检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Qu, Sanqing Zou, Tianpei Röhrbein, Florian Lu, Cewu Chen, Guang Tao, Dacheng Jiang, Changjun The School of Automotive Engineering Department of Computer Science Tongji University China The Faculty of Computer Science Chemnitz University of Technology Germany The Department of Computer Science Shanghai Jiao Tong University China The School of Computer Science Faculty of Engineering The University of Sydney Australia The Department of Computer Science Key Laboratory of Embedded System and Service Computing Ministry of Education Tongji University China

Deep neural networks often exhibit sub-optimal performance under covariate and category shifts. Source-Free Domain Adaptation (SFDA) presents a promising solution to this dilemma, yet most SFDA approaches are restricted to closed-set scenarios. In this paper, we explore Source-Free Universal Domain Adaptation (SF-UniDA) aiming to accurately classify "known" data belonging to common categories and segregate them from target-private "unknown" data. We propose a novel Global and Local Clustering (GLC) technique, which comprises an adaptive one-vs-all global clustering algorithm to discern between target classes, complemented by a local k-NN clustering strategy to mitigate negative transfer. Despite the effectiveness, the inherent closed-set source architecture leads to uniform treatment of "unknown" data, impeding the identification of distinct "unknown" categories. To address this, we evolve GLC to GLC++, integrating a contrastive affinity learning strategy. We examine the superiority of GLC and GLC++ across multiple benchmarks and category shift scenarios. Remarkably, in the most challenging open-partial-set scenarios, GLC and GLC++ surpass GATE by 16.7% and 18.6% in H-score on VisDA, respectively. GLC++ enhances the novel category clustering accuracy of GLC by 4.3% in open-set scenarios on Office-Home. Furthermore, the introduced contrastive learning strategy not only enhances GLC but also significantly facilitates existing methodologies. Copyright © 2024, The Authors. All rights reserved.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Recovering 3D facial shape via coupled 2D/3D space learning

Recovering 3D facial shape via coupled 2D/3D space learning

引用

International Conference on Automatic Face and Gesture Recognition

作者： Annan Li Shiguang Shan Xilin Chen Xiujuan Chai Wen Gao Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Beijing China System Research Center Nokia Research Center Beijing China Institute of Digital Media Peking University Beijing China

This paper presents a method for recovering 3D facial shape from single image via learning the relationship between the 2D intensity images and the 3D facial shapes. With a coupled training set, the intensity images and their corresponding facial shapes make up two vector spaces respectively. But only the correlated components in both spaces are useful for inference, so there must be embedded hidden subspaces in each space which preserve the inter-space correlation information. Thus by learning the projection onto hidden subspaces based on maximum correlation criteria and optimizing the linear transform between the hidden spaces, 3D facial shape is inferred from the intensity image. The effectiveness of the method is demonstrated on both synthesized and real world data.

关键词： Content addressable storage Humans Face Lighting Light sources Statistics Deformable models Image reconstruction Active shape model Space technology

来源：评论

学校读者我要写书评

暂无评论

PEPT: Expert Finding Meets Personalized Pre-training

arXiv

引用

arXiv 2023年

作者： Peng, Qiyao Xu, Hongyan Wang, Yinghui Liu, Hongtao Huo, Cuiying Wang, Wenjun School of New Media and Communication Tianjin University Tianjin China College of Intelligence and Computing Tianjin University Tianjin China Key Laboratory of Information System and Technology Beijing Institute of Control and Electronic Technology Beijing China Du Xiaoman Technology Beijing China Yazhou Bay Innovation Institute Hainan Tropical Ocean University Hainan China

Finding experts is essential in Community Question Answering (CQA) platforms as it enables the effective routing of questions to potential users who can provide relevant answers. The key is to personalized learning expert representations based on their historical answered questions, and accurately matching them with target questions. Recently, the application of Pre-trained Language Models (PLMs) have gained significant attraction due to their impressive capability to comprehend textual data, and are widespread used across various domains. There have been some preliminary works exploring the usability of PLMs in expert finding, such as pre-training expert or question representations. However, these models usually learn pure text representations of experts from histories, disregarding personalized and fine-grained expert modeling. For alleviating this, we present a personalized pre-training and fine-tuning paradigm, which could effectively learn expert interest and expertise simultaneously. Specifically, in our pre-training framework, we integrate historical answered questions of one expert with one target question, and regard it as a candidate aware expert-level input unit. Then, we fuse expert IDs into the pre-training for guiding the model to model personalized expert representations, which can help capture the unique characteristics and expertise of each individual expert. Additionally, in our pre-training task, we design: 1) a question-level masked language model task to learn the relatedness between histories, enabling the modeling of question-level expert interest;2) a vote-oriented task to capture question-level expert expertise by predicting the vote score the expert would receive. Through our pre-training framework and tasks, our approach could holistically learn expert representations including interests and expertise. Our method has been extensively evaluated on six real-world CQA datasets, and the experimental results consistently demonstrate the superio

关键词： Question answering

来源：评论

学校读者我要写书评

暂无评论

CFDIL: A context-aware feature deep interaction learning for app recommendation

Research Square

引用

Research Square 2021年

作者： Hao, Qingbo Zhu, Ke Wang, Chundong Wang, Peng Mo, Xiuliang Liu, Zhen Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin University of Technology Tianjin China School of Computer Science and Engineering Tianjin University of Technology Tianjin China Engineering Research Center of Learning-Based Intelligent System Ministry of Education Tianjin China Graduate School of Engineering Nagasaki Institute of Applied Science Nagasaki Japan

The rapid development of Mobile Internet has spawned various mobile applications (apps). A large number of apps make it difficult for users to choose apps conveniently, causing the app overload problem. As the most effective tool to solve the problem of app overload, the app recommendation has attracted extensive attention of researchers. Traditional recommendation methods usually use historical data of apps used by users to explore their preferences, and then make an app recommendation list for users. Although the traditional app recommendation methods have achieved certain results, the performance of app recommendation still needs to be improved due to the following two reasons. On the one hand, it is difficult to construct traditional app recommendation models when facing with the sparse user-app interaction data. On the other hand, contextual information has a large impact on users’ app usage preferences, which is often overlooked by traditional app recommendation methods. To overcome the aforementioned problems, we proposed a Context-aware Feature Deep Interaction Learning (CFDIL) method to explore user preferences, and then perform app recommendation by learning potential user-app relationships in different contexts. The novelty of CFDIL is as follows: (1) CFDIL incorporates contextual features into users’ preferences modeling by constructing a novel user and app feature portrait. (2) The problem of data sparsity is effectively solved by the use of dense user and app feature portraits, as well as the tensor operations for label sets. (3) CFDIL trains a new deep network structure, which can make accurate app recommendation using the contextual information and attribute information of users and apps. We applied CFDIL on three real datasets and conducted extensive experiments, which showed that CFDIL outperformed the benchmark method. © 2021, CC BY.

关键词： User profile

来源：评论

学校读者我要写书评

暂无评论

Simulation of Nuclear Reactor Accident Scenarios using Physics-Informed Neural Networks and Transfer-Learning

Simulation of Nuclear Reactor Accident Scenarios using Physi...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 International Conference on

作者： Yang Yu Yufei Xie Wenlin Wang Guohua Wu Haitao Lan Enbo Lin Ping An Zibin Sun Haichuan Zhang Yixian Wu National Key Laboratory of Parallel and Distributed Computing National University of Defense Technology Changsha China Science and Technology on Reactor System Design Technology Laboratory Nuclear Power Institute of China Chengdu China School of Automation Wuhan University of Technology Wuhan China Sino-German College of Intelligent Manufacturing Shenzhen Technology University Shenzhen China Institute of Automotive Engineers Hubei University of Automotive Technology Shiyan China Nuclear Power Institute of China Chengdu China

ISBN: (数字)9798331531409

ISBN: (纸本)9798331531416

In a Loss of Coolant Accident (LOCA), reactor core temperatures can rise rapidly, leading to potential fuel damage and radioactive material release. This research presents a groundbreaking method that combines the power of Monte Carlo Sampling and Physics-Informed Neural Networks (PINNs) to simulate and effectively address the challenging Loss of Coolant Accidents (LOCA) in nuclear reactors. In the event of a LOCA, reactor core temperatures can soar rapidly, posing a significant threat to fuel integrity and potentially leading to the release of radioactive materials. By leveraging the strengths of both Monte Carlo Sampling and PINNs, this approach aims to provide a comprehensive and accurate simulation framework for assessing and mitigating the consequences of such accidents. The method yields high prediction accuracy (MAE: 0.033, RMSE: 0.098, R2: 0.814) and demonstrates robustness through transfer learning, maintaining strong performance (MAE: 0.064, RMSE: 0.163, R 2 : 0.735).

关键词： Radioactive materials Accuracy Monte Carlo methods Transfer learning Neural networks Robustness Data models Fuels Inductors Accidents

来源：评论

学校读者我要写书评

暂无评论

Joint Entity and Relation Extraction Based on Prompt Learning and Multi-channel Heterogeneous Graph Enhancement

Joint Entity and Relation Extraction Based on Prompt Learnin...

引用

International Symposium on Parallel and Distributed Processing with Applications, ISPA

作者： Haiqing Lv Xiaohui Han Peipei Wang Wenbo Zuo Jing Guo Lijuan Xu Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China Quan Cheng Laboratory Jinan China Information Research Institute Qilu University of Technology (Shandong Academy of Sciences) Jinan China

ISBN: (数字)9798331509712

ISBN: (纸本)9798331509729

Joint extraction of entity and relation is crucial in information extraction, aiming to extract all relation triples from unstructured text. However, current joint extraction methods face two main issues. Firstly, they rarely consider the semantic information of entity and relation labels, leading to models that fail to fully understand and utilize the rich semantics in these labels, thereby limiting their performance. Secondly, although table-filling methods are widely used, they focus only on the start or end positions and ignore deep interactions between tables, relying solely on word-level information. To address these issues, we propose the P-MHE framework based on prompt learning and multi-channel heterogeneous graph enhancement. First, we use prompt templates to construct semantic nodes for entity and relation type labels, initializing them along with words as nodes in a heterogeneous graph. We iteratively fuse these semantic nodes through a message-passing mechanism to obtain node representations suitable for entity and relation extraction tasks. Secondly, we design a multi-channel heterogeneous graph to model node relationships from different perspectives, enhancing feature interactions among different types of nodes. Finally, we aggregate the semantic node information of entity and relation type labels after iteration, constructing separate decoding tables for each entity and relation type to better adapt to their respective characteristics. We evaluated our model on four public datasets. Experimental results show that P-MHE outperforms existing models on multiple public datasets. Extensive additional experiments further validate the effectiveness of our model.

关键词： Training Adaptation models Limiting Fuses Semantics Natural languages Information retrieval Feature extraction Data mining Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

Joint Transmit Power and Trajectory Optimization for Two-Way Multi-Hop UAV Relaying Networks

Joint Transmit Power and Trajectory Optimization for Two-Way...

引用

IEEE International Conference on Communications Workshops, ICC

作者： Bing Li Shengjie Zhao Rongqing Zhang Hao Zhang Hanli Wang Liuqing Yang School of Software Engineering Tongji University Shanghai China National Mobile Communications Research Laboratory Southeast University China Ministry of Education Key Laboratory of Embedded System and Service Computing Tongji University Shanghai China School of Electronic and Information Engineer Tongji University Shanghai China Department of Electrical & Computer Engineering Colorado State University CO USA

ISBN: (数字)9781728174402

ISBN: (纸本)9781728174419

Unmanned aerial vehicle (UAV) has been regarded as a promising means to supplement ground communications. As flying relays, UAVs can be rapidly and flexibly deployed to assist data transmissions in many practical scenarios. In this paper, we investigate a two-way multi-hop UAV relaying network, where there are two ground users as sources and multiple UAVs as relays to help the two ground sources exchange information. We first provide an efficient two-way multi-hop UAV relaying pattern, which can achieve a data rate of 2/4 data packets per time slot with decode-and-forward (DF) protocol. Then, we further formulate a joint transmit power and trajectory optimization problem for the UAVs in this two-way multi-hop relaying scenario. The formulated problem is non-convex which makes it difficult to solve directly, hence we propose an iterative algorithm to obtain an approximate optimal solution. Numerical results demonstrate that our proposed network achieves significant throughput gains.

关键词： Relays Protocols Throughput Trajectory optimization Data communication

来源：评论

学校读者我要写书评

暂无评论

Achieving safe minimum circle circumnavigation around multiple targets: a dynamic compensation approach

arXiv

引用

arXiv 2021年

作者： Wang, Chao Shia, Yingjing Li, Rui Song, Yongduan School of Automation Engineering University of Electronic Science and Technology of China Chengdu611731 China Key Laboratory of Dependable Service Computing in Cyber Physical Society of Ministry of Education Chongqing University Chongqing400044 China School of Automation Chongqing University Chongqing400044 China

Minimum circle circumnavigation is proposed in this paper, which is of special value in target monitoring, capturing and/or attacking. In this paper, a safe minimum circle circumnavigation of multiple targets based on bearing measurements is studied. In contrast with the traditional circumnavigation problem, with the new pattern, one agent is able to enclose multiple targets along a minimum circle with the desired enclosing distance and tangential speed. To achieve the minimum circle circumnavigation, an algorithm including dynamic compensators and a control protocol is proposed, by which collision is avoided between the agent and the multiple targets during the whole moving process. Moreover, the control protocol developed for a single agent is further extended to the scenarios of multiple agents by adding a coordination mechanism into the tangential velocity term, which drives the agents to distribute evenly on each expected circular orbit with the same radius or different radius. Simulations results illustrate the effectiveness of the proposed methods. Copyright © 2021, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Quality Assurance for Automated Commit Message Generation

Quality Assurance for Automated Commit Message Generation

引用

IEEE International Conference on Software Analysis, Evolution and Reengineering (SANER)

作者： Bei Wang Meng Yan Zhongxin Liu Ling Xu Xin Xia Xiaohong Zhang Dan Yang Key Laboratory of Dependable Service Computing in Cyber Physical Society (Chongqing University) Ministry of Education China School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science and Technology Zhejiang University Hangzhou China Monash University Australia

ISBN: (纸本)9781728196305;9781728196312

Many automated commit message generation (CMG) approaches have been proposed for facilitating the understanding of software changes. They are shown to be promising and can generate commit messages that are semantically relevant to the reference messages for a number of commits. However, a large proportion (over 50%) of semantically irrelevant commit messages are also generated simultaneously. Such messages may mislead developers, require additional efforts of developers to confirm and filter out, and hinder the application of existing CMG approaches in practice. For tackling this problem, prior work mainly focuses on proposing new methods to improve the generation accuracy. However, another promising way for bridging the gap between CMG approaches and the practice has not been well investigated, which is: can we automatically assure the semantic relevance of the generated messages?To that end, in this work, we propose an automated Quality A ssurance framework for commit message generation (QAcom). QAcom can assure the quality of generated commit messages by automatically filtering out the semantically-irrelevant generated messages and preserving the semantically-relevant ones as many as possible. In particular, QAcom consists of a Collaborative-Filtering-based (CF) component and a Retrieval-based (RE) component. Given a commit message generated by a CMG approach, QAcom estimates whether this generated message is semantically relevant to its ground truth, which is unknown when estimating, based on both the collaborative filtering algorithm and the similarity between this commit and historical commits. We evaluate the effectiveness of QAcom by "plugging" it in three state-of-the-art CMG approaches. Experimental results on three public datasets show that QAcom can effectively filter out semantically-irrelevant generated messages and preserve semantically-relevant ones.

关键词： Quality assurance Filtering Conferences Collaborative filtering Semantics Writing Filtering algorithms

来源：评论

学校读者我要写书评

暂无评论

An Automatic Tooth Position and Dental Disease Detection Algorithm Based on YOLOv8

An Automatic Tooth Position and Dental Disease Detection Alg...

引用

International Conference on Computer and Communications (ICCC)

作者： Hongliang Wang Ke Diao Lin Wu Xuerao Li Xin Zhou Xiaozhou Liu Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Shenyang China School and Hospital of Stomatology China Medical University Liaoning Provincial Key Laboratory of Oral Diseases Shenyang China Shenyang Institute of Computing Technology Chinese Academy of Sciences Liaoning Province Human-Computer Interaction System Engineering Research Center Based on Digital Twin Shenyang China

ISBN: (数字)9798331507077

ISBN: (纸本)9798331507084

With the development of digital dental imaging technology, panoramic tomographic images have become an effective tool for diagnosing dental diseases. However, due to the diversity and complexity of dental lesions, accurately identifying tooth positions and pathological conditions from these images remains challenging. To address the issue of low target detection accuracy caused by the high similarity and complex textures of teeth, this paper introduces YOLOv8-Teeth, an enhanced teeth detection algorithm designed for accurate identification of teeth positions and dental diseases from panoramic radiographs. key innovations include integrating the C2f_ConvNeXtv2 module for improved feature extraction, employing the ASPP module for optimized multi-scale feature capture, and utilizing Focal-EloU Loss for refined bounding box regression. Experimental results on a custom dataset of 476 panoramic radiographs demonstrate significant performance gains, achieving a mean average precision (mAP) of 91.3%, precision of 93.6%, and recall of 88.7%. These improvements offer promising potential for early diagnosis and treatment planning in dental care.

关键词： Technological innovation Accuracy Computational modeling Teeth Tomography Feature extraction Real-time systems Dentistry Detection algorithms Diseases

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：