检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Zhu, Guangxu Lyu, Zhonghao Jiao, Xiang Liu, Peixi Chen, Mingzhe Xu, Jie Cui, Shuguang Zhang, Ping Shenzhen Research Institute of Big Data Shenzhen518172 China Shenzhen518172 China State Key Laboratory of Advanced Optical Communication Systems and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering Institute for Data Science and Computing University of Miami Coral Gables33146 United States State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China Peng Cheng Laboratory Shenzhen518066 China

Pushing artificial intelligence (AI) from central cloud to network edge has reached board consensus in both industry and academia for materializing the vision of artificial intelligence of things (AIoT) in the sixth-generation (6G) era. This gives rise to an emerging research area known as edge intelligence, which concerns the distillation of human-like intelligence from the huge amount of data scattered at wireless network edge. In general, realizing edge intelligence corresponds to the process of sensing, communication, and computation, which are coupled ingredients for data generation, exchanging, and processing, respectively. However, conventional wireless networks design the sensing, communication, and computation separately in a task-agnostic manner, which encounters difficulties in accommodating the stringent demands of ultra-low latency, ultra-high reliability, and high capacity in emerging AI applications such as auto-driving. This thus prompts a new design paradigm of seamless integrated sensing, communication, and computation (ISCC) in a task-oriented manner, which comprehensively accounts for the use of the data in the downstream AI applications. In view of its growing interest, this article provides a timely overview of ISCC for edge intelligence by introducing its basic concept, design challenges, and enabling techniques, surveying the state-of-the-art development, and shedding light on the road ahead. Copyright © 2022, The Authors. All rights reserved.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

FERI: Feature Enhancement and Relational Interaction for Image-text Matching

FERI: Feature Enhancement and Relational Interaction for Ima...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Shuo Zhao Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Image-text matching is an important problem at the intersection of computer vision and natural language processing. It aims to establish the semantic link between image and text to achieve high-quality semantic alignment between the two modalities. However, the existing methods have the problem that the meaning expressed in the image or the complex narrative in the text cannot be fully understood due to insufficient feature extraction. Moreover, due to the essential modal differences between images and texts, how to effectively and accurately align the semantic contents in images and texts has become the key of research. In order to solve the above problems, this paper proposes a method based on feature enhancement and relationship interaction. When processing images, the proposed method fuses labeled features, region features and location features to represent images. When processing text, a combination of Bi-GRU and self-attention mechanism is used to represent the text. In order to further align the semantic content in images and texts accurately, this paper improves two relational interaction mechanisms by identifying connection relationships and learning association relationships. Thus, the relation enhanced embedding is obtained. Finally, it calculated the similarity of the enhanced embedding to judge the matching degree of the image and text. Extensive experiments on the public datasets Flickr30K and MSCOCO demonstrate the effectiveness of our method.

关键词： Computer vision Fuses Image matching Semantics Feature extraction Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Cross-modal knowledge distillation method for automatic cued speech recognition

arXiv

引用

arXiv 2021年

作者： Wang, Jianrong Tang, Ziyue Li, Xuewei Yu, Mei Fang, Qiang Liu, Li College of Intelligence and Computing Tianjin University Tianjin China Tianjin International Engineering Institute Tianjin University Tianjin China Institute of Linguistics Chinese Academy of Social Science Beijing China Shenzhen Research Institute of Big Data Chinese University of Hong Kong Shenzhen Hong Kong

Cued Speech (CS) is a visual communication system for the deaf or hearing impaired people. It combines lip movements with hand cues to obtain a complete phonetic repertoire. Current deep learning based methods on automatic CS recognition suffer from a common problem, which is the data scarcity. Until now, there are only two public single speaker datasets for French (238 sentences) and British English (97 sentences). In this work, we propose a cross-modal knowledge distillation method with teacher-student structure, which transfers audio speech information to CS to overcome the limited data problem. Firstly, we pretrain a teacher model for CS recognition with a large amount of open source audio speech data, and simultaneously pretrain the feature extractors for lips and hands using CS data. Then, we distill the knowledge from teacher model to the student model with frame-level and sequence-level distillation strategies. Importantly, for frame-level, we exploit multi-task learning to weigh losses automatically, to obtain the balance coefficient. Besides, we establish a five-speaker British English CS dataset for the first time. The proposed method is evaluated on French and British English CS datasets, showing superior CS recognition performance to the state-of-the-art (SOTA) by a large margin. © 2021, CC0.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similarity Computation Model with Attention Mechanism

SCTAR: A Multi-Layer BiLSTM-Based Chinese Short Text Similar...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Shuo Zhao Yiyun Xing Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co. Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Text semantic similarity is a crucial research area in Natural Language Processing (NLP). However, traditional methods for calculating the similarity of short Chinese texts often fall short in accuracy and other crucial aspects. The Bidirectional Long Short-Term Memory Network (BiLSTM) has demonstrated remarkable performance in computing the similarity of short Chinese texts by effectively capturing long-range dependencies and semantic information. Additionally, the multi-head attention mechanism considers the interaction between different text locations and semantic information, enhancing the model’s representative capacity. Building upon this foundation, our paper proposes an enhanced model known as SCTbilstmAttRdrop (SCTAR). This model is constructed based on a multilayer BiLSTM architecture and incorporates an SE-gated convolutional module and a convolutional multi-head attention-aware model. We conducted extensive evaluations using two Chinese short text datasets, Chinese-SNLI and CCKS2018_Task3. The experimental results unequivocally demonstrate that our SCTAR model surpasses other common methods in terms of accuracy, precision, recall, and F1 scores when tasked with computing the similarity of Chinese short texts.

关键词： Accuracy Attention mechanisms Computational modeling Semantics Bidirectional control Feature extraction Nonhomogeneous media

来源：评论

学校读者我要写书评

暂无评论

Breast mass classification method based on convolutional neural networks

Breast mass classification method based on convolutional neu...

引用

3rd Asian Conference on Artificial Intelligence Technology, ACAIT 2019

作者： Sun, Lilei Wang, Junqian Xu, Yong Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China College of Computer Science and Technology Guizhou University Guiyang China Bio-Computing Research Centre Harbin Institute of Technology Shenzhen China

To classify the X-ray mammograms images as benign or malignant is a long-standing unresolved problem, due to the high similarity of different between the mammograms images. In this study, a novel convolutional neural network based X-ray breast mass classification method is proposed. The method receives original breast mass image and its transformed image simultaneously, and extracts more abundant features from the breast mass images. Though the transformed image is a simple inverse of the original image, it allows another side of the thing to be perceived by the network at a very low cost. Experiment results demonstrate that the proposed method significantly outperforms the compared state-of-the-art classification methods for breast mass. © 2020 Institution of Engineering and Technology. All rights reserved.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Text Matching Model Based on Multilayer Coding and Feature Enhancement

A Novel Text Matching Model Based on Multilayer Coding and F...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Yu Zhang Jianqiang Zhang Gongpeng Song Qin Lu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong Branch of China Mobile Communication Group Design Institute Co Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

With the rapid development of Natural Language Processing (NLP), text matching has become the basis of many downstream tasks in NLP, and the study of text matching is of great research significance for solving tasks such as question and answer and information retrieval in NLP. Most of the current text matching methods tend to have problems such as mismatch of grammatical structures and insufficient interaction information in sentences. In order to solve the problems of insufficient interaction information and lack of features and ability to capture keyword and sequence information in text matching, this paper proposes a text matching method based on multi-layer coding and soft attention mechanism. The method first embeds the text and sends it to a gating module for processing, then sends the processed result to a module containing a combination of multilayer coding and soft attention mechanism for further operations such as multiple alignment, and finally sends it to a classifier containing a three-layer fully-connected network for predicting whether the input text pairs match or not. The two modules proposed in this paper are practically feasible, and comparison and ablation experiments have been conducted on the publicly available datasets LCQMC dataset and BQ dataset, and the experimental results show that the two modules improve the accuracy of text matching by 2.44% and 1.02%, respectively.

关键词： Attention mechanisms Accuracy Computational modeling Impedance matching Nonhomogeneous media Information retrieval Encoding

来源：评论

学校读者我要写书评

暂无评论

Moto: Enhancing Embedding with Multiple Joint Factors for Chinese Text Classification

Moto: Enhancing Embedding with Multiple Joint Factors for Ch...

引用

International Conference on Pattern Recognition

作者： Xunzhu Tang Rujie Zhu Tiezhu Sun Shi Wang National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China University of Central Florida Orlando FL USA Momenta Suzhou China Institute of Computing Technology Chinese Academy beijing China

Recently, language representation techniques have achieved great performances in text classification. However, most existing representation models are specifically designed for English materials, which may fail in Chinese because of the huge difference between these two languages. Actually, few existing methods for Chinese text classification process texts at a single level. However, as a special kind of hieroglyphics, radicals of Chinese characters are good semantic carriers. In addition, Pinyin codes carry the semantic of tones, and Wubi reflects the stroke structure information, etc. Unfortunately, previous researches neglected to find an effective way to distill the useful parts of these four factors and to fuse them. In our works, we propose a novel model called Moto: Enhancing Embedding with Multiple Joint Factors. Specifically, we design an attention mechanism to distill the useful parts by fusing the four-level information above more effectively. We conduct extensive experiments on four popular tasks. The empirical results show that our Moto achieves SOTA 0.8316 (F₁-score, 2.11% improvement) on Chinese news titles, 96.38 (1.24% improvement) on Fudan Corpus and 0.9633 (3.26% improvement) on THUCNews.

关键词： Fuses Text categorization Semantics Pattern recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Survey on Large Language Model-Enhanced Reinforcement Learning: Concept, Taxonomy, and Methods

引用

IEEE Transactions on Neural Networks and Learning Systems 2024年第6期36卷 9737-9757页

作者： Yuji Cao Huan Zhao Yuheng Cheng Ting Shu Yue Chen Guolong Liu Gaoqi Liang Junhua Zhao Jinyue Yan Yun Li Department of Mechanical and Automation Engineering The Chinese University of Hong Kong Hong Kong SAR China Department of Building Environment and Energy Engineering The Hong Kong Polytechnic University Hong Kong China School of Science and Engineering The Chinese University of Hong Kong Shenzhen China Center for Crowd Intelligence Shenzhen Institute of Artificial Intelligence and Robotics for Society (AIRS) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China School of Electrical and Electronic Engineering Nanyang Technological University Jurong West Singapore School of Mechanical Engineering and Automation Harbin Institute of Technology Shenzhen China Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen China i4AI Ltd. London U.K.

With extensive pretrained knowledge and high-level general capabilities, large language models (LLMs) emerge as a promising avenue to augment reinforcement learning (RL) in aspects, such as multitask learning, sample efficiency, and high-level task planning. In this survey, we provide a comprehensive review of the existing literature in LLM-enhanced RL and summarize its characteristics compared with conventional RL methods, aiming to clarify the research scope and directions for future studies. Utilizing the classical agent-environment interaction paradigm, we propose a structured taxonomy to systematically categorize LLMs’ functionalities in RL, including four roles: information processor, reward designer, decision-maker, and generator. For each role, we summarize the methodologies, analyze the specific RL challenges that are mitigated and provide insights into future directions. Finally, the comparative analysis of each role, potential applications, prospective opportunities, and challenges of the LLM-enhanced RL are discussed. By proposing this taxonomy, we aim to provide a framework for researchers to effectively leverage LLMs in the RL field, potentially accelerating RL applications in complex applications, such as robotics, autonomous driving, and energy systems.

关键词： Taxonomy Surveys Visualization Reviews Planning Reinforcement learning Games Transformers Natural language processing Large language models

来源：评论

学校读者我要写书评

暂无评论

Decoupling Long- and Short-Term Patterns in Spatiotemporal Inference

arXiv

引用

arXiv 2021年

作者： Hu, Junfeng Liang, Yuxuan Fan, Zhencheng Liu, Li Yin, Yifang Zimmermann, Roger the School of Computing National University of Singapore Singapore Guangzhou China the School of Big Data & Software Engineering Chognqing University China Institute for Infocomm Research A∗STAR Singapore the Faculty of Engineering and Information Technology University of Technology Sydney Australia

Sensors are the key to environmental monitoring, which impart benefits to smart cities in many aspects, such as providing real-time air quality information to assist human decision-making. However, it is impractical to deploy massive sensors due to the expensive costs, resulting in sparse data collection. Therefore, how to get fine-grained data measurement has long been a pressing issue. In this paper, we aim to infer values at non-sensor locations based on observations from available sensors (termed spatiotemporal inference), where capturing spatiotemporal relationships among the data plays a critical role. Our investigations reveal two significant insights that have not been explored by previous works. Firstly, data exhibits distinct patterns at both long- and short-term temporal scales, which should be analyzed separately. Secondly, short-term patterns contain more delicate relations including those across spatial and temporal dimensions simultaneously, while long-term patterns involve high-level temporal trends. Based on these observations, we propose to decouple the modeling of short-term and long-term patterns. Specifically, we introduce a joint spatiotemporal graph attention network to learn the relations across space and time for short-term patterns. Furthermore, we propose a graph recurrent network with a time skip strategy to alleviate the gradient vanishing problem and model the long-term dependencies. Experimental results on four public real-world datasets demonstrate that our method effectively captures both long- and short-term relations, achieving state-of-the-art performance against existing methods. © 2021, CC BY.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Generalized Face Forgery Detection via Adaptive Learning for Pre-trained Vision Transformer

arXiv

引用

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

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：