检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Anan Liu Jintao Li Yongdong Zhang Sheng Tang Yan Song Zhaoxuan Yang School of Electronic Engineering Tianjin University TJU Tianjin China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Institute for Computing Technology Beijing China

In this paper, we present an innovative model of tempo and its application in action scene detection for movie analysis. For the first time, we clearly propose that tempo indicates the rhythm of both movie scenarios and human perception. By thoroughly analyzing both aspects, we classify the factors of tempo into two sorts. The first is based on the film grammar and we use the low level features of shot length and camera motion to describe filmmaking by directors. The second is based on the human perception and we originally propose the information measure for perception depending on the cognitive informatics, a newly emerging and significative subject. With the information in both visual and auditory modalities, the low level features of motion intensity, motion complexity, audio energy and audio pace are integrated for the formulation of information to describe the viewers' emotional changes to continuously developing storyline. With both aspects, tempo is defined and tempo flow plot is derived as the clue of storyline. On the basis of video structuralization and movie tempo analysis, we build a system for hierarchical browse and edit with action scene annotation. The large-scale experiments demonstrate the effectiveness and generality of tempo for action movie *** this paper, we present an innovative model of tempo and its application in action scene detection for movie analysis. For the first time, we clearly propose that tempo indicates the rhythm of both movie scenarios and human perception. By thoroughly analyzing both aspects, we classify the factors of tempo into two sorts. The first is based on the film grammar and we use the low level features of Shot Length and Camera Motion to describe filmmaking by directors. The second is based on the human perception and we originally propose the information measure for perception depending on the cognitive informatics, a newly emerging and significative subject. With the information in both visual and auditor

关键词： Layout Motion pictures Humans information analysis information retrieval Laboratories information processing Computers Rhythm Cameras

来源：评论

学校读者我要写书评

暂无评论

Build Context-based Reasoning Space for Web Service Composition

Build Context-based Reasoning Space for Web Service Composit...

引用

International Symposium on Computational Intelligence and Design, ISCID

作者： Wenjia Niu Peng Hui Peng Cao Zhongzhi Shi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Graduate School of the Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Beijing China Chinese Academy of Sciences Beijing Beijing CN

Dynamic description logic (DDL) is among the few emerging service composition solutions through logical reasoning in AI area. To increase DDL reasoning efficiency, we proposed a new DDL-based service composition model that supports context-aware service pre-filtering over DDL reasoning space. In this model, service filtering based on contexts runs under the workflow control logic. We evaluated filtering approach on a simple, yet realistic example, and the results shows this approach provides a practical solution.

关键词： Context-aware services Web services Logic Context modeling Filtering Artificial intelligence Computational intelligence Space technology Laboratories Competitive intelligence

来源：评论

学校读者我要写书评

暂无评论

A pixel-wise local information-based background subtraction approach

A pixel-wise local information-based background subtraction ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Zhong Wei Shuqiang Jiang Qingming Huang Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences China Institute of Computing Technology Chinese Academy and Sciences Beijing China

Background subtraction is a widely used method for moving object detection in computer vision. It is usually applied in video surveillance systems. There are two major kinds of background subtraction approaches: pixel-based and block based. Yet there are three problems that can not be simultaneously solved by either method: the robustness to illumination changes, the effectiveness in suppressing shadows, and the smoothness of foregroundpsilas boundary. In order to solve these problems, a pixel-wise local information-based background subtraction method is proposed in this paper. In the proposed method, Gabor filters are performed to extract the spatial feature vectors for each pixel from the source image sequence. Then, the spatial feature vectors are modeled by Gaussian Mixture Model, and then moving objects are detected. Experiments show the validity of the proposed method.

关键词： Pixel Gabor filters Computational modeling Feature extraction Lighting Mathematical model Computer vision

来源：评论

学校读者我要写书评

暂无评论

Enhancing web search with heterogeneous semantic knowledge

IFIP Advances in Information and Communication Technology

引用

IFIP Advances in information and Communication technology 2008年 288卷 92-101页

作者： Huang, Rui Shi, Zhongzhi Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Graduate University of the Chinese Academy of Sciences Beijing100049 China

ISBN: (纸本)9780387876849

This paper explores four kinds of semantic knowledge to improve keyword- based Web search, including thesauruses, categories, ontologies, and social annotations. These heterogeneous semantic knowledge represent meanings of Web information, thus they can be used to improve search results in respect of semantic relevance. Currently, different semantic search paradigms have been developed for different kind of semantic knowledge respectively. However, how to make the most of all heterogeneous semantic knowledge to optimize Web search is still a big challenge in practice. To these ends, this paper proposes an integrated semantic search mechanism to incorporate textual information and keyword search with heterogeneous semantic knowledge and semantic search. Experiments show that the proposed mechanism effectively integrates heterogeneous semantic knowledge to improve Web search. © 2008, IFIP International Federation for information Processing. All rights reserved.

关键词： Ontology

来源：评论

学校读者我要写书评

暂无评论

A context model for service composition based on dynamic description logic

IFIP Advances in Information and Communication Technology

引用

IFIP Advances in information and Communication technology 2008年 288卷 7-16页

作者： Niu, Wenjia Shi, Zhongzhi Chang, Liang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100080 China Graduate School of the Chinese Academy of Sciences Beijing100039 China

ISBN: (纸本)9780387876849

A service composition task for service broker is to discovery and compose provider’s services to satisfy user’s request. Many researchers model the context utilizing ontology-based or attribute-based method to assist service composition. We propose a new context model by combining the context logic with the dynamic description logic (DDL), where user’ context, provider’s context and broker’s context are described by DDL separately and reasoned under the context logic. The reasoning results finally can be used to discovery and compose services intelligently. We evaluate this model on a simple, yet realistic example, and the results show that our context model provides a practical solution. © 2008, Springer New York LLC . All rights rserved.

关键词： Data description

来源：评论

学校读者我要写书评

暂无评论

Image segmentation using dynamic mechanism based PCNN model

Image segmentation using dynamic mechanism based PCNN model

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yuanhua Qiao Jun Miao Lijuan Duan Yunfeng Lu College of Applied Science Beijing University of Technology Beijing China Institute of Computing Technology and the Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China College of Computer Science and Technology Beijing University of Technology Beijing China

Pulse-coupled neuron networks (PCNN) can be efficiently applied to image segmentation. However, the performance of segmentation depends on the suitable PCNN parameters, which are obtained by manual experiment, and the effect of the segmentation needs to be improved for images with noise. In this paper, dynamic mechanism based PCNN(DMPCNN) is brought forward to simulate the integrate-and-fire mechanism, and it is applied to segment images with noise effectively. Parameter selection is based on dynamic mechanism. Experimental results for image segmentation show its validity and robustness.

关键词： Neurons Image segmentation Couplings Mathematical model Equations Fires Artificial neural networks

来源：评论

学校读者我要写书评

暂无评论

Mahalanobis distance based Polynomial Segment Model for Chinese Sign Language Recogniton

Mahalanobis distance based Polynomial Segment Model for Chin...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yu Zhou Xilin Chen Debin Zhao Hongxun Yao Wen Gao School of Computer Science and Technology Harbin Institute of Technology Harbin China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Institute of Digital Media Peking University Beijing China

Sign Language Recognition (SLR) systems are mostly based on Hidden Markov Model (HMM) and have achieved excellent results. However, the assumption of frame independence in HMM makes it inconsistent with the characteristic of strong temporal correlation in sign language signals. Polynomial Segment Model (PSM) explicitly represents the temporal evolution of sign language features as a Gaussian process with time-varying parameters. In this paper PSM is first introduced to SLR framework to solve the temporal correlation problem. Considering the correlation among the coefficients of polynomial trajectorypsilas different orders, Mahalanobis distance is used as the classification criterion to evaluate the likelihood of test data. Experimental results show that our method outperform the conventional HMM methods by 6.81% in recognition accuracy.

关键词： Hidden Markov models Handicapped aids Distance measurement Trajectory Vocabulary Euclidean distance Polynomials

来源：评论

学校读者我要写书评

暂无评论

Visual context representation using a combination of feature-driven and object-driven mechanisms

Visual context representation using a combination of feature...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Jun Miao Lijuan Duan Laiyun Qing Xilin Chen Wen Gao Institute of Computing Technology and the Key Laboratory of Intelligent Information Processing Chinese Academy and Sciences Beijing China College of Compter Science and Technology Beijing University of Technology Beijing China School of Information Science and Engineering University of the Chinese Academy of Science Beijing China Institute of Degital Media Peking University and the Institute of Computing Technology Chinese Academy and Sciences Beijing China

Visual context between objects is an important cue for object position perception. How to effectively represent the visual context is a key issue to study. Some past work introduced task-driven methods for object perception, which led a large coding quantity. This paper proposes an approach that incorporates feature-driven mechanism into object-driven context representation for object locating. As an example, the paper discusses how a neuronal network encodes the visual context between feature salient regions and human eye centers with as little coding quantity as possible. A group of experiments on efficiency of visual context coding and object searching are analyzed and discussed, which show that the proposed method decreases the coding quantity and improve the object searching accuracy effectively.

关键词： Artificial neural networks Joints

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-fine video text detection

Coarse-to-fine video text detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Guangyi Miao Qingming Huang Shuqiang Jiang Wen Gao Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy and Sciences Beijing China Institute of Digital Media Peking University Beijing China

In this paper, we propose an effective coarse-to-fine algorithm to detect text in video. Firstly, in coarse-detection section, stroke filter is employed to detect all candidate stroke pixels, and then a fast region growing method is developed to connect these pixels into regions which are further separated into candidate text lines by projection operation. Secondly, in fine-detection section, correct text regions are selected from candidate ones by support vector machine (SVM) model and stroke features, and text regions in multi-resolution are integrated. Finally, the result is optimized significantly according to temporal correlation information. Experimental results show that our algorithm achieves real-time performance and is robust for the variation of language, font, size, color and noise of text caused by low frame resolution in video.

关键词： Pixel Support vector machines Feature extraction Classification algorithms Filtering algorithms Streaming media Correlation

来源：评论

学校读者我要写书评

暂无评论

Illumination transfer using homomorphic wavelet filtering and its application to light-insensitive face recognition

Illumination transfer using homomorphic wavelet filtering an...

引用

International Conference on Automatic Face and Gesture Recognition

作者： Hu Han Shiguang Shan Xilin Chen 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 Institute of Digital Media Peking University Beijing China

In this paper, we propose a novel homomorphic wavelet filtering based illumination transfer technique to change the dominant lighting of one face image (source face image) to another face image (reference face image ). Specifically, in the proposed method, based on the ldquoreflectance-illuminationrdquo imaging model, we first obtain an approximate estimate of the illumination component of the face image through a wavelet-based Multiresolution Analysis (MRA) in the logarithm domain of the input image. Then, a homomorphic filtering procedure is applied to improve the accuracy of the illumination component estimation. Finally, the source face image is re-lighted by substituting the estimated illumination component of the reference image for that of the source image. The proposed method is entirely an image processing based method without any 3D geometry modeling steps, so it is simple but effective. The method is also applied easily to illumination invariant face recognition by transferring a standard illumination to all the face images. Experimental results show that our method is quite effective for both illumination transfer and illumination-insensitive face recognition.

关键词： Lighting Filtering Face recognition Solid modeling Geometry Face detection Facial animation Multiresolution analysis Image processing Digital filters

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：