检索结果-内蒙古大学图书馆

Large-scale data archiving: At the interface of archive science and computer science

data Science and Informetrics 2023年第3期3卷 1-17页

作者： Chaolemen Borjigin Qingwen Jin Key Laboratory of Data Engineering and Knowledge Engineering Renmin University of ChinaBeijingChina School of Information Resource Management Renmin University of ChinaBeijingChina

Both computer science and archival science are concerned with archiving large-scale data,but they have different ***-scale data archiving in computer science focuses on technical aspects that can reduce the cost of data storage and improve the reliability and efficiency of Big data *** weaknesses lie in inadequate and non-standardized *** in archival science focuses on the management aspects and neglects the necessary technical considerations,resulting in high storage and retention costs and poor ability to manage Big ***,the integration of large-scale data archiving and archival theory can balance the existing research limitations of the two fields and propose two research topics for related research-archival management of Big data and large-scale management of archived Big data.

关键词： data archiving Archive Science Computer Science Large-scale data data storage

来源：评论

学校读者我要写书评

暂无评论

Joint Memory Propagation and Rectification for Video Object Segmentation 12th

Joint Memory Propagation and Rectification for Video Objec...

引用

12th International Conference on Image and Graphics, ICIG 2023

作者： Wang, Jiale Xu, Hongli yin, Hui Wan, Jin Chen, Jianhuan Key Laboratory of Beijing for Railway Engineering Beijing Jiaotong University Beijing China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China

ISBN: (纸本)9783031463136

Spatio-temporal memory matching-based methods have achieved significant breakthroughs in the task of video object segmentation. Nevertheless, they are deficient in exploiting the long-term temporal correlation of frames by performing pixel-wise memory matching with limited reference frames, and tend to segment similar objects incorrectly. In this paper, we propose two novel modules, memory propagation and rectification modules, that are able to execute the memory reading in all proceeding frames while leveraging long-term temporal smoothness. Specifically, the memory propagation module employs the lightweight ConvGRU architecture to integrate abundant temporal cues from the reference frame sequence. Afterwards, the memory rectification module guided by the similarity between frames is proposed to increase the inter-frame consistency constraint to retrieve reliable memory and transfer them to the current frame. Additionally, we adopt a tiny-capacity spatio-temporal matching module to model the pixel relationship with only two reference frames. The experimental results on DAVIS and YouTube-VOS datasets demonstrate that combining memory propagation and rectification can achieve considerable performance gain and maintain constant inference time and memory usage in the sequence segmentation. To facilitate research in this direction, we release the project code at https://***/GDPUCJH/MPRNet. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Measuring China's Real Estate Financial Innovation from the Perspective of Government,Enterprises and the Public:Index Compilation and Its Spatial-Temporal Characteristics Analysis

引用

Journal of Systems Science and Information 2023年第1期11卷 1-34页

作者： Jichang DONG Lijun YIN Xiaoting LIU Xiuting LI School of Economics and Management University of Chinese Academy of SciencesBeijing 100190China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100190China China Construction Second Engineering Bureau Co.Ltd Beijing 100070China

In recent years,China has witnessed the rapid development in housing finance,and there have emerged constantly real estate finance innovations;however,there exists no relevant index for measuring the innovations of China's real estate *** on the perspectives of the governments,enterprises and the public,this paper constructs the"innovation index of real estate finance"on a quarterly basis from 2009 to 2019,with the method of empowerment which combines the subjective method(analytic hierarchy process)and the objective one(range coefficient method).It clearly and concretely depicts the innovations in housing finance and the related temporal-spatial characteristics in China since the outbreak of the financial crisis in *** index covers 30 provinces,autonomous regions and municipalities directly under the central government,and analyzes its temporal and spatial *** findings show that there exist a strong spatial autocorrelation and a big regional difference in innovations.

关键词： governments enterprises public real estate finance innovation

来源：评论

学校读者我要写书评

暂无评论

Feature Enhancement for Multi-modal Entity Alignment Transformer

Feature Enhancement for Multi-modal Entity Alignment Transfo...

引用

IEEE International Conference on Big knowledge (ICBK)

作者： Zewen Deng Zan Zhang Bingbing Dong Xiulin Zheng Xindong Wu Key Laboratory of Knowledge Engineering With Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9798331508821

ISBN: (纸本)9798331508838

Multi-modal entity alignment (MMEA) aims to identify equivalent entities across different multi-modal knowledge graphs. In these graphs, entities are enriched with information from various modalities, such as text, images, and numerical data, making the alignment task both challenging and crucial for improving knowledge graph quality. Current MMEA algorithms typically encode entity information separately for each modality using corresponding encoders, and then integrate these representations through various modal fusion strategies. However, these methods often fail to fully exploit the multi-modal information of entities. To address this issue, we propose a feature-enhanced multi-modal entity alignment transformer (FEMEAT). FEMEAT enhances entity attribute information by incorporating modal distribution data, which captures the inherent distribution of different modalities for each entity. This inclusion allows the model to have a richer understanding of entity characteristics across modalities. Additionally, FEMEAT utilizes an Optical Character Recognition (OCR) model to extract and incorporate textual information from images. By integrating this text extracted from images, the model can better utilize the visual modality, enhancing its ability to understand and process multi-modal information. Furthermore, FEMEAT employs a multi-head cross-modal attention (MHCA) mechanism for modal fusion to achieve comprehensive multi-modal entity representation. This mechanism enables the model to attend to different modalities simultaneously and learn a detailed representation of entities by considering the interactions between modalities. The multi-head cross-modal attention mechanism facilitates a nuanced understanding and integration of multi-modal data. Experimental results demonstrate that our model achieves state-of-the-art (SOTA) performance across various training scenarios. The code and datasets used in this study can be accessed at https://***/zewenD/FEMEAT.

关键词： Training Visualization Attention mechanisms Optical character recognition Noise knowledge graphs Transformers Robustness Numerical models data mining

来源：评论

学校读者我要写书评

暂无评论

High Dynamic Collaborative Team Query via Multi-Fuzzy-Constrained Graph Pattern Matching

High Dynamic Collaborative Team Query via Multi-Fuzzy-Constr...

引用

IEEE International Conference on Cloud Computing and Big data Analysis (ICCCBDA)

作者： Tao Hu Zan Zhang Chenyang Bu Lei Li Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) School of Computer Science and Information Engineering Hefei University of Technology Hefei China

ISBN: (数字)9798350373554

ISBN: (纸本)9798350373561

Graph pattern matching is a technique widely used in various fields such as protein structure analysis, social group querying, and expert localization. This technique involves finding matching subgraphs in large social networks that align with the patterns specified in the pattern graph. In this paper, we focus on a specific sub-problem in social group querying, known as the cooperative team query, which arises from practical applications, where the nodes in the pattern graph and the data graph represent team member entities, while the edges represent their social relationships. We note that the requirements of many teams in the real world are dynamic, necessitating iterative computation for graph pattern matching using traditional methods. To address this challenge in highly dynamic systems, we propose a graph pattern matching method based on core pattern graph matching cache. This approach involves extracting the core pattern graph, and comprising core team members based on the characteristics of cooperative teams. The core graph-based matching cache enables the second half of the algorithm to operate on an order-of-magnitude smaller graph, significantly improving efficiency. Additionally, the multi-threaded approach fully leverages hardware resources, synchronizing multiple matching result of the core pattern graph to reduce matching time. Experimental results on three real social network datasets demonstrate that our proposed algorithm, Core Pattern Graph Matching Cache-based Multi-threaded Exploration (CCMTE), significantly outperforms existing methods in terms of efficiency.

关键词： Proteins Location awareness Social networking (online) Social groups Heuristic algorithms knowledge graphs Hardware

来源：评论

学校读者我要写书评

暂无评论

Perovskite photodetector-based single pixel color camera for artificial vision

引用

Light(Science & Applications) 2023年第4期12卷 509-511页

作者： Chaohao Chen Ziyuan Lie Lan Fu School of Electrical and Data Engineering Faculty of Engineering and Information TechnologyThe University of Technology SydneySydneyNSW 2007Australia Australlian Research Council Centre of Excellence for Transformative Meta-Optical Systems Department of Electronic Materials EngineeringResearch School of PhysicsThe Australian National UniversityCanberraACT 2600Australia MoE Key Lab of Photoelectronic Imaging Technology and System School of Optics and PhotonicsBeijing Institute of TechnologyBeijing 100081China

Narrowband red,green,blue self-filtering perovskite photodetectors and a broadband white photodetector are incorporated into a single pixel imaging camera to mimic the long-,medium-,and short-wavelength cone cells and... 详细信息

关键词： artificial pixel filtering

来源：评论

学校读者我要写书评

暂无评论

ModelLock: Locking Your Model With a Spell 24

ModelLock: Locking Your Model With a Spell

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Gao, Yifeng Sun, Yuhua Ma, Xingjun Wu, Zuxuan Jiang, Yu-Gang Shanghai Key Lab of Intell. Info. Processing School of Cs Fudan University Shanghai China Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9798400706868

This paper presents a novel model protection paradigm Model Locking that locks the performance of a finetuned model on private data to make it unusable or unextractable without the right key. Specifically, we proposed a diffusion-based framework dubbed ModelLock that explores text-guided image editing to transform the private finetuning data into unique styles or blend new objects into the background. A model finetuned on this edited dataset will be locked and can only be unlocked by the key prompt, i.e., the same text prompt used to edit the data. We conduct extensive experiments on both image classification and segmentation tasks and show that 1) ModelLock can effectively lock finetuned models without significantly reducing their unlocked performance, and more importantly, 2) the locked model cannot be easily unlocked without knowing both the key prompt and the diffusion model. Our work opens up a new direction for intellectual property protection of private models. © 2024 ACM.

关键词： keys (for locks)

来源：评论

学校读者我要写书评

暂无评论

knowledge-augmented Self-training of A Question Rewriter for Conversational knowledge Base Question Answering

Knowledge-augmented Self-training of A Question Rewriter for...

引用

2022 Findings of the Association for Computational Linguistics: EMNLP 2022

作者： Ke, Xirui Zhang, Jing Lv, Xin Xu, Yiqi Cao, Shulin Li, Cuiping Chen, Hong Li, Juanzi School of Information Renmin University of China Beijing China Key Laboratory of Data Engineering and Knowledge Engineering of Ministry of Education China Department of Computer Science and Technology Tsinghua University Beijing China

The recent rise of conversational applications such as online customer service systems and intelligent personal assistants has promoted the development of conversational knowledge base question answering (ConvKBQA). Different from the traditional single-turn KBQA, ConvKBQA usually explores multi-turn questions around a topic, where ellipsis and coreference pose great challenges to the single-turn KBQA systems which require self-contained questions. In this paper, we propose a rewrite- and-reason framework to first produce a full-fledged rewritten question based on the conversation history and then reason the answer by existing single-turn KBQA models. To overcome the absence of the rewritten supervision signals, we introduce a knowledge-augmented self-training mechanism to transfer the question rewriter from another dataset to adapt to the current knowledge base. Our question rewriter is decoupled from the subsequent QA process, which makes it easy to be united with either retrieval-based or semantic parsing-based KBQA models. Experiment results demonstrate the effectiveness of our method and a new state-of-the-art result is achieved. The code and dataset are available online now. © 2022 Association for Computational Linguistics.

关键词： knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Short Text Topic Modeling Techniques, Applications, and Performance: A Survey

引用

IEEE Transactions on knowledge and data engineering 2022年第3期34卷 1427-1445页

作者： Qiang, Jipeng Qian, Zhenyu Li, Yun Yuan, Yunhao Wu, Xindong Department of Computer Science Yangzhou University Jiangsu225009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei Anhui230026 China Mininglamp Academy of Sciences Minininglamp Beijing China

Analyzing short texts infers discriminative and coherent latent topics that is a critical and fundamental task since many real-world applications require semantic understanding of short texts. Traditional long text topic modeling algorithms (e.g., PLSA and LDA) based on word co-occurrences cannot solve this problem very well since only very limited word co-occurrence information is available in short texts. Therefore, short text topic modeling has already attracted much attention from the machine learning research community in recent years, which aims at overcoming the problem of sparseness in short texts. In this survey, we conduct a comprehensive review of various short text topic modeling techniques proposed in the literature. We present three categories of methods based on Dirichlet multinomial mixture, global word co-occurrences, and self-aggregation, with example of representative approaches in each category and analysis of their performance on various tasks. We develop the first comprehensive open-source library, called STTM, for use in Java that integrates all surveyed algorithms within a unified interface, benchmark datasets, to facilitate the expansion of new methods in this research field. Finally, we evaluate these state-of-the-art methods on many real-world datasets and compare their performance against one another and versus long text topic modeling algorithm. © 2020 IEEE.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Multilingual Lexical Simplification via Zero-Shot Paraphrasing

IEEE Transactions on Audio, Speech and Language Processing

引用

IEEE Transactions on Audio, Speech and Language Processing 2025年 33卷 2200-2214页

作者： Kang Liu Jipeng Qiang Yun Li Yi Zhu Yunhao Yuan Kaixun Hua Xindong Wu Department of Computer Science Yangzhou University Yangzhou China Department of Industrial and Management Systems Engineering University of South Florida Tampa USA Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei China

Lexical simplification (LS) method based on pretrained language models is a straightforward yet powerful approach for generating potential substitutes for a complex word through analysis of its contextual surroundings. Nonetheless, these methods necessitate distinct pretrained models tailored to diverse languages, often overlooking the imperative task of preserving a sentence’s meaning. In this paper, we propose a novel multilingual LS method via zero-shot paraphrasing (LSPG), as paraphrases provide diversity in word selection while preserving the sentence’s meaning. We regard paraphrasing as a zero-shot translation task within multilingual neural machine translation that supports hundreds of languages. Once the input sentence is channeled into the paraphrasing, we embark on the generation of the substitutes. This endeavor is underpinned by a pioneering decoding strategy that concentrates exclusively on the lexical modifications of the complex word. To utilize the strong capabilities of large language models (LLM), we further introduce a novel approach PromLS that incorporates the results of LSPG to generate heuristic-enhanced context, enabling the LLM to generate diverse candidate substitutions. Experimental results demonstrate that LSPG surpasses BERT-based methods and zero-shot GPT3-based methods significantly in English, Spanish, and Portuguese. We also demonstrate a substantial improvement achieved by PromLS compared to the previous state-of-the-art LLM approach. LS approaches usually assume that complex words and their replacements are individual terms, concentrating on word-for-word substitutions. To tackle the more challenging task of multi-word lexical simplification, including phrase-to-phrase replacements, we extend LSPG and PromLS into MultiLSPG and MultiPromLS. MultiLSPG identifies multi-word expressions matched with their corresponding word counts in specific positions, while MultiPromLS, akin to PromLS, utilizes these candidates to generate a heuristi

关键词： Multilingual Decoding Translation Rhetoric Large language models Training Neural machine translation Encoding Speech processing Probability distribution

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：