检索结果-内蒙古大学图书馆

23rd China National Conference on Computational Linguistics, CCL 2024

作者： Liang, Qiuyu Wang, Weihua Lv, Lei Bao, Feilong College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Mongolian Information Processing Technology Hohhot China

ISBN: (纸本)9789819783663

Knowledge graphs are used to alleviate the problems of data sparsity and cold starts in recommendation systems. However, most existing approaches ignore the hierarchical structure of the knowledge graph. In this paper, we propose a box embedding method for knowledge graph-enhanced recommendation system. Specifically, the box embedding represents not only the interaction between the user and the item, but also the head entity, the tail entity and the relation between them in the knowledge graph. Then the interaction between the item and the corresponding entity is calculated by the multi-task attention unit. Experimental results show that our method provides a large improvement over previous models in terms of Area Under Curve (AUC) and accuracy in publicly available recommendation datasets with three different domains. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

E-RNS : Enhancing Negative Sample Quality from Gradient Perspective for Graph Recommendation

E-RNS : Enhancing Negative Sample Quality from Gradient Pers...

引用

International Conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Qiangsheng Feng Jiwei Qin Jie Ma School of Computer Science and Technology Xinjiang University Key Laboratory of Signal Detection and Processing

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Bayesian Personalized Ranking (BPR) is a widely used optimization function in GNN-based recommender systems, and negative samples are usually obtained through the Random Negative Sampling (RNS) method during BPR training. However, from the gradient perspective, RNS tends to select low-quality samples with minimal information, resulting in small gradients. These small gradients contribute little to BPR optimization, limiting the model’s ability to effectively distinguish between positive and negative samples. To alleviate this issue, we propose a general negative sample information enhancement method: Enhancing Random Negative Sampling (E-RNS), which constructs hard negative samples by enhancing the information in randomly selected negative samples. Specifically, in the Noise Injection step, it generates initial noise and injects a certain amount of noise in the same direction into the vector dimensions of positive samples to create enriched information. Then, in the Information Fusion step, this enriched information is mixed with the negative samples to synthesize new hard negative samples. Extensive experiments demonstrate that applying E-RNS to GNN-based recommender models significantly improves performance.

关键词： Training Limiting Noise Information filters Vectors Acoustics Bayes methods Speech processing Optimization Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Optimization algorithm for global k-means algorithm 13

Optimization algorithm for global k-means algorithm

引用

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 New Machine-Learning Extracting Approach to Construct a Knowledge Base: A Case Study on Global Stromatolites over Geological Time

引用

Journal of Earth Science 2023年第5期34卷 1358-1373页

作者： Xiaobo Zhang Hao Li Qiang Liu Zhenhua Li Claire E.Reymond Min Zhang Yuangeng Huang Hongfei Chen Zhong-Qiang Chen School of Computer China University of GeosciencesWuhan 430078China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of GeosciencesWuhan 430074China School of Earth Resources China University of GeosciencesWuhan 430074China State Key Laboratory of Biogeology and Environmental Geology China University of GeosciencesWuhan 430078China

Within any scientific disciplines, a large amount of data are buried within various literature depositories and archives, making it difficult to manually extract useful information from the datum swamps. The machine-learning extraction of data therefore is necessary for the big-data-based studies. Here, we develop a new text-mining technique to reconstruct the global database of the Precambrian to Recent stromatolites, providing better understanding of secular changes of stromatolites though geological time. The step-by-step data extraction process is described as below. First, the PDF documents of stromatolite-containing literatures were collected, and converted into text formation. Second, a glossary and tag-labeling system using NLP(Natural Language processing) software was employed to search for all possible candidate pairs from each sentence within the papers collected here. Third, each candidate pair and features were represented as a factor graph model using a series of heuristic procedures to score the weights of each pair feature. Occurrence data of stromatolites versus stratigraphical units(abbreviated as Strata), facies types, locations, and age worldwide were extracted from literatures, respectively, and their extraction accuracies are 92%/464, 87%/778, 92%/846, and 93%/405 from 3 750 scientific abstracts, respectively, and are 90%/1 734, 86%/2 869, 90%/2 055 and 91%/857 from 11 932 papers, respectively. A total of 10 072 unique datum items were identified. The newly obtained stromatolite dataset demonstrates that their stratigraphical occurrences reached a pronounced peak during the Proterozoic(2 500 – 541 Ma), followed by a distinct fall during the Early Phanerozoic, and overall fluctuations through the Phanerozoic(541–0 Ma). Globally, seven stromatolite hotspots were identified from the new dataset, including western United States, eastern United States, western Europe, India, South Africa, northern China, and southern China. The proportional occurren

关键词： machine learning knowledge base construction stromatolites Precambrian knowledge graph

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

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-Labeling and Knowledge Distillation 4

Few-Shot Class-Incremental Semantic Segmentation via Pseudo-...

引用

4th International Conference on Information Science, Parallel and Distributed Systems, ISPDS 2023

作者： Jiang, Chengjia Wang, Tao Li, Sien Wang, Jinyang Wang, Shirui Antoniou, Antonios Minjiang University Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Fuzhou China Fujian Education Institutions Wuyi University The Key Laboratory of Cognitive Computing and Intelligent Information Processing Wuyishan China College of Computer and Data Science Fuzhou University Fuzhou China European University Cyprus Department of Computer Science and Engineering Nicosia Cyprus

ISBN: (纸本)9798350337181

We address the problem of learning new classes for semantic segmentation models from few examples, which is challenging because of the following two reasons. Firstly, it is difficult to learn from limited novel data to capture the underlying class distribution. Secondly, it is challenging to retain knowledge for existing classes and to avoid catastrophic forgetting. For learning from limited data, we propose a pseudo-labeling strategy to augment the few-shot training annotations in order to learn novel classes more effectively. Given only one or a few images labeled with the novel classes and a much larger set of unlabeled images, we transfer the knowledge from labeled images to unlabeled images with a coarse-to-fine pseudo-labeling approach in two steps. Specifically, we first match each labeled image to its nearest neighbors in the unlabeled image set at the scene level, in order to obtain images with a similar scene layout. This is followed by obtaining pseudo-labels within this neighborhood by applying classifiers learned on the few-shot annotations. In addition, we use knowledge distillation on both labeled and unlabeled data to retain knowledge on existing classes. We integrate the above steps into a single convolutional neural network with a unified learning objective. Extensive experiments on the Cityscapes and KITTI datasets validate the efficacy of the proposed approach in the self-driving domain. Code is available from https://***/ChasonJiang/FSCILSS. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

MDT-Net: A Mask Decoder Tuning Strategy for CLIP-Based Zero-Shot 3D Classification 31st

MDT-Net: A Mask Decoder Tuning Strategy for CLIP-Based Zero...

引用

31st International Conference on Multimedia Modeling, MMM 2025

作者： Yan, Hao Bai, Jing The School of Computer Science and Engineering North Minzu University Ningxia Yinchuan750021 China The Key Laboratory of Images and Graphics Intelligent Processing of State Ethnic Affairs Commission Ningxia Yinchuan750021 China

ISBN: (纸本)9789819620609

PointCLIP shows that transferring 2D knowledge to zero-shot 3D shape classification tasks can be effective, even without incorporating 3D-specific knowledge. However, the absence of 3D knowledge limits the model’s performance, leading to efforts focused on improving 3D-to-2D projection algorithms. This work advances previous methods by introducing a learnable fine-tuning strategy, called MDT-Net, for Contrastive Language-Image Pre-training (CLIP) on 3D datasets. MDT-Net freezes the CLIP encoder to keep view features aligned with semantic information and incorporates a shape decoder with masked view consistency and attention-guided fusion, enabling more effective fine-tuning of CLIP for 3D tasks. The decoder receives both raw view features and masked view features. In the shallow layers, a mask consistency constraint is utilized between two types of view features to enhance the model’s generalization and robustness. In the deeper layers, attention-guided fusion is introduced to better capture the contextual information between views and compact all view features into one. MDT-Net is evaluated on different benchmarks of 5 datasets for zero-shot classification, achieving a competitive classification accuracy on ModelNet10, ModelNet40, McGill, and ZS3D datasets. These experiment results demonstrate the effectiveness of this approach. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Zero-shot learning

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

A C-band quad-cluster low-profile broadband circularly polarized antenna array based on sequentially rotating metasurface-based

A C-band quad-cluster low-profile broadband circularly polar...

引用

International Applied Computational Electromagnetics Society Symposium (ACES)

作者： Rongxian Bai Minquan Li Key Laboratory of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China

ISBN: (数字)9798350355581

ISBN: (纸本)9798350355598

This paper proposes a metasurface-based left-handed circularly polarized (CP) sequential rotating metasurface-based (MTS) antenna array for C-band. The array comprises a cluster of 4 × 4 periodically aligned MTS cells, which exhibit excellent performance at a low profile of 0.08 λ 0 . The antenna array is constructed on a Rogers RO4003 dielectric board in two layers. The upper surface of the upper layer is the MTS, the floor has a gap between the upper and lower layers, and the lower surface of the lower layer is the sequential feed network. The simulation conducted in HFSS software yielded an integrated bandwidth (IBW) of 95% (3.79-8.54 GHz) and an antenna radiation bandwidth (ARBW) of 49.8% (3.77-6.26 GHz), respectively. The dimensions of the antenna are 1.33λ 0 × 1.33λ 0 × 0.08λ 0 . This configuration results in a miniaturized, compact, and low-profile antenna array. This antenna configuration is applicable to satellite communications using circularly polarized waves through MTS units.

关键词： Satellite antennas C-band Bandwidth Antenna feeds Metasurfaces Software Broadband communication Broadband antennas Satellite communications Antenna arrays

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

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：