检索结果-内蒙古大学图书馆

Automatic treebank conversion via informed decoding-A case study on Chinese treebanks

ACM Transactions on Asian Language Information processing 2011年第3期10卷 1–24页

作者： Zhu, Muhua Zhu, Jingbo Xiao, Tong Key Laboratory of Medical Image Computing Natural Language Processing Lab Northeastern University Shenyang 110819 China

Treebanks are valuable resources for syntactic parsing. For some languages such as Chinese, we can obtain multiple constituency treebanks which are developed by different organizations. However, due to discrepancies of underlying annotation standards, such treebanks in general cannot be used together through direct data combination. To enlarge training data for syntactic parsing, we focus in this article on the challenge of unifying standards of disparate treebanks by automatically converting one treebank (source treebank) to fit a different standard which is exhibited by another treebank (target treebank). We propose to convert a treebank in two sequential steps which correspond to the part-of-speech level and syntactic structure level (including tree structures and grammar labels), respectively. Approaches used in both levels can be unified as an informed decoding procedure, where information derived from original annotation in a source treebank is used to guide the conversion conducted by a POS tagger (or a parser in the syntactic structure level) trained on a target treebank. We take two Chinese treebanks as a case study, and experiments on these two treebanks show significant improvements in conversion accuracy over baseline systems, especially in situations where a target treebank is small in size. © 2011 ACM.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

MP-MAT: A 3D-AND-INSTANCE-AWARE HUMAN MATTING AND EDITING FRAMEWORK WITH MULTIPLANE REPRESENTATION

arXiv

引用

arXiv 2025年

作者： Jiao, Siyi Zeng, Wenzheng Li, Yerong Zhang, Huayu Gao, Changxin Sang, Nong Shou, Mike Zheng Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Show Lab National University of Singapore Singapore

Human instance matting aims to estimate an alpha matte for each human instance in an image, which is challenging as it easily fails in complex cases requiring disentangling mingled pixels belonging to multiple instances along hairy and thin boundary structures. In this work, we address this by introducing MP-Mat, a novel 3D-and-instance-aware matting framework with multiplane representation, where the multiplane concept is designed from two different perspectives: scene geometry level and instance level. Specifically, we first build feature-level multiplane representations to split the scene into multiple planes based on depth differences. This approach makes the scene representation 3D-aware, and can serve as an effective clue for splitting instances in different 3D positions, thereby improving interpretability and boundary handling ability especially in occlusion areas. Then, we introduce another multiplane representation that splits the scene in an instance-level perspective, and represents each instance with both matte and color. We also treat background as a special instance, which is often overlooked by existing methods. Such an instance-level representation facilitates both foreground and background content awareness, and is useful for other down-stream tasks like image editing. Once built, the representation can be reused to realize controllable instance-level image editing with high efficiency. Extensive experiments validate the clear advantage of MP-Mat in matting task. We also demonstrate its superiority in image editing tasks, an area under-explored by existing matting-focused methods, where our approach under zero-shot inference even outperforms trained specialized image editing techniques by large margins. Code is open-sourced at https://***/JiaoSiyi/***. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Gait identification by sparse representation

Gait identification by sparse representation

引用

2011 8th International Conference on Fuzzy Systems and Knowledge Discovery, FSKD 2011, Jointly with the 2011 7th International Conference on Natural Computation, ICNC'11

作者： Gong, Minyan Xu, Yi Yang, Xiaokang Zhang, Wenjun Institute of Image Communication and Information Processing Shanghai China Shanghai Key Lab of Digital Media Processing and Transmissions Shanghai China

ISBN: (纸本)9781612841816

Gait recognition under variations of clothing and carrying condition is still a challenging task. In this paper, we present a gait identification method via sparse representation. We formulate the recognition problem as finding the coefficients of linear combination of the training samples plus an error term and discuss sparse signal representation theory that offers the solution to this problem. Based on the sparse representation computed by l1-minimization, we define a new distance metric to choose non-polluted area and propose a method for gait identification. Compared with the state-of-the-art methods on a large dataset, the proposed method achieves significant performance improvement in identification rates and it shows robustness to variations. © 2011 IEEE.

关键词： Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

A Regularized Super Resolution Algorithm for Generalized Gaussian Noise

引用

Journal of Donghua University(English Edition) 2010年第1期27卷 25-35页

作者：陈文方向忠刘立峰蒋伟丁大为乔艳涛 Institute of Image Communication and Information Processing Shanghai Jiaotong University Computer and Information Department Shanghai University of Electric Power Key Lab oratory of Intelligent Computing & Signal Processing Ministry of EducationAnhui University

In this paper,an iterative regularized super resolution (SR) algorithm considering non-Gaussian noise is *** on the assumption of a generalized Gaussian distribution for the contaminating noise,an lp norm is adopted to measure the data fidelity term in the cost *** the meantime,a regularization functional defined in terms of the desired high resolution (HR) image is employed,which allows for the simultaneous determination of its value and the partly reconstructed image at each iteration *** convergence is thoroughly *** results show the effectiveness of the proposed algorithm as well as its superiority to conventional SR methods.

关键词： super resolution generalized p-Gaussian distribution regularization parameter

来源：评论

学校读者我要写书评

暂无评论

A camera self-calibration method based on dual constraints of multi-view images

A camera self-calibration method based on dual constraints o...

引用

2011 International Conference on Wireless communications and Signal processing, WCSP 2011

作者： Liu, Feng Han, Weiwei Xu, Qiong Lin, Qiongjie Fan, Jingjing Image Processing and Image Communication Jiangsu Key Laboratory Nanjing China Key Lab of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing University of Posts and Telecommunications Nanjing China

ISBN: (纸本)9781457710100

Camera calibration is the essential step of obtaining 3D information from 2D views in the field of computer vision, which is widely used in the area of 3D reconstruction, navigation, visual supervision, etc. A camera self-calibration method based on dual constraints of multi-view images is proposed to make calibration possible when there is no reference calibration block or the movement of camera is arbitrary. In this method, multi-view images are preprocessed first to select three images which are most suitable for camera self-calibration, then we use the method based on the genetic algorithm, the camera parameters are finally estimated by using epipolar geometry matching error and reprojection error as fitness functions as two steps. Experimental results show that the proposed camera self-calibration method is correct and effective. © 2011 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Revolutionary entrapment model of uniformly distributed swarm robots in morphogenetic formation

引用

Defence Technology（防务技术） 2024年第1期31卷 496-509页

作者： Chen Wang Zhaohui Shi Minqiang Gu Weicheng Luo Xiaomin Zhu Zhun Fan Shantou University ShantouGuangdongChina National University of Defense Technology ChangshaChina Key Lab of Digital Signal and Image Processing of Guangdong Province China

This study proposes a method for uniformly revolving swarm robots to entrap multiple targets,which is based on a gene regulatory network,an adaptive decision mechanism,and an improved *** the gene regulatory network method,the robots can generate entrapping patterns according to the environmental input,including the positions of the targets and ***,an adaptive decision mechanism is proposed,allowing each robot to choose the most well-adapted capture point on the pattern,based on its *** robots employ an improved Vicsek-model to maneuver to the planned capture point smoothly,without colliding with other robots or *** proposed decision mechanism,combined with the improved Vicsek-model,can form a uniform entrapment shape and create a revolving effect around targets while entrapping *** study also enables swarm robots,with an adaptive pattern formation,to entrap multiple targets in complex *** robots can be deployed in the military field of unmanned aerial vehicles’(UAVs)entrapping multiple *** experiments demonstrate the feasibility and superiority of the proposed gene regulatory network method.

关键词： Swarm intelligence Revolutionary entrapment Flocking Robots Gene regulatory network Vicsek-model Entrapping multiple targets

来源：评论

学校读者我要写书评

暂无评论

An steganography algorithm with robust fine performance

An steganography algorithm with robust fine performance

引用

Proceedings of the International Computer Congress 2004 on Wavelet Analysis and its Applications, and Active Media Technology

作者： Cao, Yuqiang Bai, Sen Zheng, Peng Image Processing Lab. Chongqing Communication Institute Chongqing 400035 China

ISBN: (纸本)981238961X

A novel steganography algorithm operating in the wavelet domain is presented. The proposed algorithm gives two kinds of secret messages bits, which can be classified based on their important, and then have these bits hidden in intermediate or high frequency. 0 or 1 bist can be embedded through regulating intermediate or high frequency coefficients. The most important secret messages is hidden in intermediate frequency, which can resist normal JPEG compressing attack, The other is hidden in high frequency, which has high capacity advantage. The simulation results demonstrate stego-image possesses good visual effect after datum is hidden. Through blind extracting, rates of restoring datum are preferably.

关键词： Information technology

来源：评论

学校读者我要写书评

暂无评论

Improved EZW image coding algorithm based on Zero-tree index

Improved EZW image coding algorithm based on Zero-tree index

引用

Proceedings of the International Computer Congress 2004 on Wavelet Analysis and its Applications, and Active Media Technology

作者： You, Chunyan Wu, Lehua Image Processing Lab. ChongQing Communication Institute ChongQing 400035 China

ISBN: (纸本)981238961X

In Embedded Zero-trees Wavelet Compression, there exist two problems, i.e. multi-scanning of wavelet coefficients and redundancy in the binary code. Considering it, this paper presents Improved EZW image Coding Algorithm Based on zero-tree Index. The algorithm builds a new strategy with a from the bottom up scanning path by introducing the concept of zero-tree index, which reduces the times of repeated scanning and simplifies the computational complexity. We facilitate successive exclude scanning to get rid of the position information redundancy. As for the amplitudes of significant coefficients, we use multi-threshold to optimize the process of SAQ according to HVS, and consequently enhances the coding strategy.

关键词： Information technology

来源：评论

学校读者我要写书评

暂无评论

Blind digital audio watermarking based on SCS in wavelet domain

Blind digital audio watermarking based on SCS in wavelet dom...

引用

Proceedings of the International Computer Congress 2004 on Wavelet Analysis and its Applications, and Active Media Technology

作者： You, Chunyan Wu, Lehua Bai, Sen Image Processing Lab. ChongQing Communication Institute ChongQing 400035 China

ISBN: (纸本)981238961X

Performance of digital watermarking depends on the parameters of embedding algorithm. Most algorithms cannot give the quantitative relationship between embedding parameters and its performance. This paper proposes a new algorithm of bind digital audio watermarking based on SCS. This algorithm can design the embedding parameters according to the requirement. The paper adds the watermark in wavelet domain and compares its performance with that in time domain against attacks of additive noise, mp3 compression and resample. Computer simulation proves that this algorithm is effective and stable.

关键词： Digital watermarking

来源：评论

学校读者我要写书评

暂无评论

Signal processing for sound synthesis:: Computer-generated sounds and music for all

引用

IEEE SIGNAL processing MAGAZINE 2007年第2期24卷 8-+页

作者： Valimaki, Vesa Rabenstein, Rudolf Rocchesso, Davide Serra, Xavier Smith, Julius O. Key Lab of Intelligent Perception and Image Understanding of Ministry of Education Xidian University Xi'an China Key Lab of Radar Signal Processing Xidian University Xi'an China

Almost everybody uses sound synthesis in their daily lives, although many may not know it.

关键词： Editors signal processing Music Synthesis of Sound

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：