检索结果-南通市图书馆

Data-driven digital entertainment: a computational perspective

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2013年第7期14卷 475-476页

作者： yue-ting zhuang Zhejiang University

Today massive collections of data can be obtained across different sources (or domains), e.g., the depth data from Kinect, the geometrical data from scanning devices, the imagery/video data from cameras, and the motion data from mocap devices. Since heterogeneous data may have different discriminative powers and are intrinsically complementary for certain tasks, it is desirable to leverage all

关键词：扫描装置异构数据数字娱乐几何形状数据集合深度数据几何数据视频数据

Patch-guided facial image inpainting by shape propagation

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第2期10卷 232-238页

作者： yue-ting zhuang Yu-shun WANG Timothy K. SHIH Nick C. TANG Institute of Artilicial Intelligence School of Computer Science and Technology Zhejiang University Hangzhou 310027 China Department of Compter Science National Taipei University of Education Taipei 10671 Taiwan China Department of Comp.ter Science and Information Engineering Tamkang University Taipei 25137 Taiwan China

Images with human faces comprise an essential part in the imaging realm. Occlusion or damage in facial portions will bring a remarkable discomfort and information loss. We propose an algorithm that can repair occluded or damaged facial images automatically,named 'facial image inpainting'. Inpainting is a set of image processing methods to recover missing image portions. We extend the image inpainting methods by introducing facial domain knowledge. With the support of a face database,our ap-proach propagates structural information,i.e.,feature points and edge maps,from similar faces to the missing facial regions. Using the inferred structural information as guidance,an exemplar-based image inpainting algorithm is employed to copy patches in the same face from the source portion to the missing portion. This newly proposed concept of facial image inpainting outperforms the traditional inpainting methods by propagating the facial shapes from a face database,and avoids the problem of variations in imaging conditions from different images by inferring colors and textures from the same face image. Our system produces seamless faces that are hardly seen drawbacks.

关键词：图像识别图像修复人脸重建特征点提取

Temporality-enhanced knowledge memory network for factoid question answering

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2018年第1期19卷 104-115页

作者： Xin-yu DUAN Si-liang TANG Sheng-yu ZHANG Yin ZHANG Zhou ZHAO Jian-ru XUE yue-ting zhuang Fei WU College of Computer Science and Technology Zhejiang University School of Information Management Wuhan University Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University

Question answering is an important problem that aims to deliver specific answers to questions posed by humans in natural language.How to efficiently identify the exact answer with respect to a given question has become an active line of research.Previous approaches in factoid question answering tasks typically focus on modeling the semantic relevance or syntactic relationship between a given question and its corresponding answer.Most of these models suffer when a question contains very little content that is indicative of the answer.In this paper,we devise an architecture named the temporality-enhanced knowledge memory network(TE-KMN) and apply the model to a factoid question answering dataset from a trivia competition called quiz bowl.Unlike most of the existing approaches,our model encodes not only the content of questions and answers,but also the temporal cues in a sequence of ordered sentences which gradually remark the answer.Moreover,our model collaboratively uses external knowledge for a better understanding of a given question.The experimental results demonstrate that our method achieves better performance than several state-of-the-art methods.

关键词：存储器暂时性网络知识语义关联语法

挑战与希望:AI 2.0时代从大数据到知识（英文）

在线全文

学校读者我要写书评

暂无评论

Frontiers of Information Technology & Electronic Engineering 2017年第1期18卷 3-14页

作者： yue-ting zhuang Fei WU Chun CHEN Yun-he PAN College of Computer Science and Technology Zhejiang University

本文对大数据时代人工智能领域近期出现的若干理论和技术进展进行了综述。我们认为,将数据驱动机器学习方法与人类的常识先验与隐式直觉有效结合起来,可实现可解释、更鲁棒和更通用的人工智能。AI 2.0时代大数据人工智能具体表现为:从... 详细信息

本文对大数据时代人工智能领域近期出现的若干理论和技术进展进行了综述。我们认为,将数据驱动机器学习方法与人类的常识先验与隐式直觉有效结合起来,可实现可解释、更鲁棒和更通用的人工智能。AI 2.0时代大数据人工智能具体表现为:从浅层计算到深度神经推理;从单纯依赖于数据驱动的模型到数据驱动与知识引导相结合学习;从领域任务驱动智能到更为通用条件下的强人工智能(从经验中学习)。下一代人工智能(AI 2.0)将改变计算本身,将大数据转变为知识以支持人类社会作出更好决策。

关键词：深推理知识库人口人工的一般智力大数据穿过媒介 TP391.4

基于众包标签数据深度学习的命名实体消歧算法（英文）

在线全文

学校读者我要写书评

暂无评论

信息与电子工程前沿：英文版 2017年第1期18卷 97-106页

作者： Le-kui ZHOU Si-liang TANG Jun XIAO Fei WU yue-ting zhuang Institute of Artificial Intelligence College of Computer Science and TechnologyZhejiang University

命名实体消歧主要研究如何将存在歧义的文本描述映射到其对应知识库(例如Wikipedia)中的实体。本文结合群体智能(即群体用户生成的标签)和深度学习(即数据驱动学习),提出了在命名实体消歧过程中生成区别度更高的特征方法。具体来说,通... 详细信息

命名实体消歧主要研究如何将存在歧义的文本描述映射到其对应知识库(例如Wikipedia)中的实体。本文结合群体智能(即群体用户生成的标签)和深度学习(即数据驱动学习),提出了在命名实体消歧过程中生成区别度更高的特征方法。具体来说,通过设计一个众包模型,学习文本描述或实体所对应"众包特征",然后利用"众包特征"对动态卷积神经网络(Dynamic convolutional neural network,DCNN)进行优化,最后用优化得到的DCNN来提取"深度众包特征",以此来解决传统命名实体消歧算法中单独依赖手工设计特征的不足。本文所提出方法巧妙将群体认知(由众包标签反映)结合到命名实体消歧深度学习框架中。实验分析表明,当有足够多众包标签时,所提出方法优于传统手工设计特征。

关键词：命名实体歧义消除 Crowdsourcing 深学习 TP391.4

Synergistic effects of three traditional herbs green tea,mulberry leaf and corn silk on glucose uptake level of L6 myoblasts and the hypoglycemic mechanism

在线全文

学校读者我要写书评

暂无评论

Traditional Medicine Research 2024年第7期9卷 1-12页

作者： Jing-Na Zhou Ming-yue Li ting-ting Zhang Jing-Yang Lu Min Zhang Peng-Wei zhuang Hai-Xia Chen Tianjin Key Laboratory for Modern Drug Delivery&High-Efficiency School of Pharmaceutical Science and TechnologyTianjin UniversityTianjin 300072China. School of Food Science and Bioengineering Tianjin Agricultural UniversityTianjin 300384China. State Key Laboratory of Nutrition and Safety Tianjin University of Science&TechnologyTianjin 300457China. Haihe Laboratory of Modern Chinese Medicine Chinese Materia Medica CollegeTianjin University of Traditional Chinese MedicineTianjin 301617China.

Background:Green tea,mulberry leaf and corn silk are traditional herbs used in the prevention and treatment of diabetes in China for a long time,but their synergistic hypoglycemic effects and mechanisms remain unclear.Methods:The effective components of green tea,mulberry leaf and corn silk were extracted and enriched.Mixture design of experiments was used to study the influences of different combinations on the cell viability and glucose uptake level of L6 myoblasts,so as to determine the optimal synergistic hypoglycemic combination.The possible hypoglycemic mechanism of the optimal synergistic combination was explored by cytotoxicity assay,glucose uptake assay,and western blot.Results:Three polyphenol enrichment fractions of the herbs,30%ethanol elution fraction of green tea(GT),50%ethanol elution fraction of mulberry leaf(ML)and 60%ethanol elution fraction of corn silk(CS)were obtained.The antioxidant activities of GT-30%,ML-50%and CS-60%were superior to those of crude extracts,and showed strong potential inα-amylase andα-glucosidase inhibition activities.The optimal synergistic combination of crude extracts G7(crude extract of green tea:crude extract of mulberry leaf:crude extract of corn silk=1:5:3),polyphenol enrichment fractions R3(GT-30%:ML-50%:CS-60%=1:7:1)and monomers X2(epigallocatechin gallate:morusin:formononetin=3:1:2)were selected,respectively.G7,R3,and X2 showed promoting effects on the cell viability and glucose uptake of L6 myoblasts within the detected concentration range.In addition,G7,R3,and X2 could increase the expression levels of p-PI3K/PI3K and p-Akt/Akt in L6 myoblasts,and promote the translocation of Glut4,but G7 and R3 showed more significant effects.Conclusion:The synergistic hypoglycemic effects of green tea,mulberry leaf and corn silk had the characteristics of multiple-components and multiple-targets with p-PI3K/PI3K,p-Akt/Akt and the translocation of Glut4 signal pathways involved.The three traditional herbs might have the potential to be combined used for the prevention and trea

关键词： green tea mulberry leaf corn silk synergistic effect type 2 diabetes mellitus mechanism

Efficient shape matching for Chinese calligraphic character retrieval

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2011年第11期12卷 873-884页

作者： Wei-ming LU Jiang-qin WU Bao-gang WEI yue-ting zhuang School of Computer Science and Technology Zhejiang University Hangzhou 310027 China

An efficient search method is desired for calligraphic characters due to the explosive growth of calligraphy works in digital libraries. However, traditional optical character recognition (OCR) and handwritten character recognition (HCR) technologies are not suitable for calligraphic character retrieval. In this paper, a novel shape descriptor called SC-HoG is proposed by integrating global and local features for more discriminability, where a gradient descent algorithm is used to learn the optimal combining parameter. Then two efficient methods, keypoint-based method and locality sensitive hashing (LSH) based method, are proposed to accelerate the retrieval by reducing the feature set and converting the feature set to a feature vector. Finally, a re-ranking method is described for practicability. The approach filters query-dissimilar characters using the LSH-based method to obtain candidates first, and then re-ranks the candidates using the keypointor sample-based method. Experimental results demonstrate that our approaches are effective and efficient for calligraphic character retrieval.

关键词：书法形状特征特性检索有效匹配

CMSOF:a structured data organization framework for scanned Chinese medicine books in digital libraries

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2010年第11期11卷 882-892页

作者： Jie YUAN Bao-gang WEI Li-dong WANG Wei-ming LU yue-ting zhuang School of Computer Science and Technology Zhejiang University Hangzhou 310027 China

Organizing unstructured information from books into a well-defined structure is a significant challenge in digital libraries.Most digital libraries can provide only search services at the granularity of books and few libraries allow books to be accessed at the granularity of chapters,as manually constructing directory information for books is time-consuming.Extracting structured data from scanned books thus remains an urgent and important work.In this paper,we propose a novel structured data organization framework called CMSOF to organize scanned data automatically,and apply it to a Chinese medicine digital library. In the framework,image blocks and text blocks on the scanned page of books are separated based on the gray histogram projection method or a hybrid method of region growth and the Ada-Boosting classifier at first,and then the text structure is obtained from text blocks by text size and font type recognition.Finally,image blocks and structured OCRed text are correlated at the semantic level.By integrating the structured data into a Chinese medicine information system(CMIS) ,we can organize the Chinese medicine books well and users can access the books with flexibility,which indicates that CMSOF is an efficient framework to organize books mixed with images and text.

关键词： Digital library Chinese medicine Structured data organization Cross media Image separation

Javelin:an access and manipulation interface for large displays

在线全文

学校读者我要写书评

暂无评论

Journal of Zhejiang University-Science C(Computers and Electronics) 2010年第11期11卷 893-902页

作者： Zhen-kun ZHOU Jiang-qin WU Yin ZHANG Da-wei XIE yue-ting zhuang School of Computer Science and Technology Zhejiang University Hangzhou 310027 China

We describe a user interface and interaction technique,named'Javelin',designed for large display environments.It provides quick access to random screen regions and manipulation methods for screen widgets which are difficult or impossible to reach.It consists of a dynamic global thumbnail,a touchpad widget that drives the screen cursor,and a teleport widget in which interactions are transferred to its target screen region.Javelin can be easily integrated into many programs to optimize their interaction performance in large screens.The experiment and user study show that Javelin can extend user access field and enhance widget manipulation in large displays.

关键词： Large display User interface Interaction method Screen widget Remote target acquisition Human-computer interaction (HCI)