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

Classification of Underwater Fish Image Based on Supervised Contrastive Learning 4

Classification of Underwater Fish Image Based on Supervised ...

引用

4th International Symposium on intelligent Robotics and Systems, ISoIRS 2024

作者： Yan, Qiankun Du, Xiujuan Qinghai Normal University Qinghai Provincial Key Laboratory of IoT College of Computer Xining China College of Computer Qinghai Normal University Qinghai Provincial Key Laboratory of IoT The State Key Laboratory of Tibetan Intelligent Information Processing and Application Xining China

ISBN: (纸本)9798350364798

Classification of underwater fish images is of great scientific research significance for assessing the ocean's health. However, compared with land-based optical images, underwater optical images are characterized by color distortion, low contrast, and high noise intensity, making it challenging to perform effective feature extraction and train a highly accurate recognition model for underwater images. This paper proposes a supervised contrastive learning-based classification method for underwater fish images. First, the residual idea is integrated to improve the representation of the last four stages of the residual network to obtain the stage residual network, which more fully utilizes the shallow features and reduces the risk of network overfitting at the same time;second, the channel attention mechanism is incorporated at the end of the last four stages of the backbone network, which prompts the model to pay more attention to the feature channels with high contribution;finally, the contrastive learning loss function is improved by the introduction of labels, and realizes the supervised contrastive learning. Dividing the backbone network and the classifier into two stages of training effectively closes the intra-class distance and distances the inter-class distance and improves the model's performance. The experimental results show that the accuracy, precision, recall, and F1 value of this paper's model on the public benchmark dataset Fish4Knowledge are 99.28%, 98.17%, 94.15%, and 95.71%, and it can realize the classification of underwater fish images under extreme noise conditions more efficiently. © 2024 IEEE.

关键词： Contrastive Learning

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

Real-time pricing method through market auction based on multi-agent reinforcement learning 8

Real-time pricing method through market auction based on mul...

引用

8th International Conference on Power and Renewable Energy, ICPRE 2023

作者： Hong, Peng He, Shuping Fang, Xiaohan Anhui University Key Laboratory of Intelligent Computing and Signal Processing of Ministry of Education School of Electrical Engineering and Automation Hefei230601 China

ISBN: (纸本)9798350328813

With the development of distributed energy systems, pricing different energy sources in microgrids has become a significant challenge. To solve this problem, this paper proposes an real-time pricing method through market auction based on multi-agent reinforcement learning. The energy supply side provides different energy production and quotations, while consumers on the energy demand side freely quote and purchase the required energy in the energy market based on their own needs. The final transaction price of different energy sources is determined by the quotes of the buyer and seller who have reached the transaction. The simulation results indicate that the proposed pricing method have a good performance. © 2023 IEEE.

关键词： Market auction Multi-agent reinforcement learning Real-time pricing

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

Weak Change Detection of Wide field Foggy Video Image 24

Weak Change Detection of Wide field Foggy Video Image

引用

4th International Conference on Artificial Intelligence, Big Data and Algorithms, CAIBDA 2024

作者： Li, Wen Jia, Zhenhong Song, Sensen Huang, Xiaohui Wang, Jiajia Zhou, Gang Shi, Fei School of Computer Science and Technology Xinjiang University Urumqi Xinjiang China Key Laboratory of Signal Detection and Processing Xinjiang University Urumqi Xinjiang China

ISBN: (纸本)9798400710247

Hawk-eye devices are often used in surveillance and security, and the video images collected by them have a wide field of view. Under foggy conditions, the video images captured by eagle-eye surveillance have low contrast and details are easily lost. In order to solve these problems, this paper proposes a change detection algorithm for foggy wide field video images based on the Discrete Wavelet Transform (DWT) image fusion and FCM clustering algorithm. Firstly, the improved neighborhood ratio operator and the most value mean pixel ratio operator are used to generate the disparity map, and then the DWT is used to fuse the disparity map, and after obtaining the fused disparity map, the soft threshold function and the FCM clustering algorithm are used to carry out the coarse classification and fine classification respectively, and obtain the final change detection result map. © 2024 Copyright held by the owner/author(s).

关键词： Discrete wavelet transforms

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

Sparsity-aware Subband Adaptive Filtering in Impulsive Interferences 7

Sparsity-aware Subband Adaptive Filtering in Impulsive Inter...

引用

7th IEEE International Conference on Electronic Information and Communication Technology, ICEICT 2024

作者： Gong, Zhikai Li, Yingsong Pang, Baohe Li, Xueyan Xiao, Wudang Li, Liping Zlatanov, Nikola Harbin Engineering University College of Information and Communication Engineering Harbin150001 China Ministry of Education Anhui University Key Laboratory of Intelligent Computing and Signal Processing China Innopolis University Faculty of Computer and Engineering Sciences Russia

ISBN: (纸本)9798350384437

In this paper, we propose two new subband adaptive filtering (SAF) algorithms based on the cost function of the logistic distance metric cost function and use the proportionate proximal gradient algorithm to exploit the sparsity of the system fully. Compared with prior works, the proposed algorithms can handle many different situations better. Through computer simulations, we prove that the algorithm performs excellently in sparse systems disturbed by impulse noises. The algorithm can be used in areas like system identifications. © 2024 IEEE.

关键词： Adaptive filtering

来源：评论

学校读者我要写书评

暂无评论

intelligent Innovation Dataset on Scientific Research Outcomes and Patents

引用

Journal of Social Computing 2025年第1期6卷 63-73页

作者： Wu, Xinran Zou, Hui Xing, Yidan Qu, Jingjing Guo, Weiwei Fu, Xiaoming School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Shanghai University Department of Library and Information Science Shanghai200444 China Big Data Technology Co. Ltd. Shanghai200082 China Shanghai Artificial Intelligence Laboratory Shanghai200082 China Fudan University Department of Management Shanghai200433 China Fudan University Shanghai Key Laboratory of Intelligent Information Processing Shanghai200433 China Institute of Computer Science University of Göttingen Göttingen37073 Germany

Various stakeholders, such as researchers, government agencies, businesses, and research laboratories require a large volume of reliable scientific research outcomes including research articles and patent data to support their work. These data are crucial for a variety of application, such as advancing scientific research, conducting business evaluations, and undertaking policy analysis. However, collecting such data is often a time-consuming and laborious task. Consequently, many users turn to using openly accessible data for their research. However, these existing open dataset releases typically suffer from lack of relationship between different data sources and a limited temporal coverage. To address this issue, we present a new open dataset, the intelligent Innovation Dataset (IIDS), which comprises six interrelated datasets spanning nearly 120 years, encompassing paper information, paper citation relationships, patent details, patent legal statuses, and funding information. The extensive contextual and extensive temporal coverage of the IIDS dataset will provide researchers and practitioners and policy maker with comprehensive data support, enabling them to conduct indepth scientific research and comprehensive data analyses. © 2020 Tsinghua University Press.

关键词： Decentralized finance

来源：评论

学校读者我要写书评

暂无评论

IDENTIFYMIX: AN EFFICIENT TWO-STAGE LEARNING APPROACH TO COMBATING LABEL NOISE

Journal of Applied and Numerical Optimization

引用

Journal of Applied and Numerical Optimization 2023年第2期5卷 237-253页

作者： Tong, Kai Ke, Xiao Fujian Provincial Key Laboratory of Networking Computing and Intelligent Information Processing College of Computer and Data Science Fuzhou University Fuzhou350116 China Key Laboratory of Spatial Data Mining & Information Sharing Ministry of Education Fuzhou350003 China

Deep neural networks require correct label annotation during supervised learning. It is inevitable, however, that some labels are noisy during the labeling process. A deep neural network retains incorrect labels during training, resulting in a degradation of performance. Therefore, it is essential to identify samples with potentially correct labels. In state-of-the-art methods, small-loss samples are chosen for subsequent training through a sample selection strategy. Howerver, it typically ignores the imbalance in noise ratios between mini-batches when performing sample selection within each minibatch. Further, numerous valuable samples with high losses are discarded, which adversely affects the generalization performance of the model, particularly under conditions of high noise ratios. To this end, this paper proposes IdentifyMix, an effective two-stage learning approach for noisy robust learning that combines an unique sample selection strategy and the semi-supervised learning technique. By observing how the dynamics of network training are changing, AUM (Area Under the Margin) provides a criterion that is applied in this research to identify mislabeled data. Moreover, by combining semi-supervised learning with contrastive learning and data augmentation, it is possible to extract more useful information from mislabeled samples. Experiments on several synthetic and real-world noise benchmarks demonstrate the effectiveness of IdentifyMix compared with state-of-the-art methods. © 2023 Journal of Applied and Numerical Optimization.

关键词： Image classification

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：