of palm leaf samples at different degradation levels. Using advanced machine learning algorithms and an efficient feature extraction method, a model is created that accurately classifies palm leaves by level of degradation. The research incorporates Gabor feature extraction and statistical classifiers to train the extracted features. The classifiers used are k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), Multi-Layer Perceptron (MLP), Logistic Regression (LR), Random Forest (RF), Decision Tree (DT), Naive Bayes (NB), XG Boost (XGB), and Ada Boost (AB). After employing SMOTE, normalization, and feature selection, RF obtained the highest mean accuracy of 87.25% and a standard deviation of 0.08 in comparison with the other classifiers. © IFIP International Federation for Information Processing 2025.

关键词： Random forests

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Comparative Study of Artificial Neural Network (ANN) and Support Vector Machines (SVM) on Stock Forecasting

引用

Annals of Data science 2023年第1期10卷 183-208页

作者： Kurani, Akshit Doshi, Pavan Vakharia, Aarya Shah, Manan Department of Computer Engineering Indus University Gujarat Ahmedabad India Department of Computer Science and Engineering Indus University Gujarat Ahmedabad India Department of Chemical Engineering School of Technology Pandit Deendayal Petroleum University Gujarat Gandhinagar382007 India

From exchanging budgetary instruments to tracking individual spending plans to detail a business's profit, money-related organisations utilise computational innovation day by day. Here in this paper, we focus on the significance of innovation in accounts such as financial risk management and stock prediction. We discuss two significant algorithms that have a notable role in stock forecasting. Artificial Neural Networks (ANN), as absenteeism of some data points, does not hamper the network functioning. Secondly, Support Vector Machines (SVM) has several features, and due to simple decision boundaries, it avoids over-fitting. The paper first looks at the different technologies applied in stock market prediction. It examines how sentimental analysis, decision trees, moving average algorithm, and data mining is applied in various stock prediction scenarios. The paper covers the recent past studies to explore the concepts and methodologies through which ANN's and SVM's have been used. Additionally, the paper incorporates significant aspects of novel methods and technologies in which ANN as a hybrid model like ANN-MLP, GARCH-MLP, a combination of the Backpropagation algorithm and Multilayer Feed-forward network, yields better results. Simultaneously, SVM's have been successfully applied in stock prediction, giving an accuracy of about 60%–70% for simple SVM, which is further improved by combining methods like Random Forest, Genetic Algorithm more accurate outcomes. Further, we present our thoughts on where SVM's and ANN's stand as prediction algorithms and challenges like the time constraint, current scenarios, data limitation, and cold start problems were raised. Conclusively SVM and ANN played prominent roles in tackling these issue to an extent and can further be enhanced with their integration with other novel techniques resulting in hybrid methodologies. It will lead students, researchers and financial enthusiasts to more potent approaches for Stock forecasting. © 20

关键词： Machine learning ANN SVM Artificial neural network Support-vector machine Decision tree Backpropagation Stock market Autoregressive conditional heteroskedasticity Neural network Data mining

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive End-to-End Solution for Web Security with Cryptography, Multi-Factor Authentication, and Secure Communication 3

A Comprehensive End-to-End Solution for Web Security with Cr...

引用

3rd International Conference on Intelligent Data Communication Technologies and Internet of Things, IDCIoT 2025

作者： Kumar, Kanderi Johith Sai, Kandlapalli Aravind Reddy, Adapala Dharshan Reddy, Chinthamreddy Pranay Daiwik Rajagopal, Shinu M. Dept. of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9798331527549

In today’s digital landscape, securing sensitive information has become an essential priority in the modern digital era for both individuals and organizations. This project introduces a comprehensive web application that integrates advanced encryption and decryption functionalities alongside multifactor authentication (MFA) and secure payment processing. The application supports various cryptographic algorithms, including AES, DES, Triple DES, Blowfish, etc., allowing users to securely encrypt and decrypt data through dedicated routes accessed over secure HTTPS connections. To further enhance security, robust multifactor authentication mechanisms, such as OTP-based challenge-response and QR-code-enabled 2FA, have been implemented to prevent unauthorized access to sensitive operations. The platform also incorporates PGP encryption powered by Keybase, enabling users to securely exchange encrypted emails. Additionally, a secure payment gateway is integrated using Stripe, ensuring sensitive payment data is encrypted and handled safely. With a strong focus on data integrity, user privacy, and modern web security standards, this project delivers an all-encompassing solution for safeguarding sensitive information and facilitating secure communication. By addressing common vulnerabilities and security risks, the platform stands as a reliable and scalable tool for data protection. © 2025 IEEE.

关键词： Authentication Protocol

来源：评论

学校读者我要写书评

暂无评论

SamPar: A Marathi Hate Speech Dataset for Homophobia, Transphobia 2nd

SamPar: A Marathi Hate Speech Dataset for Homophobia, Trans...

引用

2nd International Conference on Speech and Language Technologies for Low-Resource Languages, SPELLL 2023

作者： Chhaya, Bhargav Kumaresan, Prasanna Kumar Ponnusamy, Rahul Chakravarthi, Bharathi Raja School of Computer Science University of Galway Galway Ireland College of Science and Engineering University of Galway Galway Ireland

ISBN: (纸本)9783031584947

Marathi-speaking communities, especially those experiencing a change of heart after Article 377 was repealed in India, have expressed their sentiments regarding the LGBTQ+ community on social media. Leveraging a meticulously curated dataset extracted from prominent social media platforms, YouTube and Facebook, the study unveils the social, cultural, and moral perspectives palpable across both urban and rural domains. The data, derived via a rigorous manual scraping methodology, was categorized into ‘Homophobic’, ‘Non-LGBTQ+’, and ‘Transphobic’ comments, attaining a commendable Cohen’s Kappa score of 0.967, thus reflecting a high inter-annotator agreement. Our exploitative analysis unveiled a stark presence of homophobic (15.84%) and transphobic (10.52%) remarks within the digital discussions. Employing an array of machine learning and deep learning models, with a particular spotlight on Decision Trees and LSTM which achieved macro F1-scores of 0.45 and 0.53 respectively, the study not only elevates the understanding of the sociolinguistic intricacies prevalent in digital dialogues but also lays a substantive foundation for future research. It assists in understanding and potentially curtailing digital hate speech and discriminatory remarks against the LGBTQ+ community in the Marathi digital diaspora. Thus, the paper propels the conversation towards crafting a more inclusive, empathetic, and supportive digital environment, synchronizing technological prowess with socio-cultural cognizance. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A Secure and Efficient Framework for Multi-Round Data Trading Over the Internet of Artificially Intelligent Things

引用

IEEE Internet of Things Magazine 2022年第1期5卷 119-124页

作者： Zheng, Xu Zhang, Lizong Hui, Bei Tian, Ling Cai, Zhipeng School of Computer Science and Engineering University of Electronic Science and Technology of China China School of Information and Software Engineering University of Electronic Science and Technology of China China Georgia State University Department of Computer Science United States

IoT data trading has greatly benefited the popularization of both the Internet of Things (IoT) and Artificial Intelligence of Things (AIoT). Current solutions mainly treat the dataset owned by each device as a commodity and focus on maintaining a data market. Meanwhile, inspired by recent achievements in distributed machine learning and federated learning, AIoT can actually realize its services by retaining the data locally on devices and only exchanging model parameters. However, existing IoT data trading methods fail to meet this secure and efficient process. Therefore, this article proposes a novel framework for data trading over AIoT. It allows the service provider to trade on deep learning model training instead of purchasing the full datasets. Key factors for the security issues and data pricing are addressed for the framework, including the design of the learning parameters and the comprehensive privacy concerns. Then a novel data trading strategy is proposed for the service provider to jointly maintain the model performance and the budget consumption. Evaluation results reveal the improvements on the model performance. Finally, some open problems in the design of data trading in AIoTs are discussed. © 2018 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Classifying Lung Cancer Disease Using Random Forest Algorithm 4

Classifying Lung Cancer Disease Using Random Forest Algorith...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Madaan, Vijay Sharma, Neha Chauhan, Rahul Joshi, Kireet Kumar, Bura Vijay Sunil, G. Chitkara University Institute of Engineering & Technology Chitkara University Punjab Rajpura India Graphic Era Deemed to Be University Computer Science & Engineering Uttarakhand Dehradun India Sr University School of Computer Science and Artificial Intelligence Warangal India Sr University School of Computer Science & Artificial Intelligence Warangal India

ISBN: (纸本)9798350307757

Through the use of a Random Forest Classifier and the utilization of a varied dataset, this research presents a machine learning model that is targeted at the early diagnosis of lung cancer. An outstanding overall accuracy of 97% is shown by the model, which demonstrates its capacity to properly identify between those who have lung cancer and those who do not have lung cancer. Underscoring the model's skill in limiting false positives and assuring exact identification of positive cases, precision measures suggest a significant accuracy of 0.98 for Class 1 (Lung Cancer). This demonstrates the model's ability to effectively identify positive instances. To provide a complete approach, the model takes into account important characteristics such as age, smoking status, and anxiety levels. The high recall of 0.99 for Class 1 indicates that the model is efficient in catching the majority of lung cancer cases, which is essential for administering timely therapies. This study contributes to the current improvements in healthcare by offering a viable tool for the early diagnosis of lung cancer and perhaps improving the results for patients. © 2024 IEEE.

关键词： Diseases

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：