检索结果-内蒙古大学图书馆

Learning Feedback in Intelligent Tutoring Systems Report of the FIT Project, Conducted from December 2011 to March 2015

引用

KUNSTLICHE INTELLIGENZ 2015年第4期29卷 413-418页

作者： Gross, Sebastian Mokbel, Bassam Hammer, Barbara Pinkwart, Niels Humboldt Univ Inst Informat Unter Linden 6 D-10099 Berlin Germany Bielefeld Univ CITEC Cognit Interact Technol Ctr Excellence D-33594 Bielefeld Germany

Intelligent Tutoring Systems (ITSs) are adaptive learning systems that aim to support learners by providing one-on-one individualized instruction. Typically, instructing learners in ITSs is build on formalized domain knowledge and, thus, the applicability is restricted to welldefined domains where knowledge about the domain being taught can be explicitly modeled. For ill-defined domains, human tutors still by far outperform the performance of ITSs, or the latter are not applicable at all. As part of the DFG priority programme ''Autonomous Learning'', the FIT project has been conducted over a period of 3 years pursuing the goal to develop novel ITS methods, that are also applicable for ill-defined problems, based on implicit domain knowledge extracted from educational data sets. Here, machine learning techniques have been used to autonomously infer structures from given learning data (e.g., student solutions) and, based on these structures, to develop strategies for instructing learners.

关键词： Intelligent tutoring systems example-based feedback Machine learning Prototype-based clustering

来源：评论

学校读者我要写书评

暂无评论

Model-based Image Editing

引用

IT-INFORMATION TECHNOLOGY 2009年第6期51卷 309-312页

作者： Blanz, Volker Univ Siegen Siegen Germany

Photos and 3D Scans of objects and scenes may help to create digital media content in photorealistic quality and at a low cost. However, only sophisticated software can integrate these data into digital data sets and allow users to modify them. The article presents a statistical, learning-based approach that reconstructs, modifies, animates and exchanges human faces in images.

关键词： Computing Methodologies: Image Processing and Computer Vision Computing Methodologies: Computer Graphics facial animation morphable model example-based analysis by synthesis

来源：评论

学校读者我要写书评

暂无评论

LazyFluids: Appearance Transfer for Fluid Animations

引用

ACM TRANSACTIONS ON GRAPHICS 2015年第4期34卷 1-10页

作者： Jamriska, Ondrej Fiser, Jakub Asente, Paul Lu, Jingwan Shechtman, Eli Sykora, Daniel Czech Tech Univ Fac Elect Engn CR-16635 Prague Czech Republic

In this paper we present a novel approach to appearance transfer for fluid animations based on flow-guided texture synthesis. In contrast to common practice where pre-captured sets of fluid elements are combined in order to achieve desired motion and look, we bring the possibility of fine-tuning motion properties in advance using CG techniques, and then transferring the desired look from a selected appearance exemplar. We demonstrate that such a practical workflow cannot be simply implemented using current state-of-the-art techniques, analyze what the main obstacles are, and propose a solution to resolve them. In addition, we extend the algorithm to allow for synthesis with rich boundary effects and video exemplars. Finally, we present numerous results that demonstrate the versatility of the proposed approach.

关键词： texture synthesis flow-guided example-based temporal coherency fluid simulation

来源：评论

学校读者我要写书评

暂无评论

Super-resolution using Neighbor Embedding of Back-projection residuals

Super-resolution using Neighbor Embedding of Back-projection...

引用

18th International Conference on Digital Signal Processing (DSP)

作者： Bevilacqua, Marco Roumy, Aline Guillemot, Christine Morel, Marie-Line Alberi INRIA SIROCCO Res Team Rennes France Bell Labs Alcate Lucent Nozay France

ISBN: (纸本)9781467358057

In this paper we present a novel algorithm for neighbor embedding based super-resolution (SR), using an external dictionary. In neighbor embedding based SR, the dictionary is trained from couples of high-resolution and low-resolution (LR) training images, and consists of pairs of patches: matching patches (m-patches), which are used to match the input image patches and contain only low-frequency content, and reconstruction patches (r-patches), which are used to generate the output image patches and actually bring the high-frequency details. We propose a novel training scheme, where the m-patches are extracted from enhanced back-projected interpolations of the LR images and the r-patches are extracted from the back-projection residuals. A procedure to further optimize the dictionary is followed, and finally nonnegative neighbor embedding is considered at the SR algorithm stage. We consider singularly the various elements of the algorithm, and prove that each of them brings a gain on the final result. The complete algorithm is then compared to other state-of-the-art methods, and its competitiveness is shown.

关键词： super-resolution neighbor embedding example-based back-projection

来源：评论

学校读者我要写书评

暂无评论

Stratification - based Super - Resolution Algorithm for Document Processing 2

Stratification - Based Super - Resolution Algorithm for Docu...

引用

2nd International Conference on Image, Vision and Computing (ICIVC)

作者： Yu, Xiang Luo, Yupin Tsinghua Univ Dept Automat Beijing Peoples R China

ISBN: (纸本)9781509062386

This paper presents a super-resolution algorithm specifically aimed at the document processing. There are some particular characteristics in document image, such as step edge, fixed pattern etc. And in the practical application scenarios, such as scanner optimization, electronic books and so on, all of them propose a real-time requirement to the algorithm. For these scenarios, the existing interpolation-based and learning-based super-resolution methods have their limitations. based on the idea of stratification, this paper proposes the application of guided filter in document matting, and divides the image with this approach into three layers: foreground color, background color and text edge. Interpolated algorithm are used for foreground and background parts to maintain their smoothness and high fidelity of color. For the key structure information contained in the edge layer, the super-resolution reconstruction is performed using the training-based algorithm. The algorithm has the characteristics of color fidelity, edge preserving, clear structure, and efficient training, which can meet the application requirements of document processing well. This paper provides a detailed description of the algorithm, and at the same time provides sufficient comparison and quantification experiments to demonstrate the effectiveness of the algorithm.

关键词： document image stratification guided filter example-based real-time

来源：评论

学校读者我要写书评

暂无评论

Hairstyle Suggestion Using Statistical Learning

Hairstyle Suggestion Using Statistical Learning

引用

18th International Conference on Multimedia Modeling (MMM 2012)

作者： Yang, Wei Toyoura, Masahiro Mao, Xiaoyang Univ Yamanashi Kofu Yamanashi 4008511 Japan

ISBN: (纸本)9783642273544

Hairstyle is one of the most important features people use to characterize one's appearance. Whether a hairstyle is suitable or not is said to be closely related to one's facial shape. This paper proposes a new technique for automatically retrieving a suitable hairstyle from a collection of hairstyle examples through learning the relationship between facial shapes and suitable hairstyles. A method of hair-face image composition utilizing modern matting technique was also developed to synthesize realistic hairstyle images. The effectiveness of the proposed technique was validated through evaluation experiments.

关键词： Hairstyle retrieval example-based statistical learning non-parametric sampling hairstyle image synthesis

来源：评论

学校读者我要写书评

暂无评论

StyleBin: Stylizing Video by example in Stereo 22

StyleBin: Stylizing Video by Example in Stereo

引用

SIGGRAPH Asia Conference

作者： Kucera, Michal Mould, David Sykora, Daniel Czech Tech Univ FEE Prague Czech Republic Carleton Univ SCS Ottawa ON Canada

ISBN: (纸本)9781450394703

In this paper we present StyleBin-an approach to example-based stylization of videos that can produce consistent binocular depiction of stylized content on stereoscopic displays. Given the target sequence and a set of stylized keyframes accompanied by information about depth in the scene, we formulate an optimization problem that converts the target video into a pair of stylized sequences, in which each frame consists of a set of seamlessly stitched patches taken from the original stylized keyframe. The aim of the optimization process is to align the individual patches so that they respect the semantics of the given target scene, while at the same time also following the prescribed local disparity in the corresponding viewpoints and being consistent in time. In contrast to previous depth-aware style transfer techniques, our approach is the first that can deliver semantically meaningful stylization and preserve essential visual characteristics of the given artistic media. We demonstrate the practical utility of the proposed method in various stylization use cases.

关键词： video style transfer example-based stereo

来源：评论

学校读者我要写书评

暂无评论

LEARNING SUPER-RESOLUTION FROM MISALIGNED exampleS

LEARNING SUPER-RESOLUTION FROM MISALIGNED EXAMPLES

引用

Colour and Visual Computing Symposium (CVCS)

作者： Demetriou, Maria Lena Hardeberg, Jon Yngve Adelmann, Gabriel Gjovik Univ Coll Norwegian Colour & Visual Comp Lab N-2802 Gjovik Norway

ISBN: (纸本)9781479906093

Implementations of example-based Super-Resolution (EB-SR) have been developed extensively. Any such EB-SR method is typically evaluated against a constructed test set as to define its performance and applicability. Nevertheless, it is rare for a formed test set to precisely resemble data met in a real-world problem. Usually, low-quality training and test subsets are obtained directly from their corresponding high-quality ground truth data. This allows for a complete and reliable quantitative examination of performance at a later stage. In a real-world problem however, test data are obtained from another source, as for example, printed images. Naturally, low-quality scanned halftones and high-quality continuous tone images would possibly be spatially incoherent training pairs. Such circumstances give rise to one major consideration, misalignment in training subsets. The present work demonstrates the significance of effect of misalignment among training subsets in applying EB-SR and supports the necessity of image registration in preprocessing to overcome this problem.

关键词： example-based Dictionary Image Registration Inverse Halftoning

来源：评论

学校读者我要写书评

暂无评论

Improved Face Image Super-resolution with Restricted Patch-searching Area 19

Improved Face Image Super-resolution with Restricted Patch-s...

引用

3rd International Conference on Cryptography, Security and Privacy (ICCSP) / 4th International Conference on Multimedia and Image Processing (ICMIP)

作者： Hamdan, Suhail Fukumizu, Yohei Izumi, Tomonori Yamauchi, Hironori Ritsumeikan Univ 1-1-1 Noji Higashi Kusatsu Shiga 5258577 Japan

ISBN: (纸本)9781450366182

Recently, an example-based super-resolution (SR) method specifically for face image, which takes the correspondence of facial parts into consideration, was proposed. The method constructs a database of face-image patches with their positions from example images of normalized faces. Given a low-resolution (LR) image, the method generates an SR image by finding similar patches in the database and incorporating high-frequency component of the patches to the LR image. Since the method just divides an example image into patches, for example, 5x5 patches in five-pixels intervals, the SR process may misses the chance to have the patch of the finest position. The proposed method generates patches in one-pixel intervals to increase the chance. In order to cope with the massively increased size of the patch database, the proposed method restricts the area to search the patch candidates for each position. An experimental result shows the proposed method achieves better results than the previous in term of the peak signal-to-noise ratio (PSNR). Furthermore, the proposed method has reduced computational time by 90% compared to the previous.

关键词： example-based face image super-resolution facial parts patch-searching area computational time

来源：评论

学校读者我要写书评

暂无评论

A case-based natural language dialogue system using dialogue act

A case-based natural language dialogue system using dialogue...

引用

IEEE International Conference on Systems, Man and Cybernetics (SMC)

作者： Inui, N Ebe, T Indurkhya, B Kotani, Y Tokyo Univ Agr & Technol Dept Comp Sci Tokyo 1848588 Japan

ISBN: (纸本)0780370872

This paper proposes an approach to enhance dialogue capabilities between humans and the computer, In order for a computer system to sustain a natural conversation without constraining the topic, it must be able to generate a natural response to a wide variety of topics. In particular, a good general-purpose dialogue system must be able to infer the user's intention from an utterance and be able to respond to it appropriately, A case-based dialogue system could provide an approach to solve these problems because it can work as an empirical language learner, and can become a better hearer and speaker for the human user as the case database becomes larger during dialogues. The goal of this research is to design an efficient case-base for a dialogue system, which contains dialogues between humans or between a human and a computer. We define "dialogue act", which is a key to finding the user's intention and for searching appropriate cases in the case-base. We describe how to extract useful knowledge from example dialogues and how to choose an optimal case to generate an appropriate response.

关键词： natural language dialogue example-based dialogue acts keywords matching sentence generation

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：