检索结果-内蒙古大学图书馆

25th ACM International Conference on Multimedia, MM 2017

作者： Zhao, Zhou Lin, Jinghao Jiang, Xinghua Cai, Deng He, Xiaofei Zhuang, Yueting College of Computer Science Zhejiang University China State Key Lab. of CAD and CG Zhejiang University China

ISBN: (纸本)9781450349062

Video question answering is a challenging task in visual information retrieval, which provides the accurate answer from the referenced video contents according to the given question. However, the existing visual question answering approaches mainly tackle the problem of static image question answering, which may be ineffectively applied for video question answering directly, due to the insufficiency of modeling the video temporal dynamics. In this paper, we study the problem of video question answering from the viewpoint of hierarchical dual-level attention network learning. We obtain the object appearance and movement information in the video based on both frame-level and segment-level feature representation methods. We then develop the hierarchical duallevel attention networks to learn the question-aware video representations with word-level and question-level attention mechanisms. We next devise the question-level fusion attention mechanism for our proposed networks to learn the question-aware joint video representation for video question answering. We construct two large-scale video question answering datasets. The extensive experiments validate the effectiveness of our method. © 2017 Association for Computing Machinery.

关键词： Video recording

来源：评论

学校读者我要写书评

暂无评论

Laplacian musculoskeletal deformation for patient-specific simulation and visualisation

Laplacian musculoskeletal deformation for patient-specific s...

引用

2013 17th International Conference on Information Visualisation, IV 2013

作者： Zhao, Youbing Clapworthy, Gordon J. Kohout, Josef Dong, Feng Tao, Yubo Wei, Hui McFarlane, Nigel Centre for Computer Graphics and Visualisation University of Bedfordshire United Kingdom Department of Computer Science and Engineering University of West Bohemia Plzeò Czech Republic State Key Lab. of CAD and CG Zhejiang University Hangzhou China

ISBN: (纸本)9780769550497

In many biomedical applications, it is often desired to simulate, analyse and visualise the dynamics of a particular patient based on a patient-specific musculoskeletal model. However, reconstructing a patient-specific model directly from medical images is highly lab.ur intensive, and impractical in the clinical context. A more efficient method is to derive it from an atlas musculoskeletal model using patient-specific hints. In this paper, Laplacian mesh processing is introduced to deform an atlas model to a patient-specific model, based on patient-specific landmarks extracted from two orthogonal clinical images and using least-squares error optimization. Muscle attachment landmarks and motion landmarks in the atlas are also transformed as part of the process. Drift and inter-surface penetrations are prevented by supplementary inter-surface landmarks. Mesh simplification and reconstruction are used to avoid out-of-memory failures that may result from trying to deform models at high resolution. © 2013 IEEE.

关键词： Deformation

来源：评论

学校读者我要写书评

暂无评论

A contour-based semi-fragile image watermarking algorithm in DWT domain

A contour-based semi-fragile image watermarking algorithm in...

引用

2nd International Workshop on Education Technology and computer Science, ETCS 2010

作者： Zhang, Daxing Pan, Zhigeng Li, Haihua State Key Lab. of CAD and CG Zhejiang University Hangzhou 310027 China Inst. of Graphics and Image Hangzhou Dianzi University Hangzhou 310012 China

ISBN: (纸本)9780769539874

To authenticate image content tolerant to lossy compression, a semi-fragile image watermarking algorithm based on contour is proposed in this paper. The Y subdivision of original image is subdivided to 4x4 blocks and executed 2-level DWT transform first, then filtered contour image derived from Canny edge detector is used as image feature to generate a watermark. Arnold transform is performed on watermark image to destroy space relativity. Watermark embedding is realized through changing the relationship of selected middle DWT coefficients according corresponding watermark bit. The subtraction result of calculated contour image and extracted watermark image is used to authenticate the content of the image. There is no perceptible degradation to original image. Experiments show that the scheme is useful to meet the requirements of image content authentication and no acceptable JPEG compression is rejected. © 2010 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Discontinuity-aware video object cutout

Discontinuity-aware video object cutout

引用

作者： Zhong, Fan Qin, Xueying Peng, Qunsheng Meng, Xiangxu School of Computer Science and Technology Shandong University China State Key Lab. of CAD and CG Zhejiang University China

Existing video object cutout systems can only deal with limited cases. They usually require detailed user interactions to segment real-life videos, which often suffer from both inseparable statistics (similar appearance between foreground and background) and temporal discontinuities (e.g. large movements, newly-exposed regions following disocclusion or topology change). In this paper, we present an efficient video cutout system to meet this challenge. A novel directional classifier is proposed to handle temporal discontinuities robustly, and then multiple classifiers are incorporated to cover a variety of cases. The outputs of these classifiers are integrated via another classifier, which is learnt from real examples. The foreground matte is solved by a coherent matting procedure, and remaining errors can be removed easily by additive spatio-temporal local editing. Experiments demonstrate that our system performs more robustly and more intelligently than existing systems in dealing with various input types, thus saving a lot of user lab.r and time. © 2012 ACM.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Non-distorted texture mapping using variational interpolation 8

Non-distorted texture mapping using variational interpolatio...

引用

8th Pacific Conference on computer graphics and Applications

作者： Tang, Y Bao, HJ Mong, FY Peng, QS State Key Lab. of CAD and CG Zhejiang University China Department of Computer Science City University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)0769508685

This paper presents a new efficient texture mapping algorithm for polygonal meshes. Texture coordinates are assigned to the vertices of the mesh using the variational interpolation technique. For each patch to be mapped, the algorithm first samples equidistantly the boundaries of the patch. In order to decrease distortion, the patch is further sampled as uniformly as possible while its texture domain are correspondingly sampled. The variational interpolation technique is then invoked to yield a parameterization of the patch. The experimental results demonstrate that the algorithm has a great number of potential applications in texture mapping and surface modeling.

关键词： Application software computer science Image texture Interpolation Mesh generation Rendering (computer graphics) Sampling methods Scattering parameters Shape Surface texture

来源：评论

学校读者我要写书评

暂无评论

Statistical analysis of joint determination for skeleton driven animation of human hands

Statistical analysis of joint determination for skeleton dri...

引用

International Conference on computer graphics Theory and Applications, GRAPP 2013 and International Conference on Information Visualization Theory and Applications, IVAPP 2013

作者： Chaudhry, E. You, L.H. Jin, X. Zhang, Jian J. National Centre for Computer Animation Bournemouth University United Kingdom State Key Lab. of CAD and CG Zhejiang University China

ISBN: (纸本)9789898565464

Skeleton driven character animation is the most popular animation technique. It has been widely applied in the current computer animation industry. Correct determination of joint positions plays a very important role in creating realistic skin deformation of character animation. Current various approaches of skeleton driven character animation have not addressed this issue. In this paper, we propose a statistical method to determine the correct joint position using the statistical data analysis of different X-ray joint images. First, we measure different joint positions from sample X-ray images. Then, we statistically analyse the data, and obtain relative mean and maximum and minimum positions together with the relative range of joints which are used to determine correct joint positions.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Progressive geometry compression for meshes 8

Progressive geometry compression for meshes

引用

8th Pacific Conference on computer graphics and Applications

作者： Liu, XG Bao, HJ Heng, PA Wong, TT Sun, HQ Peng, QS State Key Lab. of CAD and CG Zhejiang Univ. China Department of Computer Science and Engineering Chinese University of Hong Kong Hong Kong

ISBN: (纸本)0769508685

A novel progressive geometry compression scheme is presented in the paper. In this scheme a mesh is represented as a base mesh followed by some groups of vertex split operations using an improved simplification method, in which each level of the mesh can be refined into the next level by carrying out a group of vertex split operations in any order. Consequently, the PM representation can be effectively encoded by permuting the vertex split operations in each group. Meanwhile, a geometry predicator using Laplacian operator is designed to predict each new vertex position using its neighbors. The correction is quantized and encoded using Huffman coding scheme. Experimental results show that our algorithm obtains higher compression ratios than the previous work. It is very suitable for progressive transmission of geometry models over Internet.

关键词： triangular mesh geometry compression manifold surface progressive mesh

来源：评论

学校读者我要写书评

暂无评论

A new method in highway route design：joining circular arcs by a single C-Bezier curve with shape paramete

引用

Journal of Zhejiang University-Science A(Applied Physics & Engineering) 2009年第4期10卷

作者： Hua-hui CAI Guo-jin WANG Institute of Computer Graphics and Image Processing State Key Lab of CAD & CG Zhejiang University

We constructed a single C-B zier curve with a shape parameter for G2 joining two circular arcs. It was shown that an S-shaped transition curve, which is able to manage a broader scope about two circle radii than the B zier curves, has no curvature extrema, while a C-shaped transition curve has a single curvature extremum. Regarding the two kinds of curves, specific algo- rithms were presented in detail, strict mathematical proofs were given, and the effectiveness of the method was shown by examples. This method has the following three advantages: (1) the pattern is unified; (2) the parameter able to adjust the shape of the tran- sition curve is availab.e; (3) the transition curve is only a single segment, and the algorithm can be formulated as a low order equation to be solved for its positive root. These advantages make the method simple and easy to implement.

关键词： Transition curve Shape parameter C-Bezier curve Monotone curvature

来源：评论

学校读者我要写书评

暂无评论

Virtual completion of facial image in ancient murals

Virtual completion of facial image in ancient murals

引用

International Workshop on Digital Media and Digital Content Management, DMDCM 2011

作者： Wang, Qi Lu, Dongmin Zhang, Hongxin College of Computer Science and Technology Zhejiang University Hangzhou China State Key Lab. of CAD and CG Zhejiang University Hangzhou China

ISBN: (纸本)9780769544137

Restore damaged face images is an important issue for ancient murals conservation and research. Since the structure and style of facial image varies with identity, dynasties, location and artists, it is a time consuming and challenging job for researchers to achieve objective and precise restoration. In this paper, we propose a novel facial image completion method based on a semantic learning framework. By few user interactions, our approach can fill missing regions with a reconstructed face which is based on candidate images with high semantic similarity. Since most of the ancient murals contain deteriorations, to archive visual pleasant result, we adopt a PCA based region blending method to produce a seamless completion. Moreover, for the criteria of mural restoration are evaluated in the view of both scientific and art, our completion process can provide the researcher an opportunity to preview a diverse set of the final results virtually before they actually start their job. The real applications in Dunhuang mural show the efficiency and effectiveness of our approach. Furthermore, these experiments suggested the potential applications for restoration facial image in ancient line drawing. © 2011 IEEE.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Opacity volume based halo generation and depth-dependent halos

Opacity volume based halo generation and depth-dependent hal...

引用

作者： Tao, Yubo Wang, Chao Lin, Hai Dong, Feng Clapworthy, Gordon State Key Lab of CAD and CG Zhejiang University Hangzhou China University of Wollongong Wollongong Australia Centre for Computer Graphics and Visualization University of Bedfordshire Luton United Kingdom

Halos are generally used to enhance depth perception and display spatial relationships in illustrative visualization. In this paper, we present a simple and effective method to create volumetric halo illustration. At the preprocessing stage, we generate, on graphics hardware, a view-independent halo intensity volume, which contains all of the potential halos around the boundaries of features, based on the opacity volume. During halo rendering, the halo intensity volume is used to extract halos only around the contours of structures for the current viewpoint. The performance of our approach is significantly faster than previous halo illustration methods, which perform both halo generation and rendering during direct volume rendering. We further propose depth-dependent halo effects, including depth color fading and depth width fading. These halo effects adaptively modulate the visual properties of halos to provide more perceptual cues for depth interpretation. Experimental results demonstrate the efficiency of our proposed approach and the effectiveness of depth-dependent halos. © 2012 Springer-Verlag Berlin Heidelberg.

关键词： Volume rendering

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：