检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zhang, Guoqing Liu, Tianqi Fang, Wenxuan Zheng, Yuhui School of Computer Science Nanjing University of Information Science and Technology Nanjing China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Xining China

Group re-identification (re-ID) aims to match groups with the same people under different cameras, mainly involves the challenges of group members and layout changes well. Most existing methods usually use the k-nearest neighbor algorithm to update node features to consider changes in group membership, but these methods cannot solve the problem of group layout changes. To this end, we propose a novel vision transformer based random walk framework for group re-ID. Specifically, we design a vision transformer based on a monocular depth estimation algorithm to construct a graph through the average depth value of pedestrian features to fully consider the impact of camera distance on group members relationships. In addition, we propose a random walk module to reconstruct the graph by calculating affinity scores between target and gallery images to remove pedestrians who do not belong to the current group. Experimental results show that our framework is superior to most methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Cascade Temporal Convolutional Network for Multitask Learning 6

Cascade Temporal Convolutional Network for Multitask Learnin...

引用

6th International Conference on Artificial Intelligence and Big Data, ICAIBD 2023

作者： Zhang, Huiyun Huang, Heming Han, Henry Baylor University School of Engineering and Computer Science Department of Computer Science United States Qinghai Normal University School of Computer Science Xining China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application School of Computer Science Xining China

ISBN: (纸本)9781665491259

Multi-task learning (MTL) is a powerful technique in machine learning that enables the simultaneous training of multiple tasks. In this paper, we propose a novel MTL approach for the recognition of emotions, speakers, and gender in speech signals. Our approach presents a novel deep learning model called the Cascade Temporal Convolutional Network (CTCN to handle MTL efficiently. CTCN is designed to effectively improve the parallel processing ability of the model in multitasking learning. It provides an effective solution for improving the performance of deep learning in multitasking scenarios. CTCN is particularly adept at processing sequences of data with varying lengths and extracting features that are relevant to multiple tasks. Our experimental results demonstrate that the proposed CTCN approach for MTL achieves significantly superior performance on all tasks on benchmark datasets compared to other deep learning models. This study will inspire more future work in the MTL field. © 2023 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

The Influence of Hyperedge Uniformity on the Characteristics of Small-world Hypernetworks

The Influence of Hyperedge Uniformity on the Characteristics...

引用

2021 International Symposium on Artificial Intelligence and intelligent Manufacturing, AIIM 2021

作者： Cheng, Wenxin Ma, Fuxiang Ma, Xiujuan Chen, Yang Li, Mingjie Liu, Qian Computer College Qinghai Normal University Qinghai Xining810016 China State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Qinghai Xining810008 China Department of Information Engineering Xining Urban Vocational and Technical College Qinghai Xining810016 China

In reality, there are many hypernetworks with small-world characteristics, such as social hypernetworks and traffic hypernetworks. At present, most researches about hypernetworks focus on scale-free hypernetworks and random hypernetworks, and there is little research on small-world hypernetworks. In order to better analyze the characteristics of small-world hypernetworks, this paper constructs four types of small-world hypernetworks evolution model algorithms based on hypergraphs, and explores the influence of the hyperedges uniformity, random probability and construction method on the small-world characteristics of the small-world hypernetworks through simulation experiments and data analysis. It can be seen that, under the same conditions, small-world hypernetworks with uniform hyperedges have the smallest average hyperpath length and the largest hyperedge aggregation coefficient, that is, the best small-world characteristics. Comparing with other hypernetworks of the same scale, the four types of small-world hypernetworks constructed in this paper all show better small-world characteristics, that is, they all have shorter average hyperpath lengths and higher hyperedge aggregation coefficients. © Published under licence by IOP Publishing Ltd.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TMFIF:Transformer-based multi-focus image fusion 5

TMFIF:Transformer-based multi-focus image fusion

引用

5th International Conference on Computer Vision, Image and Deep Learning, CVIDL 2024

作者： Li, Rui Geng, Shengling Zhang, Dan Zhou, Mingquan Qinghai Normal University School of Computer Science Xining China Nanyang Institute of Technology School of Computer and Software Nanyang China People's Government of Qinghai Province & Beijing Normal University Academy of Plateau Science and Sustainability Xining China Qinghai Normal University The State Key Laboratory of Tibetan Intelligent Information Processing and Application China

ISBN: (纸本)9798350373820

Multi-focus image fusion is a hot topic in the field of image processing, and it is a fundamental problem in the fields of image editing, image synthesis, and target retrieval. In previous fusion methods, although feature-rich datasets, models, and algorithms have been provided, there are still many problems with the effective fusion of distant and near views in complex backgrounds. To solve the challenging multi-focus image fusion problem more accurately, we introduce the Transformer Network based on Encoder Decoder (TMFIF), which can extract more generalized features based on the features of multi-focused images to achieve image fusion in complex backgrounds for better visual effects. In this work, we achieve fusion by inputting two images, near and far view. We compare the performance with other multifocal image fusion algorithms by conducting experiments on publicly available datasets and illustrated using existing evaluation methods and evaluation metrics;the results of the experiments show that our method visualizes the fusion effect better through the encoder and the decoder and the evaluation metrics are also relatively good. © 2024 IEEE.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Fusion Multi-scale Features and Attention Mechanism for Multi-view 3D Reconstruction

Fusion Multi-scale Features and Attention Mechanism for Mult...

引用

Electronic Technology, Communication and information (ICETCI), IEEE International Conference on

作者： Qiqi Xie Yuelan Xin Kexin Sun Xi Zeng Qinghai Normal University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Normal University Xining China

In order to solve the problem that it is difficult to carry out the reconstruction accurately and completely in the process of multi-view 3D reconstruction, we puts forward to a 3D reconstruction method that combined with multi-scale features and attention mechanisms. To begin with, multi-scale features are extracted from the input source and reference images using a Feature Pyramid Network that adds a bottom-up structure to obtain the connections between the different scales of the feature map. What’s more, the attention mechanism is used to optimize the cost volume regularization process and improve the accuracy of depth estimation. In the end, the improved network is trained. About the experimental results of DTU dataset, it can be seen that the 3D reconstruction results of this network reached 0.358mm and 0.366mm in Completeness (Comp) and Overall respectively, which are higher than traditional methods as well as some 3D reconstruction methods that are based on deep learning methods. At the same time, the results of visualization in the point cloud model have been significantly improved. In addition, experimental results on Tanks and Temples dataset show that this network also have a better generalization performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A hypergraph structure-based model for the evolution of drug targeted hypernetworks

A hypergraph structure-based model for the evolution of drug...

引用

2021 International Conference on Computer application and information Security, ICCAIS 2021

作者： Bai, Libing Zhu, Qihang Hu, Feng School of Computer Science Qinghai Normal University Xining810008 China Key Laboratory of Tibetan Information Processing and Machine Translation Xining810008 China State Key Laboratory of Intelligent Information Processing and Applications in Tibetan Xining810008 China Academy of Plateau Science and Sustainability Xining810016 China

ISBN: (纸本)9781510655218

Based on the traditional drug-target interactions, a drug-target hypernetwork evolution model was constructed using hypergraph theory. The evolutionary law of the growth of drug-target interactions was analyzed by mean-field theory, and it was found that the distribution of drug-target hypernetwork conformed to a power-law distribution, and further theoretical analysis obtained that the power exponent of the distribution was correlated with the growth rate of the target species corresponding to drug development. A larger exponent tends to explore new targets. By analyzing the drug target data collected from the drugbank in 2021, it was confirmed that the empirical results are consistent with the theoretical analysis and simulation results. © The Authors.

关键词： Mean field theory

来源：评论

学校读者我要写书评

暂无评论

The M-Step Competition Number of Trees and Their Digraphs Construction

SSRN

引用

SSRN 2024年

作者： Wang, Xiaoyi Zhao, Haixing Deng, Bo School of Mathematics and Statistics Qinghai Normal University Xining China Qinghai Nationalities University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

The competition graphs of digraphs are widely studied in various fields, including biology, coding, complex economics, and energy systems. In the study of competition graphs for acyclic digraphs, Roberts observed that adding sufficiently many number of isolated vertices to any graph $G$ can transform it into a competition graph of an acyclic digraph. The smallest such number of isolated vertices is called the competition number of a graph $G$. Han Hyuk Cho et al. extended this concept to the $m$-step competition number. This paper proves that the $m$-step competition number of star and double star are both $m$. And we give an upper bound for the $m$-step competition number of trees and graphs containing complete subgraphs. In addition, three types of digraphs are constructed, whose $m$-step competition graphs are composed of a star with several isolated vertices, a double star with some isolated vertices and a tree with some isolated vertices, respectively. © 2024, The Authors. All rights reserved.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Semantic Tagging Algorithm for tibetan La Case Function Words Oriented to Classification of La Case

Semantic Tagging Algorithm for Tibetan La Case Function Word...

引用

Computer Engineering and intelligent Communications (ISCEIC), International Symposium on

作者： Mabao Ban Jiecairang Duo Rui Zhang Maojia Yang Rangjia Cai College of Computer Science and Technology Qinghai Normal University Xining China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China Tibetan Information Processing and Machine Translation Key Laboratory of Qinghai Province Xining China Tibetan Information Processing Engineering Technology and Research Center of Qinghai Province Xining China

Automatic classification of tibetan La case () is a challenging and significant task in tibetan natural language processing. Compared with other short text classification tasks, the automatic classification of La case depend more on the semantic information of context and function words of La case. Based on the definition about La case classification task, this paper designs a semantic labeling algorithm for tibetan La case function words by analyzing their usage and semantic features. When training La case classification model, calling this algorithm can integrate the semantic information about La case function words, thus increasing the diversity of input features and enriching the semantic information of embedded vectors. Experiments on eight commonly used short text classification models show that the classification accuracy (ACC) after fusing the semantic information on La case function words is improved by 2.1 percentage points on average, which verifies the effectiveness and universality of the algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Improved K-means Algorithm Based on the Bayesian Inference 7th

An Improved K-means Algorithm Based on the Bayesian Inferenc...

引用

7th China National Conference on Big Data and Social Computing, BDSC 2022

作者： Chen, Rumeng Wang, Feng Hu, Feng Computer College of Qinghai Normal University Qinghai Xining810008 China The State Key Laboratory of Tibetan Intelligent Information Processing and Application Qinghai Xining810008 China Academy of Plateau Science and Sustainability Qinghai Xining810016 China

ISBN: (纸本)9789811975318

As one of the most widely used algorithms in machine learning, the fs algorithm is known for its simplicity and efficiency. However, it also has certain limitations, including pre-selecting the K value, which leads to issues such as different cluster shapes and outlier effects. In addition, this clustering algorithm needs to select the initial cluster centers, which produces the phenomenon of local optimum. To alleviate these two types of problems, this paper propose a K-means variant combined with Bayesian inference, dubbed the Bayes-K-means. Firstly, use Bayesian parameter inference to identify parameters for initial cluster centers. According to the probability function of the prior distribution, recalculate the distance from the sample points to the cluster centers. Therefore, the algorithm realizes the global search in the iterative process, which helps to improve the global optimum ability of the algorithm and avoids the phenomenon of local search caused by the K-means algorithm. We verify the Bayes-K-means and theoretically analyze its convergence from the aspect of the posterior distribution and the expression of the clustering center, respectively. Finally, applying the collected and processed real datasets, experimental tests based on artificial datasets and UCI datasets, then comparing Bayes-K-means with K-means, K-means++ and Bisecting K-means experiments, aggregated the class results are consistent with the actual situation. The results show that the proposed algorithm can effectively improve the clustering accuracy, efficiency and generalization performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Borodin-Kostochka Conjecture for Two Families of {P4∪P1}-Free Graphs

SSRN

引用

SSRN 2024年

作者： Tang, LingXiang Qin, XiaoXiao Liu, YongChao Huo, BoFeng School of Mathematics and Statists Qinghai Normal University China The State Key Laboratory of Tibetan Intelligent Information Processing and Application China Academy of Plateau Science and Sustainability Xining Qinghai810000 China

In 1941, Brooks states that for a graph $G$ with $\Delta(G)\geq 3$, $\chi(G)\leq max\{\Delta(G), \omega(G)\}$. In 1977, Borodin and Kostochka conjectured a similar result that if $\Delta(G)\geq 9$,then $\chi(G)\leq max\{\Delta(G)-1, \omega(G)\}$. The conjecture is still a open *** this paper, we show that the conjecture is true for $\{P_4 \cup P_1, diamond, house\}$-freegraphs and $\{P_4 \cup P_1, cochair,bull\}$-free graphs. © 2024, The Authors. All rights reserved.

关键词： Graphic methods

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：