检索结果-内蒙古大学图书馆

Language Technology and Digital Humanities (LTDH), International Conference on

作者： Hanyun Qi Shiliang Lyu Key Laboratory of Linguistic and Cultural Computing Ministry of Education Northwest Minzu University Key Laboratory of Minzu Language and Cultures Intelligent Information Processing Gansu Province Northwest Minzu University

ISBN: (数字)9798350380187

ISBN: (纸本)9798350380194

Zhaotong City is located in the northeast of Yunnan Province and used to be called “Zhuti County”. Due to the influence of population migration, the Zhaotong dialect has the characteristics of the northern dialect as well as its own unique features. Early research on the tones of Zhaotong dialect relied on traditional language survey methods. In this paper, we use modern methods of speech signal analysis to reanalyze the tones of Zhaotong dialect by means of spectral analysis of sound waveforms, resonance peak analysis, fundamental frequency extraction, etc. combined with the knowledge of experimental phonetics. It is concluded that the Zhaotong dialect consists of four tone categories, namely, Tone1, Tone2, Tone3, and Tone4. Among the single character tones, Tonel is characterized by a flat tonal pattern; Tone2 is characterized by a descending tonal pattern; Tone3 is characterized by a descending tonal pattern; and Tone4 is characterized by a zigzag tonal pattern.

关键词： Surveys Hands Fluctuations Urban areas Speech recognition Turning Registers Digital preservation Speech processing Spectral analysis

来源：评论

学校读者我要写书评

暂无评论

Acoustic Analysis of Long and Short Vowels of Eastern Yugur Language for Low Resource Speech Synthesis

Acoustic Analysis of Long and Short Vowels of Eastern Yugur ...

引用

Language Technology and Digital Humanities (LTDH), International Conference on

作者： Shiliang Lyu Hanyun Qi Yuwen Min Qianqian Ma Key Laboratory of Minzu Language and Cultures Intelligent Information Processing Northwest Minzu University Gansu Province Key Laboratory of Linguistic and Cultural Computing Ministry of Education Northwest Minzu University

ISBN: (数字)9798350380187

ISBN: (纸本)9798350380194

The articulation of long and short vowels is not only a change in duration, but also includes changes in the shape of the oral cavity to comprehensively affect the timbre. Since the low-resource phonetic data is very limited, especially the pronunciation of long and short vowels will be affected by the surrounding phonemes or syllables, which makes it difficult for the speech synthesis model to adequately learn and capture the differences of vowels, thus affecting the accuracy and naturalness of the synthesis of long and short vowels. The eastern Yugur language in China belongs to the Mongolian group of the Altaic language family, with an endangered language and limited phonetic resource data. If this endangered language is extinct, it can be restored through speech synthesis. In this article, we analyze the acoustics of long and short vowels in the Eastern Yugur language, and find out the differences in the distribution of acoustic parameters, as well as the differences in the parameters of males and females, so as to provide a reference for the synthesis of the Eastern Yugur language.

关键词： Time-frequency analysis Shape Resonant frequency Training data Phonetics Rhythm Resonance Acoustics Speech synthesis Timbre

来源：评论

学校读者我要写书评

暂无评论

Look Inside for More: Internal Spatial Modality Perception for 3D Anomaly Detection 39

Look Inside for More: Internal Spatial Modality Perception f...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Hanzhe Xie, Guoyang Hou, Chengbin Wang, Bingshu Gao, Can Wang, Jinbao College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Audencia Financial Technology Institute Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Intelligent Manufacturing CATL Ningde China School of Computing and Artificial Intelligence Fuyao University of Science and Technology Fuzhou China School of Software Northwestern Polytechnical University Xi’an China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (纸本)157735897X

3D anomaly detection has recently become a significant focus in computer vision. Several advanced methods have achieved satisfying anomaly detection performance. However, they typically concentrate on the external structure of 3D samples and struggle to leverage the internal information embedded within samples. Inspired by the basic intuition of why not look inside for more, we introduce a straightforward method named Internal Spatial Modality Perception (ISMP) to explore the feature representation from internal views fully. Specifically, our proposed ISMP consists of a critical perception module, Spatial Insight Engine (SIE), which abstracts complex internal information of point clouds into essential global features. Besides, to better align structural information with point data, we propose an enhanced key point feature extraction module for amplifying spatial structure feature representation. Simultaneously, a novel feature filtering module is incorporated to reduce noise and redundant features for further aligning precise spatial structure. Extensive experiments validate the effectiveness of our proposed method, achieving object-level and pixel-level AUROC improvements of 4.2% and 13.1%, respectively, on the Real3D-AD benchmarks. Note that the strong generalization ability of SIE has been theoretically proven and is verified in both classification and segmentation tasks. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

αSetup-PCTL:An Adaptive Setup-Based Two-Level Preconditioner for Sequence of Linear Systems of Three-Temperature Energy Equations

引用

Communications in Computational Physics 2022年第10期32卷 1287-1309页

作者： Silu Huang Xiaoqiang Yue Xiaowen Xu Laboratory of Computational Physics Institute of Applied Physics and ComputationalMathematicsBeijing 100088China National Center for Applied Mathematics in Hunan Key Laboratory of Intelligent Computing and Information Processing of Ministry of EducationHunan Key Laboratory for Computation and Simulation in Science and EngineeringXiangtan UniversityXiangtan 411105China

The iterative solution of the sequence of linear systems arising from threetemperature(3-T)energy equations is an essential component in the numerical simulation of radiative hydrodynamic(RHD)***,due to the complicated application features of the RHD problems,solving 3-T linear systems with classical preconditioned iterative techniques is *** address this difficulty,a physicalvariable based coarsening two-level(PCTL)preconditioner has been proposed by dividing the fully coupled system into four individual easier-to-solve *** its nearly optimal complexity and robustness,the PCTL algorithm suffers from poor efficiency because of the overhead associatedwith the construction of setup phase and the solution of ***,the PCTL algorithm employs a fixed strategy for solving the sequence of 3-T linear systems,which completely ignores the dynamically and slowly changing features of these linear *** address these problems and to efficiently solve the sequence of 3-T linear systems,we propose an adaptive two-level preconditioner based on the PCTL algorithm,referred to as α*** adaptive strategies of the αSetup-PCTL algorithm are inspired by those of αSetup-AMG algorithm,which is an adaptive-setup-based AMG solver for sequence of sparse linear *** proposed αSetup-PCTL algorithm could adaptively employ the appropriate strategies for each linear system,and thus increase the overall *** results demonstrate that,for 36 linear systems,the αSetup-PCTL algorithm achieves an average speedup of 2.2,and a maximum speedup of 4.2 when compared to the PCTL algorithm.

关键词： Sequence of linear systems sparse linear solver preconditioning methods radiation hydrodynamics simulation

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

AUCSeg: AUC-oriented pixel-level long-tail semantic segmentation 24

AUCSeg: AUC-oriented pixel-level long-tail semantic segmenta...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Boyu Han Qianqian Xu Zhiyong Yang Shilong Bao Peisong Wen Yangbangyan Jiang Qingming Huang Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and School of Computer Science and Tech. University of Chinese Academy of Sciences Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Peng Cheng Laboratory School of Computer Science and Tech. University of Chinese Academy of Sciences School of Computer Science and Tech. University of Chinese Academy of Sciences and Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS and Key Laboratory of Big Data Mining and Knowledge Management CAS

ISBN: (纸本)9798331314385

The Area Under the ROC Curve (AUC) is a well-known metric for evaluating instance-level long-tail learning problems. In the past two decades, many AUC optimization methods have been proposed to improve model performance under long-tail distributions. In this paper, we explore AUC optimization methods in the context of pixel-level long-tail semantic segmentation, a much more complicated scenario. This task introduces two major challenges for AUC optimization techniques. On one hand, AUC optimization in a pixel-level task involves complex coupling across loss terms, with structured inner-image and pairwise inter-image dependencies, complicating theoretical analysis. On the other hand, we find that mini-batch estimation of AUC loss in this case requires a larger batch size, resulting in an unaffordable space complexity. To address these issues, we develop a pixel-level AUC loss function and conduct a dependency-graph-based theoretical analysis of the algorithm's generalization ability. Additionally, we design a Tail-Classes Memory Bank (T-Memory Bank) to manage the significant memory demand. Finally, comprehensive experiments across various benchmarks confirm the effectiveness of our proposed AUCSeg method. The code is available at https://***/boyuh/AUCSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptively feature matching via joint transformational-spatial clustering

Adaptively feature matching via joint transformational-spati...

引用

作者： Wang, Linbo Tan, Li Fang, Xianyong Guo, Yanwen Wan, Shaohua MOE Key Laboratory of Intelligent Computing and Signal Processing School of Computer Science and Technology Anhui University Hefei China National Key Lab for Novel Software Technology Nanjing University Nanjing China School of Information and Safety Engineering Zhongnan University of Economics and Law Wuhan China

The transformational and spatial proximities are important cues for identifying inliers from an appearance based match set because correct matches generally stay close in input images and share similar local transformations. However, most existing approaches only check one type of them or both types consecutively with manually set thresholds, and thus their matching accuracy and flexibility in handling large-scale images are limited. In this paper, we present an efficient clustering based approach to identify match inliers with both proximities simultaneously. It first projects the putative matches into a joint transformational-spatial space, where mismatches tend to scatter all around while correct matches gather together. A mode-seeking process based on joint kernel density estimation is then proposed to obtain significant clusters in the joint space, where each cluster contains matches mapping the same object across images with high accuracy. Moreover, kernel bandwidths for measuring match proximities are adaptively set during density estimation, which enhances its applicability for matching different images. Experiments on three standard datasets show that the proposed approach delivers superior performance on a variety of feature matching tasks, including multi-object matching, duplicate object matching and object retrieval. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Clustering Density estimation Feature matching Mode-seeking

来源：评论

学校读者我要写书评

暂无评论

Design and Analysis of a Modified ZNN with Dynamic Parameter for Time Varying Generalized Sylvester Equation

Design and Analysis of a Modified ZNN with Dynamic Parameter...

引用

2022 International Conference on Machine Learning, Cloud computing and intelligent Mining, MLCCIM 2022

作者： Zhang, Yongsheng Chen, Jifeng He, Yongjun Peng, Hao Li, Ping College of Information and Mechatronics Engineering Hunan International Economics University Changsha410205 China Hunan Provincial Key Laboratory of Intelligent Computing and Language Information Processing Hunan Normal University Changsha410205 China

ISBN: (数字)9781665498586

ISBN: (纸本)9781665498586

The time varying generalized Sylvester equation (TVGSE) is widely used in many domains such as mathematics, engineering and control system. Differing from the zeroing neural network (ZNN) and varying parameter ZNN (VPZNN), a novel neural network algorithm based on a novel time-varying parameter, named modified VPZNN (MVPZNN), is presented and studied for handling TVGSE in this work. In particular, the proposed MVPZNN possesses faster convergence capacity when activated by the linear and sign-bi-power activation function, respectively. Numerical simulation indicates that MVPZNN has superiority in convergence rate in coping with TVGSE compared with fixed parameter ZNN and other VPZNN models. © 2022 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Surface Defect Detection

LRT-DETR: An Enhanced Transformer-Based Framework for PCB Su...

引用

Artificial Intelligence, Networking and information Technology (AINIT), International Seminar on

作者： Hongyu Tang Dengli Bu Guanhao Mo Panlin Lu Zhenhai Li Long Huang Key Laboratory of Intelligent Computing and Distributed Information Processing School of Computer Science and Technology Guangxi University of Science and Technology Guangxi Colleges and Universities Liuzhou China

ISBN: (数字)9798331522285

ISBN: (纸本)9798331522292

To address the issues of complex background interference and micro-defect detection in printed circuit board (PCB) surface inspection, while accommodating the deployment constraints of edge devices in industrial scenarios, this paper proposes a lightweight real-time detection Transformer (LRTDETR), an improved architecture based on RT-DETR. First, the original ResNet18 backbone is replaced with RepNCSPELAN, a lightweight network leveraging structural re-parameterization to reduce model complexity. Second, a global-local bidirectional feature pyramid network is introduced in the neck, which enhances the multi-scale feature representation through an adaptive weighted feature fusion mechanism, significantly improving small defect detection. Experimental results demonstrate that the improved model achieves a 96.9% mean average precision (mAP) with only a 0.2% performance drop compared to the baseline. Notably, the model size, the parameters, and the FLOPs are reduced by $58.3 \%, 53.5 \%$ , and 57.3%, respectively. The inference speed reaches 39 FPS, balancing accuracy and efficiency for real-time industrial inspection and edge deployment. This work provides a practical solution for highprecision, resource-efficient defect detection in industrial edge computing environments.

关键词： Adaptation models Computational modeling Image edge detection Printed circuits Inspection Feature extraction Transformers Real-time systems Neck Defect detection

来源：评论

学校读者我要写书评

暂无评论

Prediction of piRNA-mRNA interactions based on an interactive inference network

Prediction of piRNA-mRNA interactions based on an interactiv...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Liu, Yajun Li, Ru Li, Aimin Fei, Rong Guo, Xie Wu, Fang-Xiang Xi'an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology Xi'an China Xi'an University of Technology Shaanxi Key Laboratory of Complex System Control and Intelligent Information Processing Xi'an China University of Saskatchewan Division of Biomedical Engineering Department of Computer Science Department of Mechanical Engineering Saskatoon Canada

ISBN: (纸本)9798350337488

As the largest class of small non-coding RNAs, piRNAs primarily present in the reproductive cells of mammals, which influence post-transcriptional processes of mRNAs in multiple ways. Effective methods for predicting piRNA and mRNA target relationships can help identify piRNA functions, investigate the possibility of piRNAs as biomarkers and therapeutic targets. In this study, we propose a computational approach for classifying the relationships of piRNA-mRNA pairs based on an interactive inference network (IIN). First, we gather piRNA-mRNA target data, collect sequence data by position alignment, and construct a benchmark dataset. Furthermore, a reliable negative set is constructed by positive-unlabeled learning. Finally, we view a piRNA and a mRNA sequence as a premise and hypothesis sentence, respectively, and IIN model is used to predict the relationship between them. The experiments demonstrate that our method effectively characterizes piRNA-mRNA interaction and could be beneficial for researchers to investigate piRNA functions. © 2023 IEEE.

关键词： interactive inference network noncoding RNA piRNA-mRNA interactions positive-unlabeled 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：