检索结果-内蒙古大学图书馆

International Conference on Innovations in Information Technology

作者： Abdelhadi Hireche Rafat Damseh Parikshat Sirpal Abdelkader Nasreddine Belkacem Department of Computer and Network Engineering College of Information Technology United Arab Emirates University United Arab Emirates Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates School of Electrical and Computer Engineering Gallogly College of Engineering University of Oklahoma United States of America

Epilepsy is a prevalent neurological disorder and has been studied through the analysis of Electroencephalogram (EEG) signals. However, the identification and classification of epileptic seizure patterns remains challenging due to the non-stationary nature of EEG signals and the presence of artifacts. In this paper, we investigate the applicability of a transformer-based deep learning model to classify seizure patterns observed in epileptic patients. We employed the self-attention mechanism inherent in transformers to capture complex temporal relationships in the EEG recordings. By prepossessing the EEG signals into suitable input sequences and adapting the transformer architecture, we achieved 78.11% in distinguishing between different epileptic seizure patterns. Our findings indicate that the transformer model, with its ability to manage long-range dependencies, offers a robust approach to EEG-based seizure pattern classification. This work is important for building advanced automated diagnostic tools for epilepsy and related neurological disorders.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Lane marking detection algorithm based on high-precision map and multisensor fusion

Lane marking detection algorithm based on high-precision map...

引用

作者： Yao, Haichang Chen, Chen Liu, Shangdong Li, Kui Ji, Yimu Huang, Guangyan Wang, Ruchuan School of Computer Science Nanjing University of Posts and Telecommunications Nanjing China School of Computer and Software Nanjing Institute of Industry Technology Nanjing China Industrial Software Engineering Technology Research and Development Center of Jiangsu Education Department Nanjing Institute of Industry Technology Nanjing China Jiangsu HPC and Intelligent Processing Engineer Research Center Nanjing China Institute of High Performance Computing and Bigdata Nanjing University of Posts and Telecommunications Nanjing China School of Information Technology Deakin University Melbourne Australia

In case of sharp road illumination changes, bad weather such as rain, snow or fog, wear or missing of the lane marking, the reflective water stain on the road surface, the shadow obstruction of the tree, and mixed lane markings and other signs, missing detection or wrong detection will occur for the traditional lane marking detection algorithm. In this manuscript, a lane marking detection algorithm based on high-precision map and multisensor fusion is proposed. The basic principle of the algorithm is to use the centimeter-level high-precision positioning combined with high-precision map data to complete the detection of lane markings. In the process of generating high-precision maps or in the uncovered areas of high-precision maps, LIDAR (LIght Detection And Ranging) is used to estimate the curvature of the road to assist in lane marking detection. The experimental results show that the algorithm has lower false detection rate in case of bad road conditions, and the algorithm is robust. © 2020 John Wiley & Sons, Ltd.

关键词： Roads and streets

来源：评论

学校读者我要写书评

暂无评论

Mamba-Sea: A Mamba-based Framework with Global-to-Local Sequence Augmentation for Generalizable Medical Image Segmentation

arXiv

引用

arXiv 2025年

作者： Cheng, Zihan Guo, Jintao Zhang, Jian Qi, Lei Zhou, Luping Shi, Yinghuan Gao, Yang Shanghai Jiao Tong University School of Medicine Shanghai200025 China National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing210093 China State Key Laboratory for Novel Software Technology the National Institute of Healthcare Data Science Nanjing University Jiangsu Nanjing210093 China School of Computer Science and Engineering Key Lab of Computer Network and Information Integration Southeast University Jiangsu Nanjing211189 China School of Electrical and Information Engineering The University of Sydney SydneyNSW2006 Australia

To segment medical images with distribution shifts, domain generalization (DG) has emerged as a promising setting to train models on source domains that can generalize to unseen target domains. Existing DG methods are mainly based on CNN or ViT architectures. Recently, advanced state space models, represented by Mamba, have shown promising results in various supervised medical image segmentation. The success of Mamba is primarily owing to its ability to capture long-range dependencies while keeping linear complexity with input sequence length, making it a promising alternative to CNNs and ViTs. Inspired by the success, in the paper, we explore the potential of the Mamba architecture to address distribution shifts in DG for medical image segmentation. Specifically, we propose a novel Mamba-based framework, Mamba-Sea, incorporating global-to-local sequence augmentation to improve the model’s generalizability under domain shift issues. Our Mamba-Sea introduces a global augmentation mechanism designed to simulate potential variations in appearance across different sites, aiming to suppress the model’s learning of domain-specific information. At the local level, we propose a sequence-wise augmentation along input sequences, which perturbs the style of tokens within random continuous sub-sequences by modeling and resampling style statistics associated with domain shifts. To our best knowledge, Mamba-Sea is the first work to explore the generalization of Mamba for medical image segmentation, providing an advanced and promising Mamba-based architecture with strong robustness to domain shifts. Remarkably, our proposed method is the first to surpass a Dice coefficient of 90% on the Prostate dataset, which exceeds previous SOTA of 88.61%. The code is available at https://***/orange-czh/Mamba-Sea. Copyright © 2025, The Authors. All rights reserved.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Collaborative Three-Stream Transformers for Video Captioning

arXiv

引用

arXiv 2023年

作者： Wang, Hao Zhang, Libo Fan, Heng Luo, Tiejian School of Computer Science and Technology University of Chinese Academy of Sciences Beijing101408 China Institute of Software Chinese Academy of Sciences Beijing100190 China Department of Computer Science and Engineering University of North Texas DentonTX76203 United States

As the most critical components in a sentence, subject, predicate and object require special attention in the video captioning task. To implement this idea, we design a novel framework, named COllaborative three-Stream Transformers (COST), to model the three parts separately and complement each other for better representation. Specifically, COST is formed by three branches of transformers to exploit the visual-linguistic interactions of different granularities in spatial-temporal domain between videos and text, detected objects and text, and actions and text. Meanwhile, we propose a cross-granularity attention module to align the interactions modeled by the three branches of transformers, then the three branches of transformers can support each other to exploit the most discriminative semantic information of different granularities for accurate predictions of captions. The whole model is trained in an end-to-end fashion. Extensive experiments conducted on three large-scale challenging datasets, i.e., YouCookII, ActivityNet Captions and MSVD, demonstrate that the proposed method performs favorably against the state-of-the-art methods. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Model Based on Pretraining Method and Enhanced Subgraph Reconstruction

PNESR-DDI: An Effective Drug-Drug Interaction Prediction Mod...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Ke Chen Xiaosong Han Xiaoran Li Yanchun Liang Dong Xu Renchu Guan Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Software Jilin University Changchun China Key Laboratory for Symbol Computation and Knowledge Engineering of National Education Ministry College of Computer Science and Technology Jilin University Changchun China Zhuhai Laboratory of Key Laboratory of Symbol Computation and Knowledge Engineering of Ministry of Education School of Computer Science Zhuhai College of Science and Technology Zhuhai China Department of Electrical Engineering and Computer Science Christopher S. Bond Life Sciences Center University of Missouri Columbia USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Drug-Drug Interaction (DDI) task plays a crucial role in clinical treatment and drug development. Recently, deep learning methods have been successfully applied for DDI prediction. However, training deep learning models always need large amount of data, while known DDIs are scarce. To address this challenge, a graph neural network-based DDI prediction model named PNESR-DDI is proposed, which compensates for the lack of DDIs by enriching drug representations. First, to obtain initial node representations that incorporate rich semantic information from the biomedical knowledge graph (KG), a link prediction pre-training method on external KG is proposed in the node embedding pre-training module. Then, considering the large scale of the KG, subgraph extraction for the target drug pairs is introduced to reduce noise and decrease computational complexity in the subgraph anchoring module. After that, the subgraph is updated, and node similarities are propagated in the subgraph reconstruction module. Based on the node similarity scores, the subgraph is pruned and reconstructed, which adjusts node representations to be more conducive to DDI prediction. Finally, the drug embeddings, subgraph representations, and drug fingerprint features are concatenated to predict DDIs. PNESRDDI is evaluated on two benchmark DDI datasets: DrugBank and TWOSIDES. Experiment results show that PNESR-DDI achieves better performance than baselines. Ablation results validate the effectiveness of the pre-training method and the adaptive subgraph reconstruction strategy.

关键词： Drugs Deep learning Adaptation models Visualization Biological system modeling Noise Knowledge graphs Predictive models Fingerprint recognition Transformers

来源：评论

学校读者我要写书评

暂无评论

StyleAU: StyleGAN based Facial Action Unit Manipulation for Expression Editing

StyleAU: StyleGAN based Facial Action Unit Manipulation for ...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yanliang Guo Xianxu Hou Feng Liu Linlin Shen Lei Wang Zhen Wang Peng Liu Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Qualcomm Technologies Inc

Facial expression editing has a wide range of applications, such as emotion detection, human-computer interaction, and social entertainment. However, existing expression editing methods either fail to allow for fine-grained editing, resulting in unnatural and unrealistic facial expressions, or generate artifacts and blurs, leading to poor image quality. In this paper, we propose a novel framework called StyleAU, which is based on StyleGAN and facial action units, to address these problems. Our framework leverages the pre-trained StyleGAN prior knowledge to enable action unit editing of the face in the StyleGAN latent space, allowing precise expression editing. In addition, we use an encoder to extract multi-scale content features to achieve high-fidelity image reconstruction. Our approach qualitatively and quantitatively outperforms competing methods for action unit manipulation and expression editing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Road Safety with Real-Time Helmet Detection and E-Challan Issuance using YOLO and OCR

Enhancing Road Safety with Real-Time Helmet Detection and E-...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： Deepa S Vinoth Kumar C N S Vivek Duraivelu Balamurugan Easwaran Suguna R Aparna H Department of Computer Technology-PG Kongu Engineering College Erode Tamilnadu Department of Networking and Communications College of Engineering and Technology SRM Institute of Science and Technology Chennai Tamilnadu Department of Computer Science and Engineering B V Raju Institute of Technology Narsapur Telangana India School of IT Texila American University Zambia Africa Department of Computer Science and Business Systems Bannari Amman Institute of Technology Sathyamangalam Tamilnadu M.Sc(Software Systems) Kongu Engineering College Perundurai Erode Tamilnadu

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

This study proposes an integrated system combining Optical Character Recognition (OCR) and YOLO (You Only Look Once) for enforcing helmet laws and improving traffic safety. A user-friendly PyQT GUI facilitates vehicle registration, creating an organized CSV database for future reference. YOLOv5, an advanced object detection algorithm, identifies key elements like motorcycles, helmets, and number plates from input images. The primary objective is detecting motorcyclists without helmets, followed by OCR extraction of text from license plates. The extracted text is compared with registered bike information in the CSV file, generating e-challans and fines for matches. Automatic email notifications ensure timely communication and compliance with traffic regulations. The system's implementation not only aids helmet enforcement but also acts as a deterrent for future violations, fostering a safer driving environment. With scalability and practicality, this approach can integrate seamlessly into existing traffic control systems, leveraging AI technologies like YOLOv5 and OCR for effective problem-solving and enhanced road safety.

关键词： YOLO Head Traffic control Road safety Real-time systems Safety Data mining

来源：评论

学校读者我要写书评

暂无评论

PIG: Prompt Images Guidance for Night-Time Scene Parsing

arXiv

引用

arXiv 2024年

作者： Xie, Zhifeng Qiu, Rui Wang, Sen Tan, Xin Xie, Yuan Ma, Lizhuang Department of Film and Television Engineering Shanghai University Shanghai200072 China Shanghai Key Laboratory of Computer Software Testing and Evaluating China Hanghai Engineering Research Center of Motion Picture Special Effects Shanghai200072 China School of Computer Science and Technology China Normal University Shanghai200062 China Chongqing Institute of East China Normal University Chongqing401120 China School of Computer Science and Technology East China Normal University Shanghai200062 China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China

Night-time scene parsing aims to extract pixel-level semantic information in night images, aiding downstream tasks in understanding scene object distribution. Due to limited labeled night image datasets, unsupervised domain adaptation (UDA) has become the predominant method for studying night scenes. UDA typically relies on paired day-night image pairs to guide adaptation, but this approach hampers dataset construction and restricts generalization across night scenes in different datasets. Moreover, UDA, focusing on network architecture and training strategies, faces difficulties in handling classes with few domain similarities. In this paper, we leverage Prompt Images Guidance (PIG) to enhance UDA with supplementary night knowledge. We propose a Night-Focused Network (NFNet) to learn night-specific features from both target domain images and prompt images. To generate high-quality pseudo-labels, we propose Pseudo-label Fusion via Domain Similarity Guidance (FDSG). Classes with fewer domain similarities are predicted by NFNet, which excels in parsing night features, while classes with more domain similarities are predicted by UDA, which has rich labeled semantics. Additionally, we propose two data augmentation strategies: the Prompt Mixture Strategy (PMS) and the Alternate Mask Strategy (AMS), aimed at mitigating the overfitting of the NFNet to a few prompt images. We conduct extensive experiments on four night-time datasets: NightCity, NightCity+, Dark Zurich, and ACDC. The results indicate that utilizing PIG can enhance the parsing accuracy of UDA. The code is available at https://***/qiurui4shu/PIG. Copyright © 2024, The Authors. All rights reserved.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

An Efficient Autonomous Maze Solving Robot based on Microcontroller by Avoiding Obstacles Using a Decision-Making Algorithm

An Efficient Autonomous Maze Solving Robot based on Microcon...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Muhammad Imran Zulfiqar Irum Abdullah Aasma Akram Shahid Mehmood Fareeha Asad Ali School of Computer Science & Engineering Nanjing University of Science & Technology Nanjing P.R. China Department of Computer Science Lahore College for Women University Jhang Pakistan Department of Software Engineering Lahore College for Women University Lahore Pakistan Department of Computer Science Higher Education Department Punjab Faisalabad Pakistan Department of Business Administration Air University Multan

The task of maze solving has a rich historical background and continues to hold great significance in the realms of Robotics and Artificial Intelligence. The recent advancements in robotics technology aim to develop self-driving robots capable of autonomous operation, with the goal of streamlining our daily tasks. This emphasizes the focus of most research endeavors on augmenting sensor capabilities and refining algorithms to create robots that are adaptable and *** this paper, we present a contemporary approach to robotics that centers on the creation of self-navigating autonomous robots proficient in maze-solving while avoiding obstacles. This innovative research distinguishes itself from conventional line-following robots that merely adhere to predetermined paths. Instead, our proposed methodology enables the robot to navigate the maze independently, optimizing its path effectively. To achieve this, the robot employed in our study incorporates an ultrasonic sensor and operates on an open-source platform featuring an ATmega328P-based microcontroller *** core of this research lies in the development of a decision-making algorithm, which can be stored within the robot's programmable microcontroller, enabling it to tackle maze-solving tasks. The implications of this research span various applications, such as material handling, warehouse management, pipeline inspection, and bomb disposal. Compared to conventional line-following robots, our method provides superior results in terms of precision, recall, F1-score, time required to solve mazes, and practicality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explicitly Guided Difficulty-Controllable Visual Question Generation 39

Explicitly Guided Difficulty-Controllable Visual Question Ge...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xie, Jiayuan Cheng, Mengqiu Zhang, Xinting Cai, Yi Hu, Guimin Xie, Mengying Li, Qing Department of Computing The Hong Kong Polytechnic University Hong Kong School of Software Engineering South China University of Technology Guangzhou China Department of Computer Science University of Copenhagen Denmark Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Chongqing University China Guangdong Neusoft University Foshan China

ISBN: (纸本)157735897X

Visual question generation (VQG) aims to generate questions from images automatically. While existing studies primarily focus on the quality of generated questions, such as fluency and relevance, the difficulty of the questions is also a crucial factor in assessing their quality. Question difficulty directly impacts the effectiveness of VQG systems in applications like education and human-computer interaction, where appropriately challenging questions can stimulate learning interest and improve interaction experiences. However, accurately defining and controlling question difficulty is a challenging task due to its multidimensional and subjective nature. In this paper, we propose a new definition of the difficulty of questions, i.e., being positively correlated with the number of reasoning steps required to answer a question. For our definition, we construct a corresponding dataset and propose a benchmark as a foundation for future research. Our benchmark is designed to progressively increase the reasoning steps involved in generating questions. Specifically, we first extract the relationships among objects in the image to form a reasoning chain, then gradually increase the difficulty by rewriting the generated question to include more reasoning sub-chains. Experimental results on our constructed dataset show that our benchmark significantly outperforms existing baselines in controlling the reasoning chains of generated questions, producing questions with varying difficulty levels. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

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：