检索结果-内蒙古大学图书馆

Cognitive Computing and Complex Data (ICCD), International Conference on the

作者： Xinyun Zhang Li Shen Li Zhou Dawei Luo Dejiangmo Xiaonan Luo Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin China School of Physics and Electronic Information Gannan Normal University Ganzhou China School of Mathematics and Computer Science Northwest Minzu University Lanzhou China

ISBN: (数字)9798350352894

ISBN: (纸本)9798350352900

With advancements in communication technology, there is increasing demand for high-quality voice communication and accurate speech recognition. In the complex acoustic environment of a recording classroom, noise, reverberation and other interferences can seriously affect the quality and intelligibility of the picked-up target speech signal, which in turn affects the effectiveness of the subsequent speech communication and recognition, so it is crucial to enhance the target speech signal in order to satisfy people's demand for clear and recognizable speech information. In this paper, based on the network model of Deep Complex Convolutional Recurrent Network (DCCRN), we introduce the F-T-LSTM structure to more accurately describe the correlation between the time and frequency domains of speech, and at the same time, we integrate the channel attention mechanism and the spatial attention mechanism to carry out a more comprehensive feature extraction of the speech features in the complex domain, and we skillfully concentrate the computational power in the area with the most feature-rich information, so that the quality and intelligibility of speech signals under the complex domain are significantly improved. significantly improve the overall performance of speech enhancement networks in the complex domain.

关键词： Time-frequency analysis Attention mechanisms Correlation Target recognition Computational modeling Speech recognition Speech enhancement Feature extraction Complexity theory Reverberation

来源：评论

学校读者我要写书评

暂无评论

Hybrid Data-Free Knowledge Distillation

arXiv

引用

arXiv 2024年

作者： Tang, Jialiang Chen, Shuo Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Center for Advanced Intelligence Project RIKEN Japan Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

Data-free knowledge distillation aims to learn a compact student network from a pre-trained large teacher network without using the original training data of the teacher network. Existing collection-based and generation-based methods train student networks by collecting massive real examples and generating synthetic examples, respectively. However, they inevitably become weak in practical scenarios due to the difficulties in gathering or emulating sufficient real-world data. To solve this problem, we propose a novel method called Hybrid Data-Free Distillation (HiDFD), which leverages only a small amount of collected data as well as generates sufficient examples for training student networks. Our HiDFD comprises two primary modules, i.e., the teacher-guided generation and student distillation. The teacher-guided generation module guides a Generative Adversarial Network (GAN) by the teacher network to produce high-quality synthetic examples from very few real-world collected examples. Specifically, we design a feature integration mechanism to prevent the GAN from overfitting and facilitate the reliable representation learning from the teacher network. Meanwhile, we drive a category frequency smoothing technique via the teacher network to balance the generative training of each category. In the student distillation module, we explore a data inflation strategy to properly utilize a blend of real and synthetic data to train the student network via a classifier-sharing-based feature alignment technique. Intensive experiments across multiple benchmarks demonstrate that our HiDFD can achieve state-of-the-art performance using 120 times less collected data than existing methods. Code is available at https://***/tangjialiang97/HiDFD. Copyright © 2024, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Pagml: Precise Alignment Guided Metric Learning for Sketch-Based 3d Shape Retrieval

SSRN

引用

SSRN 2023年

作者： Bai, Shaojin Bai, Jing Xu, Hao Tuo, Jiwen Liu, Min School of Computer Science and Engineering North Minzu University Yinchuan750021 China National Ethnic Affairs Commission Image graphics intelligent processing laboratory Yinchuan750021 China School of Mechanical Engineering Purdue University West Lafayette47907 United States

Sketch-based 3D shape retrieval has always been a hot research topic in the computer vision community. The main challenge is to alleviate the cross-modality discrepancies such that the retrieval accuracy can be improved. In this paper, we propose a novel Precise Alignment Guided Metric Learning (PAGML) method based on master-auxiliary cross-modality retrieval framework. An auxiliary learning network is developed to indirectly guide the master learning model to extract features of rich semantic information, so as to achieve a semantic alignment between the cross-modality data. Furthermore, considering that the unbalanced data distributions led to the poor uniformity in the common embedding space, a loss function dedicated for the imbalanced cross-modality data is designed to achieve a rigid alignment between sketches and 3D shapes of the same category by pulling their rich semantic representations to the rigid center of the category. As a result, a more precise alignment between the cross-modality embedding features of same category is approached gradually, which further alleviates the cross-modality discrepancies and improves the cross-modality retrieval accuracies. Extensive experiments on two public benchmark datasets demonstrate that the proposed PAGML surpasses the state-of-the-art methods in retrieval accuracy and has excellent generalization abilities to unseen classes. © 2023, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Chinese Sentiment Analysis Model Incorporating Knowledge Graph and Deep Learning

A Chinese Sentiment Analysis Model Incorporating Knowledge G...

引用

2023 7th International Conference on Electrical, Mechanical and computer Engineering (ICEMCE)

作者： Shengping Zhao Jinlong Chen Xingguo Qin School of Computer Science and Information Security Guilin University of Electronic Technology Guilin China School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin University of Electronic Technology Guilin Guangxi China

With the rapid growth of social media and e-commerce, users are generating large amounts of textual review data on these platforms. Analyzing and mining these comment data is important for governments, enterprises, and consumers to make decisions. Therefore, sentiment analysis, especially for Chinese comments, has become an area of wide interest in industry and academia. Aiming at the characteristics of Chinese online reviews, this paper applies the techniques of knowledge graph and deep learning around sentence-level sentiment analysis and designs a sentiment analysis model that integrates different information such as sentiment knowledge graph and serialized annotation in a deep learning model to improve the accuracy and effectiveness of sentiment analysis of Chinese online reviews. This is important for improving products and services, understanding user needs, and making more informed business and policy decisions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Analysis Model of Potential Topics in English Essays Based on Semantic Space

引用

Journal of computers (Taiwan) 2022年第1期33卷 151-164页

作者： Huang, Guimin Zhang, Xiaowei Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

With the reform of English examination in China in recent years, the automatic evaluation of English essays as subjective questions has always been the focus and difficulty of research. The existing automatic essay evaluation system (AEE) has obtained good feedback on the vocabulary, syntactic and other features of English essays, but there is still a problem of low accuracy in the analysis of potential topic in English essay. In order to solve this problem, this paper takes relational triples as the carrier to analyze the potential topics of English essays. By constructing the hierarchical topic trees hybrid semantic spaces to carry out topic clustering, distributed representation of topic relational triples and topic set extension in English essays. Then, based on the improved on-topic analysis algorithm in this paper, the paper analyzes the topic of English essay in multiple dimensions to obtain more abundant potential on-topic semantic information. The experiment results show that the proposed model can reduce the noise caused by non-topic words effectively, and improve the fine-grained topic semantic space in English essays, and the proposed model has better performance than the current methods of on-topic analysis in English esssays. © 2022 computer Society of the Republic of China. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Errors Correction Model for the Errors of Non-word and Real-word in English Composition

引用

Journal of computers (Taiwan) 2022年第1期33卷 139-150页

作者： Huang, Guimin Li, Maolin Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

In the procedure from composing English, it is inevitable to face the phenomenon of word writing errors. In recent years, English composition automatic correcting system has attracted much attention. However, the precision of the existing word errors correcting system is vague generalization. So as to move forward the accuracy of checking and correcting word errors, this paper designs a word errors correction model based on natural language processing technology. This model designs phoneme matching method based on an improved IDM algorithm, and combined with a non-word input errors correction method based on character distance. The accuracy of correcting non-word errors in this model reached 86.5%. The study also proposes a real-word errors correction method, which is implemented basing on the real-word confusion set and combining the binary statistical model and the GloVe word vector model, improving the real-word errors correction method based on feature annotation of the real-word confusion set, with an accuracy of 77.9%. © 2022 computer Society of the Republic of China. All rights reserved.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Real-Time Student Behavior Analysis via YOLOv5 with Coordinate Attention 9th

Real-Time Student Behavior Analysis via YOLOv5 with Coordina...

引用

9th International Symposium on Artificial Intelligence and Robotics, ISAIR 2024

作者： Ma, Shuai Chang, Heyou Yang, Xinru Chen, Quan Han, Jian Key Laboratory of Intelligent Information Processing Nanjing XiaoZhuang University Nanjing China School of Information and Engineering Nanjing XiaoZhuang University Nanjing China School of Computer Science Nanjing University of Information Science and Technology Nanjing China Jiangsu Key Laboratory of Image and Video Understanding for Social Safety Nanjing University of Science and Technology Nanjing China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education Nanjing University of Science and Technology Nanjing China

ISBN: (纸本)9789819629138

The detection and recognition of student behavior play a pivotal role in the context of smart classrooms. However, conventional methods often encounter performance degradation due to challenges such as occlusion, data diversity, and complexity. To effectively addresses these issues, we propose a method that integrates YOLOv5 with coordinate attention mechanism and GhostConv for analyzing students' behavior. Specifically, the coordinate attention module enhances the localization ability of the proposed method by addressing problems related to target scale variations and uneven distribution. Additionally, we employ GhostConv to replace conventional convolutional layers in YOLOv5, reducing parameters while improving computational efficiency. To verify the validity of our method, a self-built challenging dataset for real teaching scenarios and Citypersons dataset are selected for the experiment. In comparison to the original YOLOv5, our method has achieved a 14.8% and 5.7% increase in mean average precision rates, with a 19.0% improvement in frames per second. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Single-Cell Clustering Algorithm Based on Structure Perturbation Non-Negative Matrix Factorization

A Single-Cell Clustering Algorithm Based on Structure Pertur...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Jiang, Hanjing Wang, Meineng Zhang, Luping Huang, Yu-An Li, Yangyuan Huang, Yabing Huazhong University of Science and Technology Key Laboratory of Image Information Processing and Intelligent Control Education Ministry of China Institute of Artificial Intelligence School of Artificial Intelligence and Automation Hubei Wuhan430074 China China University of Mining and Technology School of Computer Science and Technology Xuzhou221116 China Yichun University School of Mathematics and Computer Science Yichun336000 China East China University of Technology School of Information Engineering Nanchang330013 China Northwestern Polytechnical University School of Computer Science Xi'an710129 China Renmin Hospital Wuhan University Department of Pathology Wuhan430060 China

ISBN: (纸本)9798350386226

The advent of single-cell RNA sequencing (scRNA-seq) has facilitated the acquisition of high-resolution data regarding cell heterogeneity across various tissues. A fundamental and critical step in the analysis of scRNA-seq data is cell type identification. An appropriate graph construction strategy can reflect the topological structure between cells and allows for detailed exploration of the relationships between cells and genes. Given the sparsity of scRNA-seq data and the pronounced noise generated by shallow sequencing, choosing an appropriate graph construction strategy has become a significant challenge. In this paper, we propose a single-cell clustering method, named Sc-PNNMF, based on structural perturbation of nonnegative matrix factorization. Sc-PNNMF employs a structural perturbation algorithm to optimize the gene expression matrix. The optimized matrix guides the matrix factorization process, effectively overcoming the impact of data sparsity and significant noise in gene expression data on the graph construction strategy. We compared the clustering abilities of Sc-PNNMF with five other methods on ten real datasets. © 2024 IEEE.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

A High-Resolution Human Pose Estimation Method with Coordinate Attention 9

A High-Resolution Human Pose Estimation Method with Coordina...

引用

9th International Conference on Digital Home, ICDH 2022

作者： Deng, Zhengjie Li, Yuanzhong He, Shuqian Wang, Yizhen Wang, Xun Hainan Normal University School of Information Science and Technology Haikou China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China Hainan Normal University School of Physics and Electronic Engineering Haikou China Hainan Blue Point Computer Network Engineering Co. Ltd. Haikou China

ISBN: (数字)9781665454780

ISBN: (纸本)9781665454780

Human pose estimation is an important element in video and image analysis. However, existing methods have some problems such as less accurate predicted position and over-lapping key points. To address these problems, we construct a high-resolution human pose estimation method based on Coordinate Attention (CA) mechanism that combines coordinate perception. The method constructs a coordinate attention bottleneck module (CABottleneck) and a coordinate attention module (CABlock) based on the attention mechanism, which allow the model to obtain richer coordinate and orientation information in feature extraction, and then combine the downsampling operation to convert the original image into four different sizes of feature maps, and then fuse these feature maps in multivariate resolution. Then, we use the deconvolution module to obtain the high-resolution feature maps, and finally derive the positions of each key point to achieve the estimation of human pose. The experimental results show that the accuracy of the method in this paper is better than that of various methods such as HigherHRNet when using similar number of parameters. In the CrowdPose test dataset, the accuracy of both single-scale and multi-scale exceeds 72%, which is 6.6% better than HigherHRNet;5% better than DEKR. In the COCO2017 val dataset, our method maintains a high performance and reduces the repetition rate of human key points. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Provable Discriminative Hyperspherical Embedding for Out-of-Distribution Detection 39

Provable Discriminative Hyperspherical Embedding for Out-of-...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zou, Zhipeng Wan, Sheng Li, Guangyu Han, Bo Liu, Tongliang Zhao, Lin Gong, Chen School of Computer Science and Engineering Nanjing University of Science and Technology China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education China Jiangsu Key Laboratory of Image and Video Understanding for Social Security China Hong Kong Baptist University China Sydney AI Centre The University of Sydney Sydney Australia Department of Automation Institute of Image Processing and Pattern Recognition Shanghai Jiao Tong University China

ISBN: (纸本)157735897X

Out-of-distribution (OOD) detection aims to identify the test examples that do not belong to the distribution of training data. The distance-based methods, which identify OOD examples based on their distances from the centroids of in-distribution (ID) examples, have demonstrated promising OOD detection performance. However, the objectives utilized in prior approaches are typically designed for classification and thus might not yield sufficient discriminative power to distinguish between ID and OOD examples. Therefore, this paper proposes a prototype-based contrastive learning framework for OOD detection, which is termed provable Discriminative Hyperspherical Embedding (DHE). The proposed framework provides a theoretical analysis of inter-class dispersion, which is proved to be fundamental in reducing the false positive rate (FPR) on OOD examples. Based on this, we devise an angular spread loss to achieve the maximal dispersion of the prototypes of different classes prior to training. Subsequently, a prototype-enhanced contrastive loss is introduced to align embeddings of ID examples closely with their corresponding prototypes. In our proposed DHE, the maximal prototype dispersion is theoretically proved, thereby avoiding the pitfalls of local optima commonly encountered by most existing methods. Experimental results demonstrate the effectiveness of our proposed DHE, which showcases a remarkable reduction in FPR95 (i.e., 5.37% on CIFAR-100) and more than doubling the computational efficiency when compared with the state-of-the-art methods. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Contrastive Learning

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：