检索结果-内蒙古大学图书馆

International Conference on Smart Health, ICSH 2017

作者： Xie, Xiaodong Liu, Rui Zhou, Dongsheng Wei, Xiaopeng Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

ISBN: (纸本)9783319679631

The segmentation of motion capture data is to separate the different types of human motion data contains long movement sequence into motion clips with independent semantics in order to facilitate the storage in the database as well as medical analysis. This paper proposed a method for human motion capture data segmentation based on Laplacian Eigenmaps (LE) algorithm. Firstly, the LE algorithm is used to reduce the dimension of original data by realizing the mapping from the high dimensional data to the low dimensional space. And then a specified window was drawn in the low dimensional space which was used to calculate the space distance from frames in the specified window to each frame in the former fragment. Finally we detected the similarity to get the final segmentation points, thus obtained motion clips with independent semantics. The validity of the segmentation method is verified by experiment. © 2017, Springer International Publishing AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Palmprint recognition with deep convolutional features 12th

Palmprint recognition with deep convolutional features

引用

12th Chinese conference on Advances in Image and Graphics Technologies, IGTA 2017

作者： Sun, Qiule Zhang, Jianxin Yang, Aoqi Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian Dalian China

ISBN: (纸本)9789811073885

Palmprint recognition has become popular and significant in many fields because of its high efficiency and accuracy in personal identification. In this paper, we present a scheme for palmprint features extraction based on deep convolutional neural network (CNN). The CNN, which naturally integrates low/mid/high-level feature, performs excellently in processing images, video and speech. We extract the palmprint features using the CNN-F architecture, and exactly evaluate the convolutional features from different layers in the network for both identification and verification tasks. The experimental results on public PolyU palmprint database illuminate that palmprint features from the CNN-F respectively achieve the optimal identification rate of 100% and verification accuracy of EER= 0.25%, which demonstrate the effectiveness and reliability of the proposed palmprint CNN features. © Springer Nature Singapore Pte Ltd. 2018.

关键词： Palmprint recognition

来源：评论

学校读者我要写书评

暂无评论

Hand Pose Estimation Using Convolutional Neural Networks and Support Vector Regression 12th

Hand Pose Estimation Using Convolutional Neural Networks and...

引用

12th International Conference on e-Learning and Games, Edutainment 2018

作者： Dong, Yufeng Lu, Jian Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China

ISBN: (纸本)9783030237110

In order to improve the accuracy of hand pose estimation from a depth image, a method based on convolutional neural network (CNN) is proposed in this paper. First of all, we modify the structure of traditional CNN to recognize the 3D joint locations from a depth image. By appending some shortcuts between layers, the proposed network increases the correlation between the front and back layers. This structure can avoid the information loss caused by the simple layer-by-layer transmission, and can improve the estimation accuracy effectively. Afterwards, the estimated joint locations continue to be inputted into a support vector regression (SVR) phase. The use of SVR can introduce the constraint of local joint information, which can get rid of those abnormal estimations further. Extensive experiments show that our method enables significant performance improvement over the-state-of-arts in the accuracy of hand pose estimation. © 2019, Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Research on Speech Synthesis Technology Based on Rhythm Embedding 3

Research on Speech Synthesis Technology Based on Rhythm Embe...

引用

2020 3rd International Conference on Computer Information Science and Artificial Intelligence, CISAI 2020

作者： Wu, Tianxin Zhao, Lasheng Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

In recent years, Text-To-Speech (TTS) technology has developed rapidly. People have also been paying more attention to how to narrow the gap between synthetic speech and real speech, hoping that synthesized speech can be integrated with real rhythm. A rhythmic feature embedding method for Text-To-Speech was proposed in this thesis based on Tacotron2 model, which has arisen in the field of TTS in recent years. Firstly, rhythmic feature extraction through World vocoder can reduce redundant information in rhythmic features. Then, rhythmic feature fusion based on Variational Auto-Encoder (VAE) network can enhance rhythmic information. Experiments are carried out on the data set LJSpeech-1.0, and then subjective evaluation and objective evaluation are carried out on the synthesized speech respectively. Compared with the comparative literature, the subjective blind hearing test (ABX) score increased by 25%. At that same time, the objective Mel Cepstral Distortion value (MCD) declined to 12.77. © Published under licence by IOP Publishing Ltd.

关键词： Speech synthesis

来源：评论

学校读者我要写书评

暂无评论

The decoder based on DNA strand displacement with improved "AND" gate and "OR" gate 1

引用

12th International Conference on Bio-Inspired computing: Theories and Applications, BIC-TA 2017

作者： Han, Weixuan Zhou, Changjun Wang, Xiaojun Zhang, Qiang Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

ISBN: (数字)9789811071799

ISBN: (纸本)9789811071782

In the computational biology, DNA strand displacement technique is used to construct the logic gate model and molecular circuits. But with the increase of number of the reaction strands, the basic logic gates cannot meet the accuracy in the reaction process. This paper improved the logical unit OR gate, AND gate to solve this problem on the basic of the seesaw model and the mechanism of DNA strand displacement reaction. Since the basic circuit of the decoder is an array of AND gates, the improvement module is applied to the decoder. The molecular circuit of decoder is constructed to realize the dynamic link between the input signal and the output signal. It is concluded that the sensitivity and accuracy of the improved decoder in the molecular circuit is improved by the Visual DSD software. The improvement module laid the foundation for the development of molecular circuits. © Springer Nature Singapore Pte Ltd 2017.

关键词： Logic gates

来源：评论

学校读者我要写书评

暂无评论

DNA self-assembly model to solve compound logic operators problem 11th

DNA self-assembly model to solve compound logic operators pr...

引用

11th International Conference on Bio-inspired computing – Theories and Applications, BIC-TA 2016

作者： Zhou, Shihua Wang, Bin Zheng, Xuedong Zhou, Changjun Key Laboratory of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China

ISBN: (纸本)9789811036101

Self-assembly is the process that the component form an ordered form or structure. Because of the biochemical characteristics of DNA molecules, they become a research emphasis in the field of selfassembly. DNA-based self-assembly technology has been widely used in the fields of nanometer machining, molecular circuit, polymer materials, and so on. DNA self-assembly is an effective mechanism that nanometer structure is built bottom-up. In order to overcome the problem that any kind of self-assembled model can only solve the single algorithm, in this paper, a new DNA self-assembly algorithmic model is designed to solve compound logic operators problem. Five types of DNA tiles are designed according to the characteristic of compound operation problem, namely Initial Tile, Process Tile, Operation Tile, End Tile and Boundary Tile. At last, the process of self-assembly are demonstrated by an instance. © Springer Nature Singapore Pte Ltd. 2016.

关键词： Self assembly

来源：评论

学校读者我要写书评

暂无评论

Sentence Alignment of Historical Classics based on Mode Prediction and Term Translation Pairs 3

Sentence Alignment of Historical Classics based on Mode Pred...

引用

3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing, CLP 2014

作者： Che, Chao Zheng, Xiaojun Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

Parallel corpora are essential resources for the construction of bilingual term dictionary of historical classics. To obtain large-scale parallel corpora, this paper proposes a sentence alignment method based on mode prediction and term translation pairs. On one hand, the method rebuilds the sentence alignment process according to characteristics of the translation of historical classics, and adds mode prediction into the sentence alignment. On the other hand, due to the lack of bilingual ancient Chinese dictionary, the method exploits the term translation pairs extracted from manually aligned sentence pairs to perform alignment. The method first predicts the alignment mode probability according to the character number, punctuation number and some characters of Chinese sentence, then performs sentence alignment using length alignment probability, term alignment probability and mode probability. Besides, the method selects anchor sentence pairs based on sentence length and predicted mode to prevent the spread of alignment errors. The experiment on "Shi Ji" demonstrates that mode prediction and term translation pair both enhance the performance of sentence alignment obviously. © 2014 CLP 2014 - 3rd CIPS-SIGHAN Joint Conference on Chinese Language Processing. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Term translation extraction from historical classics using modern Chinese explanation 17th

Term translation extraction from historical classics using m...

引用

17th China National Conference on Computational Linguistics, CCL 2018 and 6th International Symposium on Natural Language Processing Based on Naturally Annotated Big Data, NLP-NABD 2018

作者： Wu, Xiaoting Zhao, Hanyu Che, Chao Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University Dalian116622 China

ISBN: (纸本)9783030017156

Extracting term translation pairs is of great help for Chinese historical classics translation since term translation is the most time-consuming and challenging part in the translation of historical classics. However, it is tough to recognize the terms directly from ancient Chinese due to the flexible syntactic of ancient Chinese and the word segmentation errors of ancient Chinese will lead to more errors in term translation extraction. Considering most of the terms in ancient Chinese are still reserved in modern Chinese and the terms in modern Chinese are more easily to be identified, we propose a term translation extracting method using multi-features based on character-based model to extract historical term translation pairs from modern Chinese-English corpora instead of ancient Chinese-English corpora. Specifically, we first employ character-based BiLSTM-CRF model to identify historical terms in modern Chinese without word segmentation, which avoids word segmentation error spreading to the term alignment. Then we extract English terms according to initial capitalization rules. At last, we align the English and Chinese terms based on co-occurrence frequency and transliteration feature. The experiment on Shiji demonstrates that the performance of the proposed method is far superior to the traditional method, which confirms the effectiveness of using modern Chinese as a substitute. © Springer Nature Switzerland AG 2018.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Image encryption algorithm based on high-dimensional chaotic systems

Image encryption algorithm based on high-dimensional chaotic...

引用

2010 International Conference on intelligent Control and Information Processing, ICICIP 2010

作者： Yu, Wanbo Chi, Chunjian Wei, Xiaopeng Yang, Xuesong Key Laboratory of Advanced Design and Intelligent Computing Ministry of Education Dalian University DalianLiaoning 116622 China

ISBN: (纸本)9781424470488

In order to protect image effectively, presented an image encryption algorithm based on wavelet function and four-dimension chaotic system. The algorithm firstly uses Wavelet function chaotic maps to scramble the image pixel location, and then use four-dimension chaotic system disturbs image pixel value. Experimental results show that the algorithm has a good properties that Shannon proposes confusion and diffusion. At the same time, It can resist a strong attack with the large key space, encryption image pixel values has a random uniform distribution and adjacent pixels value has zero correlation. These results show that the proposed scheme has good security characteristics. © 2010 IEEE.

关键词： Chaotic systems

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

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：