检索结果-内蒙古大学图书馆

International Conference on Automatic Face and Gesture recognition

作者： Zhiwen Liu Shan Li Weihong Deng Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications

Recent years, facial expression recognition has remained a challenging and interesting problem, especially for faces in the real world. Most of the traditional approaches are based on Action Units (AUs) detection or low-level features (e.g. LBP, HOG, SIFT and Gabor). Thus, when recognizing real-world facial expressions, these methods might result in poor performance. In this paper, we propose an automatic framework called 'Boosting-POOF' to extract discriminative Mid-Level features using low-level features extracted from local face regions. Rather than cascade local features altogether, we adopt class-pairwise Mid-Level descriptors for each local region to extract Mid-Level features and Adaboost feature selection to choose more discriminative features. In experiments, four facial expression benchmarks (CK+, SFEW, RAF-BASIC, RAFCOMPOUND) are evaluated. The 'Boosting-POOF' achieves state-of-the-art performance compared with recent approaches. What' more, the 'Boosting-POOF' can automatically provide the most significant difference between two expression categories, which is more useful than AUs detection for real world images.

关键词： AUs expression categories interesting

来源：评论

学校读者我要写书评

暂无评论

Image spam classification based on convolutional neural network

Image spam classification based on convolutional neural netw...

引用

International Conference on Machine Learning and Cybernetics (ICMLC)

作者： Er-Xin Shang Hong-Gang Zhang Pattern Recognition and Intelligent System Laboratory Beijing University of Post and Telecommunication

ISBN: (纸本)9781509003914

Image classification is a fundamental problem in computer vision and pattern recognition. Feature extraction is often regarded as the key for classifying images. Traditional ways rely on handcrafted features heavily, such as SIFT and BoW. In this paper, we concentrate on recognizing some specific categories of images (e.g. adult content and political images) in Email. And most importantly we propose a novel architecture of Convolutional Neural Network (CNN) to apply on image classification. In particular, most of the previous methods often use softmax activation for prediction, while instead of utilizing a softmax layer, we present a linear support vector machine (SVM) to be a part of the learning model, minimizing a margin-based loss to obtain a lower level feature representation. Accordingly, we propose a new dataset which contains 7 categories and over 52934 images totally. Experimental results on this novel dataset validate the effectiveness of our method.

关键词： Support vector machines Feature extraction Electronic mail Databases Training Fasteners Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Instance-level coupled subspace learning for fine-grained sketch-based image retrieval 14

Instance-level coupled subspace learning for fine-grained sk...

引用

Computer Vision - ECCV 2016 Workshops, Proceedings

作者： Xu, Peng Yin, Qiyue Qi, Yonggang Song, Yi-Zhe Ma, Zhanyu Wang, Liang Guo, Jun Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China National Lab of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China SketchX Lab School of Electronic Engineering and Computer Science Queen Mary University of London London United Kingdom

ISBN: (纸本)9783319466033

Fine-grained sketch-based image retrieval (FG-SBIR) is a newly emerged topic in computer vision. The problem is challenging because in addition to bridging the sketch-photo domain gap, it also asks for instance-level discrimination within object categories. Most prior approaches focused on feature engineering and fine-grained ranking, yet neglected an important and central problem: how to establish a finegrained cross-domain feature space to conduct retrieval. In this paper, for the first time we formulate a cross-domain framework specifically designed for the task of FG-SBIR that simultaneously conducts instancelevel retrieval and attribute prediction. Different to conventional phototext cross-domain frameworks that performs transfer on category-level data, our joint multi-view space uniquely learns from the instance-level pair-wise annotations of sketch and photo. More specifically, we propose a joint view selection and attribute subspace learning algorithm to learn domain projection matrices for photo and sketch, respectively. It follows that visual attributes can be extracted from such matrices through projection to build a coupled semantic space to conduct retrieval. Experimental results on two recently released fine-grained photo-sketch datasets show that the proposed method is able to perform at a level close to those of deep models, while removing the need for extensive manual annotations. © Springer International Publishing Switzerland 2016.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Structural Connectivity Enhanced Anisotropic 3D Network for Brain Midline Delineation

引用

Journal of Beijing Institute of Technology 2023年第5期32卷 562-578页

作者： Yufan Liu Kongming Liang Yinuo Jing Shen Wang Zhanyu Ma Yiming Li Yizhou Yu Yizhou Wang Jun Guo Pattern Recognition and Intelligent System Laboratory School of Artificial IntelligenceBeijing University of Posts and TelecommunicationsBeijing 100876China. Center on Frontiers of Computing Studies School of Computer SciencePeking UniversityBeijing 100871China AI Lab Deepwise HealthcareBeijing 100089China

Brain midline delineation can facilitate the clinical evaluation of brain midline shift,which has a pivotal role in the diagnosis and prognosis of various brain ***,there are still challenges for brain midline delineation:1)the largely deformed midline is hard to localize if mixed with severe cerebral hemorrhage;2)the predicted midlines of recent methods are not smooth and continuous which violates the structural *** overcome these challenges,we propose an anisotropic three dimensional(3D)network with context-aware refinement(A3D-CAR)for brain midline *** proposed network fuses 3D context from different two dimensional(2D)slices through asymmetric context *** exploit the elongated structure of the midline,an anisotropic block is designed to balance the difference between the adjacent pixels in the horizontal and vertical *** maintaining the structural priority of a brain midline,we present a novel 3D connectivity regular loss(3D CRL)to penalize the disconnectivity between nearby *** experiments on the CQ dataset and one in-house dataset show that the proposed method outperforms three state-of-the-art methods on four evaluation metrics without excessive computational burden.

关键词： brain midline delineation refinement network structure prior connectivity regular loss

来源：评论

学校读者我要写书评

暂无评论

Natural image matting based on image inpainting 2

Natural image matting based on image inpainting

引用

2nd International Conference on Computer Graphics, Image and Virtualization, ICCGIV 2022

作者： Zhang, Yuan Tan, Mian Zhou, Zhulian Yang, Yuan Liang, Yihui Feng, Fujian Guizhou Minzu University Guizhou Key Laboratory of Pattern Recognition and Intelligent System Guiyang550025 China University of Electronic Science and Technology China School of Computer Science Zhongshan528400 China

ISBN: (纸本)9781665492508

Deep image matting is a hot problem with applications in computer vision and image processing. It has been widely used in image composition, film production and video editing etc. The current matting method based on image inpainting uses a deep neural network to inpaint the foreground target and background region to further improve the accuracy of alpha matte. However, when the trimap contains large unknown regions, the excessive inpainting of foreground and background produce a lot of redundant information, which leads to a degradation of alpha matte quality. Therefore, to address this issue, a natural image matting method based on image inpainting is designed. This method involves the refinement process for trimap, which improves the quality of the trimap, enlarges the foreground and background regions providing additional information for image matting. Extensive experimental results on the composition-1k dataset demonstrate that the presented method provide high-quality alpha mattes not only in the case that the trimap contains small unknown regions, but also in the case that the trimap contains large unknown regions. © 2022 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

HCL2000 - A Large-scale Handwritten Chinese Character Database for Handwritten Character recognition

HCL2000 - A Large-scale Handwritten Chinese Character Databa...

引用

International Conference on Document Analysis and recognition

作者： Honggang Zhang Jun Guo Guang Chen Chunguang Li Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications China

In this paper, we present a large scale offline handwritten Chinese character database-HCL2000 which will be made public available for the research community. The database contains 3,755 frequently used simplified Chinese-characters written by 1,000 different subjects. The writerspsila information is incorporated in the database to facilitate testing on grouping writers with different background such as age, occupation, gender, and education etc. We investigate some characteristics of writing styles from different groups of writers. We evaluate HCL2000 database using three different algorithms as a baseline. We decide to publish the database along with this paper and make it free for a research purpose.

关键词： Large-scale systems Character recognition Image databases Handwriting recognition Performance evaluation Face recognition pattern recognition Laboratories Testing Object recognition

来源：评论

学校读者我要写书评

暂无评论

Query by humming via hierarchical filters

Query by humming via hierarchical filters

引用

International Conference on pattern recognition

作者： Zhiyuan Guo Qiang Wang Liang Yin Gang Liu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications China

ISBN: (纸本)9781467322164

This paper proposes an effective implementation of query by humming (QBH) system via hierarchical filters. Firstly locality sensitive hashing (LSH) is used to screen candidate fragments. Secondly linear scaling (LS) is applied to filter out more false candidates and a new method called linear alignment (LA) is presented to locate accurate boundaries of fragments. Then recursive alignment (RA) is employed for the remaining ones. Finally, scores of scaling factor (SF) is fused with scores of RA to rank the songs. Experiments conducted on a database of 5,000 MIDI files show that the proposed approach achieved the relative improvement of mean reciprocal rank up to 37.3% compared with the state-of-the-art method.

关键词： Filtering algorithms Vectors Feature extraction Databases Maximum likelihood detection Nonlinear filters Matched filters

来源：评论

学校读者我要写书评

暂无评论

Microblog retrieval based on term similarity graph

Microblog retrieval based on term similarity graph

引用

International Conference on Computer Science and Network Technology (ICCSNT)

作者： Yuhang Lin Yan Li Weiran Xu Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications China

ISBN: (纸本)9781467329637

In this paper, we introduce a term similarity graph based microblog retrieval model. We propose an undirected weighted graph to describe each post where nodes represent terms and they are linked together based on the co-occurrences. Then an electric network is applied to calculate the resistance distances between pairs of terms. For a given query topic, mutual relevancy in between query terms and between term groups form the expansions to better describe the query. We also define a scoring and ranking model to improve search over large set of microblogs by considering both expanded words and tweets special attributes (hyperlinks and publish time). Our experiments use Twitter 2011 two weeks' data offered by TREC 2011&2012 Microblog Track. Results show that the model better overcome tweets' limited length shortage than traditional methods, good expansion terms are found and microblog retrieval performance are greatly improved by the scoring and ranking model.

关键词： Microblog Search model Term similarity graph Weighted scoring model Scoring Line graph retrieval TWITTER Scoring Hyperlinks

来源：评论

学校读者我要写书评

暂无评论

A MANDARIN SPEECH recognition RESULT EVALUATION ALGORITHM ON MIXED WORDS

A MANDARIN SPEECH RECOGNITION RESULT EVALUATION ALGORITHM ON...

引用

2009 IEEE International Conference on Network Infrastructure and Digital Content(2009年IEEE网络基础设施与数字内容国际会议 IEEE IC-NIDC2009)

作者： Gang Liu Wei Chen Yujing Guo Jun Guo Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing

ISBN: (纸本)9781424448999

Speech recognition result is always evaluated by dynamic programming algorithm which can find the best match between recognized results and references. And the match unit could be word, syllable, phone and so on. However, in mandarin speech recognition, this traditional algorithm is not accurate because of the unique characteristics of Chinese word-formation. In order to improve evaluation performance on Chinese, we proposed a mandarin speech recognition evaluation algorithm based on mixed words. Our experiments show that our proposed algorithm can effectively reduce the false error caused by traditional evaluation algorithm.

关键词： Speech recognition Result Evaluation Dynamic Programming Mized Words

来源：评论

学校读者我要写书评

暂无评论

A Garbage Classification Method Based on Improved YOLOv5

A Garbage Classification Method Based on Improved YOLOv5

引用

2022 International Conference on Networks, Communications and Information Technology, CNCIT 2022

作者： Yan, Xiaobo Yang, Yuan Feng, Le Wang, Lin Tan, Mian Guizhou Minzu Unversity Key Laboratory of Pattern Recognition and Intelligent System of Guizhou Province. Guiyang China College of Date Science and Information Engineering. Guizhou Minzu Unversity Guiyang China

ISBN: (数字)9781665452960

ISBN: (纸本)9781665452960

With the development of national economy, people's daily garbage is increasing day by day. Relying on manpower to sort garbage is a heavy workload and low efficiency. In this paper, an automatic garbage classification system model based on computer vision is proposed to solve the above problems. Firstly, the YOLOv5 object detection algorithm is improved, and abandoning small object detection to obtain faster detection speed. Secondly, shortcut the complex network layer in the YOLOv5 algorithm framework to speed up the recognition speed while ensuring the recognition accuracy. Finally, the traditional loss function is used to improve the detection speed of large objects in raspberry pie. We collect various types of garbage data set, trains the model on the improved algorithm and tests it by embedding raspberry pie. The experimental results show that the proposed algorithm framework has the characteristics of fast speed and high precision, which can complete the garbage classification at the source of garbage. © 2022 IEEE.

关键词： Network layers

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：