检索结果-内蒙古大学图书馆

proceedings of the Seventeenth International Florida Artificial Intelligence Research Society Conference, FLAIRS 2004

作者： Gaborski, Roger S. Vaingankar, Vishal S. Chaoji, Vineet S. Teredesai, Ankur M. Laboratory for Applied Computing Rochester Institute of Technology 102 Lomb Memorial Drive Rochester NY 14623

ISBN: (纸本)1577352017

Novelty detection in video is a rapidly developing application domain within computer vision. The motivation behind this paper is a learning based framework for detecting novelty within video. Since, humans have a general understanding about their environment and possess a sense of distinction between what is normal and abnormal about the environment based on our prior experience;any aspect of the scene that does not fit into this definition of normalcy tends to be labeled as a novel event. In this paper, we propose a computational learning based framework for novelty detection and provide the experimental evidence to describe the results obtained by this framework. To begin with the framework extracts low-level features from scenes, based on the focus of attention theory and then combines unsupervised learning techniques such as clustering with habituation theory to emulate the cognitive aspect of learning.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

Minimizing the Stabbing Number of Matchings, Trees, and Triangulations

Minimizing the Stabbing Number of Matchings, Trees, and Tria...

引用

proceedings of the Fifteenth Annual acm-SIAM symposium on Discrete Algorithms

作者： Fekete, Sándor P. Lübbecke, Marco E. Meijer, Henk Dept. of Mathematical Optimization Braunschweig Univ. of Technology Pockelsstraße 14 D-38106 Braunschweig Germany Institut für Mathematik Sekr. MA 6-1 Technische Universität Berlin Straße des 17. Juni 136 D-10623 Berlin Germany Dept. of Computing Queen's University Kingston Ont. K7L 3N6 Canada

The (axis-parallel) stabbing number of a given set of line segments is the maximum number of segments that can be intersected by any one (axis-parallel) line. We investigate problems of finding perfect matchings, spanning trees, or triangulations of minimum stabbing number for a given set of points. The complexity of these problems has been a long-standing open problem;in fact, it is one of the original 30 outstanding open problems in computational geometry on the list by Demaine, Mitchell, and O'Rourke. We show that minimum stabbing problems are NP-complete. We also show that an iterated rounding technique is applicable for matchings and spanning trees of minimum stabbing number by showing that there is a polynomially solvable LP-relaxation that has fractional solutions with at least one heavy edge. This suggests constant-factor approximations. Our approach uses polyhedral methods that are related to another open problem (from a combinatorial optimization list), in combination with geometric properties. We also demonstrate that the resulting techniques are practical for actually solving problems with up to several hundred points optimally or near-optimally.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Remarks on SVM-based emotion recognition from multi-modal bio-potential signals

Remarks on SVM-based emotion recognition from multi-modal bi...

引用

13th IEEE International Workshop on Robot and Human Interactive Communication

作者： Takahashi, K Doshisha Univ Kyoto 6100321 Japan

ISBN: (纸本)0780385705

This paper proposes an emotion recognition system from multi-modal bio-potential signals. For emotion recognition, support vector machines (SVM) are applied to design the emotion classifier and its characteristics are investigated. Using gathered data under psychological emotion stimulation experiments, the classifier is trained and tested. In experiments of recognizing five emotion: joy, anger, sadness, happiness, and relax, recognition rate of 41.7% is achieved. The experimental result shows that using multi-modal biopotential signals is feasible and that SVM is well suited for emotion recognition tasks.

关键词： Psychology computing

来源：评论

学校读者我要写书评

暂无评论

A maximum-entropy Chinese parser augmented by transformation-based learning

引用

acm Transactions on Asian Language Information Processing 2004年第2期3卷 159-168页

作者： Fung, Pascale Ngai, Grace Yang, Yongsheng Chen, Benfeng Hong Kong Univ. of Sci. and Technol. Hong Kong Polytechnic University Human Language Technology Center Department of Electrical Engineering Hong Kong Universitvof Sci. Technol. Clear Water Bay Hong Kong Department of Computing Hong Kong Polytechnic University Hong Kong Hong Kong

Parsing, the task of identifying syntactic components, e.g., noun and verb phrases, in a sentence, is one of the fundamental tasks in natural language processing. Many natural language applications such as spoken-language understanding, machine translation, and information extraction, would benefit from, or even require, high accuracy parsing as a preprocessing step. Even though most state-of-the-art statistical parsers were initially constructed for parsing in English, most of them are not language-specific, in that they do not rely on properties of the language that are specific to English. Therefore, construction of a parser in a given language becomes a matter of retraining the statistical parameters with a Treebank in the corresponding language. The development of the Chinese treebank [Xia et al. 2000] spurred the construction of parsers for Chinese. However, Chinese as a language poses some unique problems for the development of a statistical parser, the most apparent being word segmentation. Since words in written Chinese are not delimited in the same way as in Western languages, the first problem that needs to be solved before an existing statistical method can be applied to Chinese is to identify the word boundaries. This is a step that is neglected by most pre-existing Chinese parsers, which assume that the input data has already been pre-segmented. This article describes a character-based statistical parser, which gives the best performance to-date on the Chinese treebank data. We augment an existing maximum entropy parser with transformation-based learning, creating a parser that can operate at the character level. We present experiments that show that our parser achieves results that are close to those achievable under perfect word segmentation conditions.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Stereo-based human head detection from crowd scenes

Stereo-based human head detection from crowd scenes

引用

2004 International Conference on Image Processing, ICIP 2004

作者： Hnang, Xiaoyu Li, Liynan Sim, Terence Institute for Infocomm Research A-Star Singapore 119613 School of Computing National University of Singapore Singapore 117543

In this paper, a novel stereo-based head detection method is proposed for human detection in crowd scene. It contains three steps: (1) scale-adaptive filtering, (2) spurious clue suppression, and (3) human head location. With the depth information, the sizes of human heads could be estimated. From this, 3D scale-adaptive filtering is proposed. It is applied for extracting the likelihood evidence of heads from the stereo image. In the second step, the extracted points whose positions in the real space are much higher or lower than the average human height above the ground surface are further suppressed. Finally, human heads are located by applying a mean-shift algorithm to the likelihood map. Good results of detecting human heads in crowds have been obtained from the experiments on real scene. ©2004 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Visual feature extraction via eye tracking for saliency driven 2D/3D registration 04

Visual feature extraction via eye tracking for saliency driv...

引用

proceedings ETRA 2004 - Eye Tracking Research and Applications symposium

作者： Chung, Adrian J. Deligianni, Fani Hu, Xiao-Peng Yang, Guang-Zhong Royal Soc./Wolfson Found. M.I.C.L. Department of Computing Imperial College London United Kingdom

ISBN: (纸本)9781581138252

This paper presents a new technique for extracting visual saliency from experimental eye tracking data. An eye-tracking system is employed to determine which features that a group of human observers considered to be salient when viewing a set of video images. With this information, a biologically inspired saliency map is derived by transforming each observed video image into a feature space representation. By using a feature normalisation process based on the relative abundance of visual features within the background image and those dwelled on eye tracking scan paths, features related to visual attention are determined. These features are then back projected to the image domain to determine spatial areas of interest for unseen video images. The strengths and weaknesses of the method are demonstrated with feature correspondence for 2D to 3D image registration of endoscopy videos with computed tomography data. The biologically derived saliency map is employed to provide an image similarity measure that forms the heart of the 2D/3D registration method. It is shown that by only processing selective regions of interest as determined by the saliency map, rendering overhead can be greatly reduced. Significant improvements in pose estimation efficiency can be achieved without apparent reduction in registration accuracy when compared to that of using a non-saliency based similarity measure.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Using the SpectraCube to build a multispectral image database

Using the SpectraCube to build a multispectral image databas...

引用

CGIV 2004 - Second European Conference on Color in Graphics, Imaging, and Vision and Sixth International symposium on Multispectral Color Science

作者： Finlayson, Graham D. Hordley, Steven D. Morovic, Peter School of Computing Sciences University of East Anglia NR4 7TJ Norwich United Kingdom

ISBN: (纸本)089208250X

Multispectral image capture, unlike traditional RGB imaging, records the colour signals in a scene. Most available devices are either filter-wheel multiple exposure systems or point-measuring diffraction grating based devices. In this article we introduce a 2D matrix, full spectral, single exposure capture system - the applied Spectral Imaging SpectraCube - which determines multispectral images, building on on the principle of interferometry. We explain the theory of operation of the SpectraCube, show characterisation results and present an initial multi-spectral database of indoor images. This step is not trivial. Often there are significant errors in the spectra captured by the SpectraCube. However, these errors are surprisingly regular and can be corrected. The images were captured at a high spectral resolution, comparable to spectroradiometers, yet at an exposure significantly shorter than that of filter-wheel based systems.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

A radial basis function equalizer for optical fiber communications systems

A radial basis function equalizer for optical fiber communic...

引用

IEEE International Conference on Acoustics, Speech, and Signal Processing

作者： Wang, W Univ Maryland Baltimore Cty Dept Comp Sci & Elect Engn Baltimore MD 21250 USA

ISBN: (纸本)0780384849

A radial basis function (RBF) equalizer is introduced for mitigation of intersymbol interference in optical communications systems. It is shown that prior information on the noise and channel characteristics can be effectively incorporated into the structure of an RBF equalizer. A training algorithm for tracking time varying statistics of the input is presented and the proposed equalizer is applied for mitigation of polarization mode dispersion in optical communications channel with dominating amplified spontaneous emission noise.

关键词： learning (artificial intelligence) optical noise random noise optical fibre polarisation radial basis function networks equalisers optical fibre communication intersymbol interference interference suppression statistical analysis optical fibre dispersion telecommunication computing radial basis function equalizer optical fiber communications systems intersymbol interference mitigation optical communications systems noise characteristics prior information training algorithm time varying statistics polarization mode dispersion amplified spontaneous emission noise neural network techniques

来源：评论

学校读者我要写书评

暂无评论

Application-level checkpointing for shared memory programs

Application-level checkpointing for shared memory programs

引用

作者： Bronevetsky, Greg Marques, Daniel Pingali, Keshav Szwed, Peter Schulz, Martin Department of Computer Science Cornell University Ithaca NY 14853 School of Electrical and Computer Engineering Cornell University Ithaca NY 14853 Center for Applied Scientific Computing Lawrence Livermore National Laboratory Livermore CA 94551

Trends in high-performance computing are making it necessary for long-running applications to tolerate hardware faults. The most commonly used approach is checkpoint and restart (CPR) - the state of the computation is saved periodically on disk, and when a failure occurs, the computation is restarted from the last saved state. At present, it is the responsibility of the programmer to instrument applications for CPR. Our group is investigating the use of compiler technology to instrument codes to make them self-checkpointing and self-restarting, thereby providing an automatic solution to the problem of making long-running scientific applications resilient to hardware faults. Our previous work focused on message-passing programs. In this paper, we describe such a system for shared-memory programs running on symmetric multiprocessors. This system has two components: (i) a pre-compiler for source-to-source modification of applications, and (ii) a runtime system that implements a protocol for coordinating CPR among the threads of the parallel application. For the sake of concreteness, we focus on a non-trivial subset of OpenMP that includes barriers and locks. One of the advantages of this approach is that the ability to tolerate faults becomes embedded within the application itself, so applications become self-checkpointing and self-restarting on any platform. We demonstrate this by showing that our transformed benchmarks can checkpoint and restart on three different platforms (Windows/x86, Linux/x86, and Tru64/Alpha). Our experiments show that the overhead introduced by this approach is usually quite small;they also suggest ways in which the current implementation can be tuned to reduced overheads further. Copyright 2004 acm.

关键词： Computer systems programming

来源：评论

学校读者我要写书评

暂无评论

An empirical comparison of token encoding strategies in the generation of vector representations of structured data

An empirical comparison of token encoding strategies in the ...

引用

proceedings of the IASTED International Conference on Artificial Intelligence and Applications (as part of the 22nd IASTED International Multi-Conference on applied Informatics

作者： Vincent, Jonathan Mintram, Robert C. Sch. of Des. Eng. and Computing University of Bournemouth United Kingdom School of Informatics University of Northumbria United Kingdom

ISBN: (纸本)088986375X

A consequence of the connectionist approach to artificial intelligence is the requirement for structured data to be encoded into fixed width vector representations (VREPS). This paper provides an empirical comparison of six different strategies for encoding the tokens that appear within tree representations of this structured data. A new two element real-valued token encoding is presented and empirical results show that it produces more compact vectors than previously possible with conventional encodings. This assessment is conducted within the General Encoder /Decoder (GED) framework and makes use of the VREP recovery profile (VRP) graphical representation to enable quantitative and qualitative judgements to be made.

关键词： Encoding (symbols)

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：