检索结果-内蒙古大学图书馆

Knowledge Graph Augmented network Towards Multiview Representation Learning for Aspect-Based Sentiment Analysis

IEEE Transactions on Knowledge and Data Engineering 2023年第10期35卷 10098-10111页

作者： Zhong, Qihuang Ding, Liang Liu, Juhua Du, Bo Jin, Hua Tao, Dacheng Wuhan University National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence School of Computer Science Hubei Key Laboratory of Multimedia and Network Communication Engineering Hubei Wuhan430072 China Jd Explore Academy at *** Beijing100101 China Wuhan University Research Center for Graphic Communication Printing and Packaging Institute of Artificial Intelligence Hubei Wuhan430072 China Hospital of Kunming University of Science and Technology Kunming650032 China

Aspect-based sentiment analysis (ABSA) is a fine-grained task of sentiment analysis. To better comprehend long complicated sentences and obtain accurate aspect-specific information, linguistic and commonsense knowledge are generally required in this task. However, most current methods employ complicated and inefficient approaches to incorporate external knowledge, e.g., directly searching the graph nodes. Additionally, the complementarity between external knowledge and linguistic information has not been thoroughly studied. To this end, we propose a knowledge graph augmented network (KGAN), which aims to effectively incorporate external knowledge with explicitly syntactic and contextual information. In particular, KGAN captures the sentiment feature representations from multiple different perspectives, i.e., context-, syntax- and knowledge-based. First, KGAN learns the contextual and syntactic representations in parallel to fully extract the semantic features. Then, KGAN integrates the knowledge graphs into the embedding space, based on which the aspect-specific knowledge representations are further obtained via an attention mechanism. Last, we propose a hierarchical fusion module to complement these multi-view representations in a local-to-global manner. Extensive experiments on five popular ABSA benchmarks demonstrate the effectiveness and robustness of our KGAN. Notably, with the help of the pretrained model of RoBERTa, KGAN achieves a new record of state-of-the-art performance among all datasets. © 1989-2012 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Research on optical microfiber pressure sensor applied in marine field 4

Research on optical microfiber pressure sensor applied in ma...

引用

4th Optics Young Scientist Summit, OYSS 2020

作者： Zhou, Lingjun Yao, Sijia Huang, Huimin Yang, Junbo Zhang, Zhenrong Yu, Yang Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronic and Information Guangxi University Nanning530004 China Center of Material Science College of Liberal Arts and Sciences National University of Defense Technology Changsha410073 China Hunan University of information technology Changsha Hunan Province410151 China

ISBN: (数字)9781510643970

ISBN: (纸本)9781510643963

A novel and compact pressure sensor for marine application based on optical microfiber coupler interferometer(OMCI) is proposed theoretically. We theoretically analyzed the characteristics of OMCI's dual sensing unit, The highest pressure sensitivity of the waist sensing unit is 654pm/Mpa, and it increases with longer wavelength. The pressure sensitivity of the interference arm sensing unit is 7pm/Mpa, the sensitivity increases with the length of the embedded elastomer. Its excellent performance can provide strong theoretical guidance for the practical application of optical ocean monitoring equipment. © SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Pressure sensors

来源：评论

学校读者我要写书评

暂无评论

Predicting the Unseen: A Novel Dataset for Hidden Intention Localization in Pre-abnormal Analysis 24

Predicting the Unseen: A Novel Dataset for Hidden Intention ...

引用

32nd ACM International Conference on multimedia, MM 2024

作者： Qi, Zehao Zhang, Ruixu Hu, Xinyi Liu, Wenxuan Wang, Zheng National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science Wuhan China School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China

ISBN: (纸本)9798400706868

Our paper introduces a novel video dataset specifically for Temporal Intention Localization (TIL), aimed at identifying hidden abnormal intention in densely populated and complex environments. Traditional Temporal Action Localization (TAL) frameworks, focusing on overt actions within constrained temporal intervals, often miss subtle pre-abnormal actions that unfold over extended periods. Our dataset comprises 228 videos with 5790 clips, each annotated to capture fine-grained actions within ambiguous temporal boundaries using the Joint-Linear-Assignment methodology. This approach enables detailed analysis of the evolution of abnormal intention over time. To detect subtle, hidden intention, we developed the Intention-Action Fusion module, an creative approach integrating dynamic feature fusion across 11 behavioral subcategories, significantly enhancing the model's ability to discern nuanced intention. This enhancement has led to performance improvements of up to 139% in specific scenarios, dramatically boosting the model's sensitivity and interpretability, crucial for advancing proactive surveillance systems. By pushing the boundaries of technology, our dataset and methodologies foster proactive surveillance systems capable of preemptively identifying potential threats from nuanced behavioral patterns, encouraging further exploration into the complexities of intention beyond observable actions. The dataset is available at https://***/Zzz99999/Hidden-Abnormal-Intention. © 2024 ACM.

关键词： Security systems

来源：评论

学校读者我要写书评

暂无评论

scIAC: clustering scATAC-seq data based on Student's t-distribution similarity imputation and denoising autoencoder

scIAC: clustering scATAC-seq data based on Student's t-distr...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Lan, Wei Ye, Jin Sun, Xun Zhu, Xiaoshu Chen, Qingfeng Pan, Yi Guangxi University School of Computer Electronic and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning China School of Computer Electronic and Information Guangxi University Nanning China Yulin Normal University School of Computer Science and Engineering Yulin China School of Computer Science and Control Engineering Shenzhen Institute of Advanced Technology Shenzhen China

ISBN: (纸本)9781665468190

Assay of single cell transposase-accessible chromatin with high-throughput sequencing (scATAC-seq) have enabled massively profiling of the chromatin accessibility landscape at the single-cell level. The essential step in analyzing scATAC-seq data is to cluster the cells into different clusters and utilize the clustering information in the subsequent downstream analysis. However, there are some challenges in the clustering analysis of scATAC-seq data. For example, scATAC-seq data are often high-dimensional and extremely sparse, as well as featuring high loss rate or noise. In this study, we proposed the scIAC to address these challenges of scATACseq data. In particular, scIAC combines the Student's t-distribution similarity imputation and the denoising autoencoder based on the Zero-inflated Negative Binomial (ZINB) distribution. The Student's t-distribution similarity imputation is used to solve the problem of high sparsity and high loss rate. The denoising autoencoder is employ to extract features which are useful for clustering and to reduce data noises. In addition, the self-training soft K-means and pairwise constraints are utilized in the clustering phase to enhance clustering performance. The experimental validation on several datasets shows that the proposed method performed better than other state-of-the-art methods. In conclusion, scIAC is an effective method to accurately cluster and identify cell types in scATAC-seq data. © 2022 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

The effect of cross-correlation items on the intersystem interference between GPS,BDS and Galileo

The effect of cross-correlation items on the intersystem int...

引用

第八届中国卫星导航学术年会

作者： Bingxue CHEN Xufang HUANG Xuyang WANG Tangchao LI Guangxi Colleges and Universities Key Laboratory of Satellite Navigation and Position sensing Guangxi Key Laboratory of multimedia communications and network technology College of Computer and Information Engineering Guangxi University

ISBN: (纸本)9789811045905

The spectrum of four global satellite navigation systems allocated on the L1 band are severely overlapped, which makes signal interfere *** carrier power-to-noise density ratio(（C/N）) and its degradation are important criteria to evaluate the degree of interference between Global Navigation Satellite Systems（GNSS）.In order to simplify the analysis process and computational complexity, the cross-correlation items between desired signal and interference signals outputted from the receiver are ignored when calculating（C/N）.In order to estimate how much deviation would be caused by ignoring the cross-correlation items, the power spectrum density（PSD） of cross-correlation items have been derived, and a new calculation formula of（C/N） considering the influence of cross-correlation items have been given, then the simulated results of intarsystem interference of GPS, BDS and Galileo were presented, and the results of intersystem interference between GPS, BDS and Galileo were also presented.

关键词： GNSS Radio Frequency Compatibility cross-correlation function carrier power-to-noise density ratio

来源：评论

学校读者我要写书评

暂无评论

Improving Cross-modal Alignment with Synthetic Pairs for Text-only Image Captioning

arXiv

引用

arXiv 2023年

作者： Liu, Zhiyue Liu, Jinyuan Ma, Fanrong School of Computer Electronics and Information Guangxi University Nanning China Guangxi Key Laboratory of Multimedia Communications and Network Technology China

Although image captioning models have made significant advancements in recent years, the majority of them heavily depend on high-quality datasets containing paired images and texts which are costly to acquire. Previous works leverage the CLIP’s cross-modal association ability for image captioning, relying solely on textual information under unsupervised settings. However, not only does a modality gap exist between CLIP text and image features, but a discrepancy also arises between training and inference due to the unavailability of real-world images, which hinders the cross-modal alignment in text-only captioning. This paper proposes a novel method to address these issues by incorporating synthetic image-text pairs. A pre-trained text-to-image model is deployed to obtain images that correspond to textual data, and the pseudo features of generated images are optimized toward the real ones in the CLIP embedding space. Furthermore, textual information is gathered to represent image features, resulting in the image features with various semantics and the bridged modality gap. To unify training and inference, synthetic image features would serve as the training prefix for the language decoder, while real images are used for inference. Additionally, salient objects in images are detected as assistance to enhance the learning of modality alignment. Experimental results demonstrate that our method obtains the state-of-the-art performance on benchmark datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Nonlinear Prediction with Deep Recurrent Neural networks for Non-Blind Audio Bandwidth Extension

引用

China communications 2018年第4期15卷 72-85页

作者： Lin Jiang Ruimin Hu Xiaochen Wang Weiping Tu Maosheng Zhang National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan 430072 China Institute of Big Data and internet Innovation Hunan University of Commerce Changsha 410205 China Software College East China University of Technology Nanchang 330013 China Collaborative Innovation Center for Economics crime investigation and prevention technology Jiangxi Province Nanchang 330103China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan 430072 China Collaborative Innovation Center of Geospatial Technology Wuhan 430079 China

Non-blind audio bandwidth extension is a standard technique within contemporary audio codecs to efficiently code audio signals at low bitrates. In existing methods, in most cases high frequencies signal is usually generated by a duplication of the corresponding low frequencies and some parameters of high frequencies. However, the perception quality of coding will significantly degrade if the correlation between high frequencies and low frequencies becomes weak. In this paper, we quantitatively analyse the correlation via computing mutual information value. The analysis results show the correlation also exists in low frequency signal of the context dependent frames besides the current frame. In order to improve the perception quality of coding, we propose a novel method of high frequency coarse spectrum generation to improve the conventional replication method. In the proposed method, the coarse high frequency spectrums are generated by a nonlinear mapping model using deep recurrent neural network. The experiments confirm that the proposed method shows better performance than the reference methods.

关键词： audio coding non-blind audiobandwidth extension context correlation deeprecurrent neural network

来源：评论

学校读者我要写书评

暂无评论

Construction of Virtual Backbones with Edge Fault Tolerance in Wireless networks with Multiple communication Modes

引用

IEEE Transactions on communications 2024年

作者： Liang, Xinyu Liang, Jiarong Zhang, Weiguang School of Artificial Intelligence Guangxi Minzu University 530004 China School of Computer Electronics and Information Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University 530004 China

Over the years, wireless networks (WNs) with multiple communication modes, such as hybrid WNs, have attracted much attention. Generally, a WN with a single communication mode can be abstracted as a unit disk graph (UDG). For a WN with multiple communication modes, there may exist two or more communication modes between two different nodes, and a UDG may not be able to abstract such a WN accurately. This paper proposes a new model called a p-quasi disk graph (p-QDG) to abstract such WNs with multiple communication modes and investigates the problem of edge fault tolerance in p-QDGs. In this paper, we introduce the concept of a k-edge-connected m-edge-dominated set (in short, (k, m)-ECDS) in a p-QDG, which can be used to abstract virtual backbones (VBs) with link fault tolerance in WNs abstracted by p-QDGs. Using the concept of a (k, m)-ECDS, we design an approximation algorithm with a performance ratio of 5(k−1) ∗ (m + 2) ∗ max{5p/m, 1} for the minimum (k, m)-ECDS problem in p-QDGs. Our simulations show that our proposed algorithm is better than the existing related algorithms in terms of CDS size, running time and success rate. © 2024 IEEE.

关键词： edge fault tolerance k-edge-connected m-edge-dominating set multigraph performance ratio wireless network

来源：评论

学校读者我要写书评

暂无评论

Guarding Quantum key Distribution with integrated Magnetic-free Nonreciprocal Structures

arXiv

引用

arXiv 2023年

作者： Liu, Qiang Huang, Yinming Luo, Tingting Huang, Chunfeng Geng, Minming Zhang, Zhenrong Wei, Kejin Guangxi Key Laboratory of Multimedia Communications and Network Technology School of Computer Electronics and Information Guangxi University Nanning China Guangxi Key Laboratory for Relativistic Astrophysics School of Physical Science and Technology Guangxi University Nanning China

Inserting nonreciprocal devices at the doorways of Alice and Bob is a widely recognized countermeasure against quantum hacking attacks in quantum key distribution (QKD) systems. However, traditional integrated nonreciprocal devices, which are typically based on magneto-optical effects, face challenges in compatibility with current semiconductor integration technology. As a result, earlier chip-based QKD systems were unable to integrate nonreciprocal components and were vulnerable to injecting-type attacks. Based on the actual parameters of SOI integration, we employed the inverse design with the direct binary search algorithm to construct several magnetic-free nonreciprocal devices, facilitating their integration into chip-based QKD systems while meeting various chip configuration design requirements. The designed devices have sizes of only a few square micrometers, yet the quasi-isolator can achieve an isolation level exceeding 27 dB. To demonstrate their practical utility in QKD, we employed the designed devices to safeguard the QKD system against Trojan-horse attacks. The simulation results demonstrate that our proposed devices effectively secure the BB84 and measure-device-independent QKD systems against Trojan-horse attacks. © 2023, CC BY.

关键词： Integration

来源：评论

学校读者我要写书评

暂无评论

Lightweight Color Image Demosaicking with Multi-Core Feature Extraction

Lightweight Color Image Demosaicking with Multi-Core Feature...

引用

IEEE Visual communications and Image Processing (VCIP)

作者： Yufei Tan Kan Chang Hengxin Li Zhenhua Tang Tuanfa Qin School of Computer and Electronic Information Guangxi University Nanning China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi University Nanning China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

Convolutional neural network (CNN)-based color image demosaicking methods have achieved great success recently. However, in many applications where the computation resource is highly limited, it is not practical to deploy large-scale networks. This paper proposes a lightweight CNN for color image demosaicking. Firstly, to effectively extract shallow features, a multi-core feature extraction module, which takes the Bayer sampling positions into consideration, is proposed. Secondly, by taking advantage of inter-channel correlation, an attention-aware fusion module is presented to efficiently reconstruct the full color image. Moreover, a feature enhancement module, which contains several cascading attention-aware enhancement blocks, is designed to further refine the initial reconstructed image. To demonstrate the effectiveness of the proposed network, several state-of-the-art demosaicking methods are compared. Experimental results show that with the smallest number of parameters, the proposed network outperforms the other compared methods in terms of both objective and subjective qualities.

关键词： Feature extraction Image reconstruction Convolution Iron Image color analysis Color Training

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：