检索结果-内蒙古大学图书馆

5th International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2024

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

ISBN: (纸本)9798331506612

In the research methods of sentence similarity, sentence similarity is often calculated from the semantic aspect, while the influence of syntactic structure is ignored. We propose an enhanced knowledge language representation model (ExtKBRCNN) based on CNN and Bi-GRU, which effectively uses the fine-grained word relations in the knowledge base to evaluate semantic similarity and models the relationship between knowledge structure and text structure. In order to make full use of the syntactic information of the sentence, we also propose a dependency tree kernel-based method (Dep-SIF), which combines syntactic information and semantic features to evaluate syntactic similarity. Finally, we propose a comprehensive model that integrates semantic and syntactic information to comprehensively evaluate sentence similarity. Experimental results show that the accuracy of the model on the MRPC dataset is 77.63% and the F1 value is 83.90%. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Grammatical Error Correction Model 5

Context-Aware Grammatical Error Correction Model

引用

5th International Conference on Big Data and Artificial Intelligence and Software Engineering, ICBASE 2024

作者： Lin, Jianxing Huang, Guimin Wang, JiaHao Guilin University of Electronic Technology School of Computer Science and Information Security Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guilin China

ISBN: (纸本)9798331506612

The pursuit of accurate and fluent English communication is the cornerstone of global academic exchange and expression. The accuracy of written English is crucial for effective discourse;however, despite advancements in grammatical error correction (GEC) technology, these systems often fall short when analyzing coherent text. This paper delves into the complexities of English writing and the challenges posed by current GEC systems, advocating for a shift toward understanding document-level context in error correction. We propose a dual-encoder architecture within an encoder-decoder model, referred to as the Context-Aware Grammatical Error Correction (CAGEC) model. The CAGEC model employs an innovative dual-encoder structure, combining the encoder of the Transformer model with a Bi-GRU (Bidirectional Gated Recurrent Unit) neural network, and integrates encoding into the decoder through attention and gating mechanisms to achieve a deep understanding of the source sentence and its context. © 2024 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Identity Manipulation for Face Inpainting 24

Audio-Driven Identity Manipulation for Face Inpainting

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Sun, Yuqi Lin, Qing Tan, Weimin Yan, Bo Shanghai Key Laboratory of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Singapore Nanyang Technological University Singapore

ISBN: (纸本)9798400706868

Recent advances in multimodal artificial intelligence have greatly improved the integration of vision-language-audio cues to enrich the content creation process. Inspired by these developments, in this paper, we first integrate audio into the face inpainting task to facilitate identity manipulation. Our main insight is that a person's voice carries distinct identity markers, such as age and gender, which provide an essential supplement for identity-aware face inpainting. By extracting identity information from audio as guidance, our method can naturally support tasks of identity preservation and identity swapping in face inpainting. Specifically, we introduce a dual-stream network architecture comprising a face branch and an audio branch. The face branch is tasked with extracting deterministic information from the visible parts of the input masked face, while the audio branch is designed to capture heuristic identity priors from the speaker's voice. The identity codes from two streams are integrated using a multi-layer perceptron (MLP) to create a virtual unified identity embedding that represennts comprehensive identity features. In addition, to explicitly exploit the information from audio, we introduce an audio-face generator to generate an 'fake' audio face directly from audio and fuse the multi-scale intermediate features from the audio-face generator into face inpainting network through an audio-visual feature fusion (AVFF) module. Extensive experiments demonstrate the positive impact of extracting identity information from audio on face inpainting task, especially in identity preservation. © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

UAV-Assisted Dynamic Avatar Task Migration for Vehicular Metaverse Services: A Multi-Agent Deep Reinforcement Learning Approach

引用

IEEE/CAA Journal of Automatica Sinica 2024年第2期11卷 430-445页

作者： Jiawen Kang Junlong Chen Minrui Xu Zehui Xiong Yutao Jiao Luchao Han Dusit Niyato Yongju Tong Shengli Xie IEEE School of Automation Guangdong University of TechnologyGuangzhou 510006China 111 Center for Intelligent Batch Manufacturing based on IoT Technology Guangzhou 510006China Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of EducationGuangzhou 510006China School of Computer Science and Engineering Nanyang Technological UniversitySingaporeSingapore Pillar of Information Systems Technology and Design Singapore University of Technology and DesignSingaporeSingapore College of Communication Engineering Army Engineering University of PLANanjing 210007China National Natural Science Foundation of China Beijing 100085China Key Laboratory of Intelligent Detection and IoT in Manufacturing Ministry of EducationGuangzhou 510006China Guangdong Key Laboratory of IoT Information Technology Guangzhou 510006China

Avatars, as promising digital representations and service assistants of users in Metaverses, can enable drivers and passengers to immerse themselves in 3D virtual services and spaces of UAV-assisted vehicular Metaverses. However, avatar tasks include a multitude of human-to-avatar and avatar-to-avatar interactive applications, e.g., augmented reality navigation,which consumes intensive computing resources. It is inefficient and impractical for vehicles to process avatar tasks locally. Fortunately, migrating avatar tasks to the nearest roadside units(RSU)or unmanned aerial vehicles(UAV) for execution is a promising solution to decrease computation overhead and reduce task processing latency, while the high mobility of vehicles brings challenges for vehicles to independently perform avatar migration decisions depending on current and future vehicle status. To address these challenges, in this paper, we propose a novel avatar task migration system based on multi-agent deep reinforcement learning(MADRL) to execute immersive vehicular avatar tasks dynamically. Specifically, we first formulate the problem of avatar task migration from vehicles to RSUs/UAVs as a partially observable Markov decision process that can be solved by MADRL algorithms. We then design the multi-agent proximal policy optimization(MAPPO) approach as the MADRL algorithm for the avatar task migration problem. To overcome slow convergence resulting from the curse of dimensionality and non-stationary issues caused by shared parameters in MAPPO, we further propose a transformer-based MAPPO approach via sequential decision-making models for the efficient representation of relationships among agents. Finally, to motivate terrestrial or non-terrestrial edge servers(e.g., RSUs or UAVs) to share computation resources and ensure traceability of the sharing records, we apply smart contracts and blockchain technologies to achieve secure sharing management. Numerical results demonstrate that the proposed approach

关键词： Avatar blockchain metaverses multi-agent deep reinforcement learning transformer UAVs

来源：评论

学校读者我要写书评

暂无评论

Robust facial landmark detection network based on multiscale attention residual blocks 12

Robust facial landmark detection network based on multiscale...

引用

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Zou, Lamei Xie, Jia Wang, Hao Lu, Luhan Wu, Chengqing Guo, Yichun Zhang, Tianbao National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

We present a robust facial landmark detection network based on multiscale attention residual blocks (MARBNet) for effectively predicting facial landmark. MARBNet consists of three modules. Firstly, the coarse feature extraction module obtains coarse features through convolution, batch normalization, ReLU activation, and maximum pooling. The fine feature extraction module is composed of 33 multiscale attention residual blocks (MARB). MARB is composed of 1x1 convolution layer, 3x3 convolution layer, 1x1 convolution layer, two multiscale convolution module(MulRes) and channel attention module(CAM). MulRes is used to extract complementary features of different scales, obtain more feature information under different Receptive field, and avoid excessive loss of key information in the input image. CAM enables the network to pay more attention to high-frequency information on the channel, effectively prevents the loss of information, so as to improve the effect of facial landmark detection. The output module consists of two 1x1 convolution layers, one of which outputs landmark heatmap score and landmark coordinate offset, and the other outputs the nearest neighbor landmark offset. The experiment results on WFLW and 300W datasets show that our method is superior to the existing algorithms in terms of normalized mean square error indicators. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Design of Welding Robot control System based on Visual Recognition Technology 23

Design of Welding Robot Control System based on Visual Recog...

引用

3rd International Conference on Robotics and control Engineering, RobCE 2023

作者： Han, Yu Han, Xu Guo, Xiaoqian Yang, Li Guo, Tinghang Qin, Zhuanping Zhao, Zhuangzhuang Tianjin Key Laboratory of Information Sensing and Intelligent Control Tianjin University of Technology and Education China

ISBN: (纸本)9781450398107

The level of industrial automation has gradually improved in recent years. Various industries gradually realize automatic welding through the combination of robot system and field equipment. To overcome the defects of traditional welding process, such as high labor costs, low safety, low welding efficiency, and unstable welding quality, a welding robot control system based on visual recognition technology is designed. The system includes three modules, namely visual module, control module and execution module. By Combining visual recognition technology, through the weld image feature measurement and processing method, the system can achieve functions such as weld image acquisition and recognition, weld feature point extraction, welding robot motion trajectory planning, and welding motion control. The system can make the welding quality and efficiency higher and is an automatic innovation of industrial welding technology. © 2023 ACM.

关键词： Quality control

来源：评论

学校读者我要写书评

暂无评论

SPIKING CONVOLUTIONAL NEURAL NETWORKS FOR TEXT CLASSIFICATION 11

SPIKING CONVOLUTIONAL NEURAL NETWORKS FOR TEXT CLASSIFICATIO...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Lv, Changze Xu, Jianhan Zheng, Xiaoqing School of Computer Science Fudan University Shanghai 200433 China Shanghai Key Laboratory of Intelligent Information Processing

Spiking neural networks (SNNs) offer a promising pathway to implement deep neural networks (DNNs) in a more energy-efficient manner since their neurons are sparsely activated and inferences are event-driven. However, there have been very few works that have demonstrated the efficacy of SNNs in language tasks partially because it is non-trivial to represent words in the forms of spikes and to deal with variable-length texts by SNNs. This work presents a "conversion + fine-tuning" two-step method for training SNNs for text classification and proposes a simple but effective way to encode pre-trained word embeddings as spike trains. We show empirically that after fine-tuning with surrogate gradients, the converted SNNs achieve comparable results to their DNN counterparts with much less energy consumption across multiple datasets for both English and Chinese. We also show that such SNNs are more robust to adversarial attacks than DNNs. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Edge computing aileron mechatronics using antiphase hysteresis Schmitt trigger for fast flutter suppression

引用

control Theory and Technology 2025年第1期23卷 153-160页

作者： Tangwen Yin Dan Huang Xiaochun Zhang Department of Automation Shanghai Jiao Tong Universityand Key Laboratory of System Control and Information Processing of Ministry of EducationShanghai200240China School of Aeronautics and Astronautics Shanghai Jiao Tong UniversityShanghai200240China Control Division Shanghai Aircraft Design and Research InstituteShanghai200210China

An aileron is a crucial control surface for *** jitter or shaking caused by the aileron mechatronics could have catastrophic consequences for the aircraft’s stability,maneuverability,safety,and *** paper presents a robust solution in the form of a fast flutter suppression digital control logic of edge computing aileron mechatronics(ECAM).We have effectively eliminated passive and active oscillating response biases by integrating nonlinear functional parameters and an antiphase hysteresis Schmitt *** findings demonstrate that self-tuning nonlinear parameters can optimize stability,robustness,and *** the same time,the antiphase hysteresis Schmitt trigger effectively rejects flutters without the need for collaborative navigation and *** hardware-in-the-loop simulation results confirm that this approach can eliminate aircraft jitter and shaking while ensuring expected stability and *** conclusion,this nonlinear aileron mechatronics with a Schmitt positive feedback mechanism is a highly effective solution for distributed flight control and active flutter rejection.

关键词： Aileron Edge computing Flutter suppression Mechatronics Nonlinear hysteresis control Positive feedback

来源：评论

学校读者我要写书评

暂无评论

Cluster routing algorithm based on agglomerative hierarchical clustering in wireless sensor networks

Cluster routing algorithm based on agglomerative hierarchica...

引用

2023 International Conference on intelligent Systems, Communications, and Computer Networks, ISCCN 2023

作者： Li, Hongbing Cui, Hao Ou, Jun Wang, Yuning Key Laboratory of Intelligent Information Processing Control of Chongqing Three Gorges University China Chongqing Key Laboratory of Geological Environment Monitoring Disaster Early Warning in Three Gorges Reservoir Area China Internet of Things and Intelligent Control Technology Chongqing Engineering Research Center China

ISBN: (纸本)9781510666238

To save the energy and extend the lifetime of the network, Cluster Routing Algorithm based on Agglomerative Hierarchical Clustering (CRAAHC) is proposed in wireless sensor networks. WSN is divided into a certain quantity of ring areas based on the energy consumption model. Clustering process is optimized by constraining the distance between clusters and the diameter of clusters to improve the quality of clustering algorithm. Cluster head selection strategy is improved by considering the residual energy of the node and energy consumption in communication with other nodes in one cluster. Simulation results show that CRAAHC algorithm can achieve energy efficiency and routing reliability. © 2023 SPIE.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Human pose estimation constrained by human structure information 12

Human pose estimation constrained by human structure informa...

引用

SPIE 12th International Symposium on Multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Zou, Lamei Wang, Hao Xie, Jia Wu, Chengqing Lu, Luhan Guo, Yichun National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674967

ISBN: (纸本)9781510674950

We present a two-dimensional human pose estimation network constrained by the human structure information (HSINet). HSINet effectively fuses features of different scales and explicitly integrates human structure information to enhance the precision of key point localization. The architecture of HSINet comprises three pivotal modules: The feature extraction module, the encoding module, and the decoding module. The feature extraction module within HSINet employs the architecture of High-Resolution Net (HRNet). In contrast to HRNet, we remove redundant layers, and enhance the ability to combine global features and local features using the Gated Attention Unit (GAU). The second module encodes the feature maps derived from the feature extraction module. Each feature map corresponds to a joint point and is characterized by two feature vectors representing the x and y axes. Utilizing graph convolution for encoding introduces constraints based on human structure information. Subsequently, these encoded feature maps are decoded into precise coordinates of key points. The experiment results on COCO datasets show that our proposed method can improve the precision of key point detection while effectively reducing the number of parameters. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

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：