检索结果-内蒙古大学图书馆

13th International Conference on Intelligent Control and information processing, ICICIP 2025

作者： Li, Sen Li, Fang Luo, Xiaonan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798331516147

The k-means method is widely utilized for clustering. Its simplicity, efficacy, and swiftness make it a favored choice among clustering algorithms. It faces the challenge of sensitivity to the initial class center. The enhancement strategy for the k-means algorithm focuses on refining the initial selection of cluster centroids, no longer using its random selection of initial class center points, but starting from the entire dataset, choosing the most distant point to serve as the starting cluster centroid. This can also prevent the local optimization problem of the k-means algorithm. The improved algorithm proposed in this article is an effective method that can select the initial class center point from a global perspective and reduce computation time. The suggested approach has undergone rigorous testing and comparative analysis across multiple datasets, yielding commendable outcomes. © 2025 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Holistic Evaluation of Piano Sound Quality 10th

A Holistic Evaluation of Piano Sound Quality

引用

10th Conference on Sound and Music technology, CSMT 2023

作者： Zhou, Monan Wu, Shangda Ji, Shaohua Li, Zijin Li, Wei Central Conservatory of Music Beijing China School of Computer Science and Technology Fudan University Shanghai200438 China Shanghai Key Laboratory of Intelligent Information Processing Fudan University Shanghai200433 China

ISBN: (纸本)9789819779611

This paper aims to develop a holistic evaluation method for piano sound quality to assist in purchasing decisions. Unlike previous studies that focused on the effect of piano performance techniques on sound quality, this study evaluates the inherent sound quality of different pianos. To derive quality evaluation systems, the study uses subjective questionnaires based on a piano sound quality dataset. The method selects the optimal piano classification models by comparing the fine-tuning results of different pre-training models of Convolutional Neural Networks (CNN). To improve the interpretability of the models, the study applies Equivalent Rectangular Bandwidth (ERB) analysis. The results reveal that musically trained individuals are better able to distinguish between the sound quality differences of different pianos. The best fine-tuned CNN pre-trained backbone achieves a high accuracy of 98.3% as the piano classifier. However, the dataset is limited, and the audio is sliced to increase its quantity, resulting in a lack of diversity and balance, so we use focal loss to reduce the impact of data imbalance. To optimize the method, the dataset will be expanded, or few-shot learning techniques will be employed in future research. © 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

Short-Term Smart Grid Load Forecasting Based on CNN-BiLSTM with Attention Mechanism 6

Short-Term Smart Grid Load Forecasting Based on CNN-BiLSTM w...

引用

6th International Conference on Energy, Power and Grid, ICEPG 2024

作者： Sun, Feihu Zhong, Yanru Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Guilin China Guilin University of Electronic Technology Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guangxi Guilin China

ISBN: (纸本)9798350377798

The existing power load data exhibits complex multidimensionality, while existing techniques often focus on learning and forecasting from single load data. To fully exploit the complex multidimensionality of the existing power load data and enhance the accuracy of short-term load forecasting, a smart grid short-term load forecasting model based on attention mechanism and CNN-BiLSTM is proposed. Firstly, the one-dimensional convolutional network (1D-CNN) slides along the temporal dimension to extract multidimensional features such as temperature and humidity from the raw power load data. Secondly, the Bidirectional Long Short-Term Memory network (BiLSTM) captures both historical and future information of the data through gate mechanisms and the bidirectional network structure. Lastly, the attention mechanism allocates weights to focus on important parts of the load sequence data, enhancing the model's ability to identify key information and further improving the accuracy of short-term power load forecasting. The method is experimented on a real-world multivariate load dataset and compared with existing learning methods. The proposed model achieved lower RMSE in 24-hour load forecasting compared to CNN-LSTM, CNN-BiLSTM, LSTM-Attention, BiLSTM-Attention and CNN-LSTM-Attention models by 13.2%, 10.6%, 6.7%, 5.7% and 5.9% respectively. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

PCRTAM-Net:A Novel Pre-Activated Convolution Residual and Triple Attention Mechanism Network for Retinal Vessel Segmentation

引用

Journal of computer Science & technology 2023年第3期38卷 567-581页

作者：汪华登李紫正保罗黎兵兵潘细朋刘振丙蓝如师罗笑南 Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin 541004China School of Computer Science and Information Security Guilin University of Electronic TechnologyGuilin 541004China School of Artificial Intelligence Guilin University of Electronic TechnologyGuilin 541004China Department of Pathology Ganzhou Municipal HospitalGanzhou 341000China

Retinal images play an essential role in the early diagnosis of ophthalmic *** segmentation of retinal vessels in color fundus images is challenging due to the morphological differences between the retinal vessels and the low-contrast *** the same time,automated models struggle to capture representative and discriminative retinal vascular *** fully utilize the structural information of the retinal blood vessels,we propose a novel deep learning network called Pre-Activated Convolution Residual and Triple Attention Mechanism Network(PCRTAM-Net).PCRTAM-Net uses the pre-activated dropout convolution residual method to improve the feature learning ability of the *** addition,the residual atrous convolution spatial pyramid is integrated into both ends of the network encoder to extract multiscale information and improve blood vessel information flow.A triple attention mechanism is proposed to extract the structural information between vessel contexts and to learn long-range feature *** evaluate the proposed PCRTAM-Net on four publicly available datasets,DRIVE,CHASE_DB1,STARE,and *** model achieves state-of-the-art performance of 97.10%,97.70%,97.68%,and 97.14%for ACC and 83.05%,82.26%,84.64%,and 81.16%for F1,respectively.

关键词： retinal image segmentation triple attention mechanism atrous convolution residual network

来源：评论

学校读者我要写书评

暂无评论

Empowering MultiModal Models' In-Context Learning Ability through Large Language Models 23

Empowering MultiModal Models' In-Context Learning Ability th...

引用

2023 ACM Turing Award Celebration Conference, CHINA 2023

作者： Han, Wenjuan Zhao, Haozhe Cai, Zefan School of Computer and Information Technology Beijing Jiaotong University Beijing China National Key Laboratory Multimedia Information Processing School of Software Microelectronics Peking University Beijing China

ISBN: (纸本)9798400702334

Pretrained visual-language models (VLMs) have made progress in developing multimodal models to improve various tasks. However, they lack reasoning and in-context learning ability. Building on the success of large language models (LLMs) in general-purple NLP tasks, researchers anticipate that the VLM should also have the same strong reasoning and ICL ability through specific techniques, for example benefiting from LLMs. To boost VLMs to solve vision-language problems via few-shot exemplars, we suggest a vision-language model, called MIC1. © 2023 Owner/Author.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Tomato Leaf Disease Identification and Growth Dataset Augmentation Based on UAE-GAN 13

Tomato Leaf Disease Identification and Growth Dataset Augmen...

引用

13th International Conference on Intelligent Control and information processing, ICICIP 2025

作者： Li, Xin Li, Fang Luo, Xiaonan School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin541004 China

ISBN: (纸本)9798331516147

To delve into the characterization of growth disorders in different crops, it is important to support the model with a large amount of image data that includes a variety of disease types and disease levels to capture the typical and subtle differences of various diseases on plant leaves. However, the actual process of gathering data is challenging, sample coverage is challenging to accomplish, data capture is impeded, and the quality of the data is subpar. This work aims to address the issue of data shortages by employing technical methods. In particular, we creatively investigated the UAE-GAN approach, which naturally combines CycleGAN, U-Net, Variational Autoencoder VAE, and Autoencoder to increase the data. Among these, U-Net can precisely extract the small details of disease locations in crop photos and provide a strong basis for further processing thanks to its special codec architectural benefits. The Variational Autoencoder (VAE) significantly enhances the diversity of data by mapping the image to the latent space and sampling based on a certain probability distribution, so producing new image samples that are distinct from the original image yet inherently connected. Learning the coding and decoding of the original image is the foundation of autoencoders. If a mild disruption is introduced into the coding process, it can achieve data augmentation in another dimension and create a sequence of new images with just little modifications to the original image. The aforementioned models are closely linked with CycleGAN to efficiently map and convert in a variety of picture domains and to fully leverage CycleGAN's remarkable unsupervised image conversion capabilities. The perception ability, feature capture ability, and information conversion ability of the fusion model for crop image data are significantly improved, and the key elements of each link in the data enhancement process are comprehensively considered to ensure that the generated new image data can not o

关键词： Fruits

来源：评论

学校读者我要写书评

暂无评论

ESNet: Evolution and Succession Network for High-Resolution Salient Object Detection 41

ESNet: Evolution and Succession Network for High-Resolution ...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Liu, Hongyu Cong, Runmin Li, Hua Xu, Qianqian Huang, Qingming Zhang, Wei Institute of Information Science Beijing Jiaotong University Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing China School of Control Science and Engineering Shandong University Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Computer Science and Technology Hainan University Hainan China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China

Preserving details and avoiding high computational costs are the two main challenges for the High-Resolution Salient Object Detection (HRSOD) task. In this paper, we propose a two-stage HRSOD model from the perspective of evolution and succession, including an evolution stage with Low-resolution Location Model (LrLM) and a succession stage with High-resolution Refinement Model (HrRM). The evolution stage achieves detail-preserving salient objects localization on the low-resolution image through the evolution mechanisms on supervision and feature;the succession stage utilizes the shallow high-resolution features to complement and enhance the features inherited from the first stage in a lightweight manner and generate the final high-resolution saliency prediction. Besides, a new metric named Boundary-Detail-aware Mean Absolute Error (MAEBD) is designed to evaluate the ability to detect details in high-resolution scenes. Extensive experiments on five datasets demonstrate that our network achieves superior performance at real-time speed (49 FPS) compared to state-of-the-art methods. Our code is publicly available at: https://***/rmcong/ESNet_ICML24. Copyright 2024 by the author(s)

关键词： Miocene

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-layer Fusion Transformer Network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy NBFC National Biodiversity Future Center Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral image (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification (CLS) token that is randomly initialized and often struggles to generalize effectively. In this paper, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism (HyCrossAttention) for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in - depth experiments on commonly - used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park (MUUFL) dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshone them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Deep Knowledge Tracing Model Based on Multi-Head Self-Attention Mechanism

A Deep Knowledge Tracing Model Based on Multi-Head Self-Atte...

引用

2023 International Conference on Algorithms, High Performance Computing, and Artificial Intelligence, AHPCAI 2023

作者： Zhou, Ya Wu, Fengzhen Huang, Guimin Lin, Jianxing Deng, Nanxiao Guo, Qingkai School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin541004 China

ISBN: (纸本)9781510671881

How to provide individualized instruction and personalized teaching for students and effectively track their knowledge status in a targeted manner is a key concern in the field of education. The target of knowledge tracing (KT) is to use the learner's behavior in historical learning activities to model the students' educational process and forcast the future performance of students. Recently, self-attention has been used several times in the KT field. Traditional models have the problem of losing information under long sequence data. Inspired by Transformer, In this paper, we present a deep knowledge tracing model (MA-DKT) based on the multi-head self-attention mechanism, which employs the LSTM model combined with the multi-head self-attention mechanism to implement a deep knowledge tracing model that is able to catch the data characteristics of the students at different temporal scales. Our model works well on publicly available datasets and achieves some improvement in AUC. © 2023 SPIE. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Zero-Shot Event-Intensity Asymmetric Stereo via Visual Prompting from Image Domain 38

Zero-Shot Event-Intensity Asymmetric Stereo via Visual Promp...

引用

38th Conference on Neural information processing Systems, NeurIPS 2024

作者： Lou, Hanyue Liang, Jinxiu Teng, Minggui Fan, Bin Xu, Yong Shi, Boxin State Key Laboratory of Multimedia Information Processing School of Computer Science Peking University China National Engineering Research Center of Visual Technology School of Computer Science Peking University China National Key Laboratory of General AI School of Intelligence Science and Technology Peking University China School of Computer Science and Engineering South China University of Technology China

Event-intensity asymmetric stereo systems have emerged as a promising approach for robust 3D perception in dynamic and challenging environments by integrating event cameras with frame-based sensors in different views. However, existing methods often suffer from overfitting and poor generalization due to limited dataset sizes and lack of scene diversity in the event domain. To address these issues, we propose a zero-shot framework that utilizes monocular depth estimation and stereo matching models pretrained on diverse image datasets. Our approach introduces a visual prompting technique to align the representations of frames and events, allowing the use of off-the-shelf stereo models without additional training. Furthermore, we introduce a monocular cue-guided disparity refinement module to improve robustness across static and dynamic regions by incorporating monocular depth information from foundation models. Extensive experiments on real-world datasets demonstrate the superior zero-shot evaluation performance and enhanced generalization ability of our method compared to existing approaches. © 2024 Neural information processing systems foundation. 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：