检索结果-内蒙古大学图书馆

2025 international conference on multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Tejesh, Vambara Supriya, M. Amrita School of Computing Amrita Vishwa Vidyapeetham Dept. of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798331509828

This research focuses on generating image captions using Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models. As deep learning advances, the availability of large datasets and increased computing power make it more feasible to build models capable of creating captions for images. This paper uses CNN and RNN models in Python to achieve this. Image captioning combines image recognition and Natural Language Processing (NLP) to interpret image context and express it in English, drawing on core computer vision principles. This study reviews important concepts in image captioning, including the applications of Keras, NumPy, and Jupyter notebook for development. This paper also explores the use of the Flickr dataset and CNN for image classification. The BLEU score of the proposed models is found to be close to 60%. On further enhancement to the model, it could be achieved to get a better score. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

multi-view 3D Reconstruction Based on Deformable Convolution and Laplace Pyramid Residuals

IAENG International Journal of Computer Science

引用

IAENG international Journal of computer science 2024年第7期51卷 896-905页

作者： Hao, Zhaoming Zhang, Ziyang Li, Hongyan Xu, Baoqing Zhang, Xiaoqiong Xu, Meng Wang, Weifeng Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China Engineer of Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China Electrical and Control Engineering Xi’an University of Science and Technology Xi’an710054 China

The current deep learning-based multi-view stereo point cloud reconstruction method has been found to have low reconstruction accuracy for target boundary contours. This paper proposes a high-precision and high-completeness multi-view stereo reconstruction network (DL-PatchMatchNet) based on an improved PatchMatchNet. Firstly, to increase the robustness of the model’s feature extraction, a deformable convolution-based feature extraction network is proposed. Secondly, to improve model reconstruction of target contours and boundaries, the Laplace pyramid residuals are introduced to guide the decoding process of the model. Lastly, a fused loss function (GSS) is proposed to enhance the accuracy of point cloud reconstruction by simultaneously considering geometric consistency loss, structural similarity metric and smoothing loss. The results of the experimental analysis on the DTU dataset demonstrate that the DL-PatchMatchNet model exhibits a lower mean absolute error (MAE) and error rate (ER) than other competing networks. This performance is reflected in the high accuracy and completeness of reconstruction achieved by the DL-PatchMatchNet model. © (2024) international Association of Engineers. All rights reserved.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

multi-view stereo based on adaptive expansion propagation 7

Multi-view stereo based on adaptive expansion propagation

引用

7th international conference on computer Information science and Application Technology, CISAT 2024

作者： Nie, Zixuan Fu, Haohai Jilin Institute of Chemical Technology School of Information and Control Engineering Jilin132022 China Changchun Institute of Technology School of Computer Technology and Engineering Changchun130012 China

ISBN: (纸本)9798350375107

Through computer vision and image processing techniques, a set of images from a scene can be reconstructed in 3D to recover a 3D model of the scene, in which dense reconstruction is a crucial part, and most existing algorithms cannot effectively recover weak texture regions in dense reconstruction. In response to this issue, this article proposes a hypothesis propagation strategy based on adaptive extension. In the hypothesis propagation stage of PatchMatch MVS, an adaptive mechanism for region propagation is introduced, and an update counter is set to regulate the expansion of the sampling area. This ensures that there are enough excellent hypotheses for sampling in this algorithm iteration, and the quality of sampling hypotheses is not limited by fixed sampling pixel positions, thereby improving the probability of excellent hypotheses being sampled in the sampling space. It is demonstrated in the ETH3D dataset that our method reconstructs models with higher integrity, and fewer voids and smoother surfaces in the reconstruction of weakly textured regions. © 2024 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

multi-stack decoding Algorithm for Polarization-adjusted Convolutional Codes 3

Multi-stack decoding Algorithm for Polarization-adjusted Con...

引用

3rd international conference on Electronic Information engineering and computer science, EIECS 2023

作者： Wu, Yuze Huang, Zhiliang Zhang, Youyan Zhou, Shuihong Zhejiang Normal University College of Computer Science Jinhua China Zhejiang Normal University College of Physics and Electronic Information Engineering Jinhua China

ISBN: (纸本)9798350316674

The Polar-Adjusted Convolutional (PAC) codes, improve the error correction ability of the polar code by concatenating convolutional transformation and polar transformation. For the traditional stack decoding algorithm, the ideal performance has not yet been achieved for some PAC codes. In this paper, we adopt a multi-stack decoding algorithm to further improve the error performance of PAC codes. In the multi-stack decoding algorithm, the original single stack is converted into multiple stacks, which expands the exploration path of decoding, obtains more possible decoding results, and improves the decoding performance of PAC codes. Compared to the single-stack decoding, the multi-stack decoding achieves a performance gain of approximately 0.2dB for a PAC code with code length 128 and rate 0.5. © 2023 IEEE.

关键词： convolutional multiple stacks PAC Sequential decoding stacks

来源：评论

学校读者我要写书评

暂无评论

multi Label Classification Based on Ensemble Learning: Investigative Study 25

Multi Label Classification Based on Ensemble Learning: Inves...

引用

25th international Arab conference on Information Technology, ACIT 2024

作者： Nasir, Ola Alazaidah, Raed Hadi, Wael Samara, Ghassan Al Daoud, Essam Owaida, Suhaila Abu Elrashidi, Ali Elsoud, Esraa Abu Alzoubi, Haneen Zarqa University Faculty of Information Technology Department of Computer Science Zarqa Jordan Zarqa University Faculty of Information Technology Department of Data Science and Ai Zarqa Jordan Petra University Faculty of Information Technology Department of Cyber Security Amman Jordan Zarqa University Faculty of Information Technolog Department of Computer Science Zarqa Jordan Al-al-Bayt University Faculty of Information Technology Department of Computer Science Mafraq Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia Applied Science Private University Faculty of It Department of Computer Science Amman Jordan

ISBN: (纸本)9798331540012

In the big data technology nowadays, activities associated with multi-Label Classification (MLC) pose big and complex challenges, receiving terrific interest in diverse fields. Existing MLC algorithms suffer from low overall performance. This paper considers four well-known Problem Transformation Methods (PTMs). Two of these PTMs are based on the frequency of the labels (MFL and LFL) while the last two PTMs are based on the positive correlations among labels. These PTMs have been implemented and compared against four multi label datasets of various sizes to identify the best one that fits the nature of MLC datasets. Moreover, six popular ensemble learning models have been carried out and compared on the four datasets with respect to several evaluation metrics such as Accuracy, Hamming loss, and Exact Match and using SMO, DecisionStump, Random Forest, and Random Commission classifiers. The results revealed that MFL accomplished the quality performance amongst the four PTMs, and Stacking SVM is the best ensemble learning technique. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparison of Different Neural Network Architectures for Cardiac Arrest Risk Prediction 5th

Comparison of Different Neural Network Architectures for Car...

引用

5th international conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Rahman, Mohammed Ziaur Mishra, Awakash Ojha, Ananta Goswami, Shubhashish School of Computer Science and Engineering Presidency University Karnataka Bengaluru India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India Karnataka Bangalore India Department of Computer Science & Engineering School of Engineering and Computing Dev Bhoomi Uttarakhand University Navgaon Manduwala Dehradun India

ISBN: (纸本)9789819780426

Using a realistic dataset based on the United Kingdom clinical exercise studies Datalink, various architectures are evolved and evaluated to decide the simplest for predicting the risk of cardiac arrest. The architectures examined include several modified lengthy short-term memory networks, multi-input/multi-output architectures, Convolutional Neural Networks (CNNs), and Residual Neural Networks. Moreover, the consequences of the architectures on the predictions are compared while the statistics are supplemented with external capabilities. Furthermore, the results recommend increasing the facts with external functions, enhancing prediction accuracy for several architectures. Via this observation, conclusions may be drawn about which architectures are satisfactory-desirable for predicting cardiac arrest chance, as well as the consequences of external capabilities on the effectiveness of the architectures. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Design and implementation of cooperative multi-agent based on MAPPO 5

Design and implementation of cooperative multi-agent based o...

引用

5th international conference on Telecommunications, Optics, and computer science, TOCS 2024

作者： Wang, Haolong Fei, Rong Chen, Ruizhu School of Computer Science and Engineering Xi'an University of Technology Xi'an China Shannxi Key Laboratory for Network Computing and Security Technology Xi'an University of Technology Xi'an China

ISBN: (纸本)9781510691667

In the past few years, with the continuous development of deep reinforcement learning, the application of deep reinforcement has been set off within the realms of self-driving vehicle technology, game games, and natural language processing, and the proximal policy optimization algorithm has emerged as a focal point in the sphere of deep reinforcement learning research. In this paper, the Proximal Policy Optimization (PPO) algorithm and the multi-Agent Proximal Policy Optimization (MAPPO) algorithm are studied, and a cooperative multi-agent system is designed and implemented based on the MAPPO algorithm in the field of StarCraft game, which is compared with the popular Q-Value Mixing (QMIX) reinforcement learning algorithm in recent years, and proposes a direction for subsequent system improvement. In the proximal policy optimization algorithm, the traditional policy gradient algorithm, natural policy gradient algorithm, trust domain policy optimization algorithm, proximal policy optimization algorithm, and independent proximal policy optimization algorithm are studied. In the multi-agent proximal policy optimization algorithm, the centralized training decentralized execution architecture, athlete critic method, value standardization, experience playback, and GAE (GAE) adopted by the MAPPO algorithm are studied. Designing and implementing a cooperative multi-agent system, introducing the StarCraft environmental campaign. Regarding the specifics of the training process, the policy gradient algorithm is used to update the policy network, the time series difference algorithm is improved, and the generalized advantage estimation is used to update the value network. Compared with the QMIX learning algorithm, the model trained by the MAPPO algorithm has the advantages of faster convergence and better stability. © 2025 SPIE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

multi-Lingual Semantic-Based Sentiment Analysis Using Generative AI

Multi-Lingual Semantic-Based Sentiment Analysis Using Genera...

引用

2024 international conference on computer, Electronics, Electrical engineering and their Applications, IC2E3 2024

作者： Biswas, Praloy Arockiam, Daniel Neogi, Subhrendu Guha Sengupta, Somenath Saraswat, Sanjeev Chanda, Rishit Amity University Madhya Pradesh Department of Computer Science and Engineering Madhya Pradesh Gwalior India The Neotia University Department of Computer Science and Engineering West Bengal Sarisha India Heritage Institute of Technology Department of Computer Science and Engineering West Bengal Kolkata India Institute of Business Management GLA University Mathura India SRM Institute of Science and Technology Faculty of Engineering and Technology Tamilnadu Chennai India

ISBN: (纸本)9798350388534

Generative AI models have extensive applications in Natural Language Processing (NLP) and large language models (LLMs) across various domains. They demonstrate high performance in numerous NLP tasks such as summarization, language understanding, reasoning, language generation, question-answering, sentiment categorization, and translation. Newer LLMs are projected to analyse and generate text in multiple languages because to their training on multilingual datasets, like ChatGPT, BLOOMZ, and other similar versions. Considering how frequently LLMs are used, it is critical to assess their effectiveness in multilingual environments. A major issue to be noted is that in a zero-shot context, the present generative models are not very good at producing text in Indian languages. Several scholarly articles studied generative LLMs in the English language. In contrast, LLM for Indic languages is not meant to be used in a zero-shot manner in downstream applications due to poor generating performance. Generative LLMs evaluate models on standard NLP benchmarks covering NLP datasets in diverse languages. We compared the performance of generative LLMs with non-autoregressive models on these tasks to evaluate the generative AI model's performance compared to the previous generation of LLMs. A framework for evaluating generative LLMs in the multilingual setting has been evaluated to provide future directions. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

A Brain Tumor Segmentation Approach with Adaptive Threshold Optimization Numerical Spiking Neural P Systems

A Brain Tumor Segmentation Approach with Adaptive Threshold ...

引用

2024 IEEE international conference on Systems, Man, and Cybernetics, SMC 2024

作者： Dong, Jianping Zhang, Gexiang Rong, Haina Fortin, Giancarlo Chen, Min School of Automation Chengdu University of Information Technology Chengdu610225 China School of Electrical Engineering Southwest Jiaotong University Chengdu611756 China University of Calabria CS Rende87036 Italy School of Computer Science and Engineering South China University of Technology Guangzhou510640 China Pazhou Laboratory Guangzhou510640 China

ISBN: (纸本)9781665410205

Magnetic resonance imaging (MRI) with the high-resolution in computer-aided diagnostic technology is widely used to provide doctors with diagnostic advice, especially in brain tumor segmentation. In addition, MRI multi-sequence images of brain tumors also provide better image data support for studying brain tumor segmentation. In this paper, an adaptive threshold segmentation numerical optimization spiking neural P system (ATONSNPS or ATONSN P system) is designed to dynamically adjust the threshold quantity. In addition, the ATONSN P system and connectivity algorithm are combined to finish multi-sequence brain tumor segmentation. Experimental results on BraTS2019 show that the multi-sequence brain tumor segmentation approach can achieve more effective segmentation of brain tumor images comparing with several benchmark algorithms. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

multi-Object Detection in 3D Point Cloud's Range Image Using Deep-Learning Technique 14

Multi-Object Detection in 3D Point Cloud's Range Image Using...

引用

14th international conference on Cloud Computing, Data science and engineering, Confluence 2024

作者： Jyothsna, D. Chandra, G. Ramesh Department of Computer Science and Engineering Jntuh Hyderabad India Department of Computer Science and Engineering Hyderabad India

ISBN: (纸本)9798350344837

In recent years, LIDARs (Light Detection and Ranging) have gained a lot of insight into various fields such as agriculture, astronomy, robotics, autonomous driving, forestry, etc. Point Clouds obtained through LIDAR have gained attention in the field of computer vision, robotics, and autonomous driving. In computer vision, there are several high level tasks namely classification, detection, tracking, segmentation and registration. Object detection in 3D Point Clouds is one of the challenges faced in the field of computer vision, which is one of the high level tasks. Due to the unordered nature of point cloud data, detecting objects by designing deep neural networks is not a straightforward task. This paper aims to provide a solution to detect the objects in a 3D point cloud data by transforming into 2D range image obtained from LIDAR using the improved YOLOV5 (You Only Look Once- Version5) approach by embedding the coordinate attention module. The improved YOLOV5 is used to detect objects in an image and conducted experiments on different sizes of custom 3D point cloud datasets with and without augmentation. The experimental results showed how the precision, recall and mean average precision (mAP) metrics improve as the dataset size increases. Also, the comparative results with YOLOV5 yielded better results on our data. © 2024 IEEE.

关键词： Object detection

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：