检索结果-内蒙古大学图书馆

16th Conference and labs of the Evaluation Forum, CLEF 2015

作者： Wang, Yunhong Chen, Jiaxin Liu, Ningning Zhang, Li Intelligent Recognition and Image Processing Lab Beihang University Beijing100191 China School of Information Technology and Management University of International Business and Economics Beijing100029 China

In this working note, we mainly focus on the image annotation subtask of imageCLEF 2015 challenge that BUAA-iCC research group participated. For this task, we firstly explore textual similarity information between each test sample and predefined concept. Subsequently, two different kinds of semantic information are extracted from visual images: visual tags using generic object recognition classifiers and visual tags relevant to human being related concepts. For the former information, the visual tags are predicted by using deep convolutional neural network (CNN) and a set of support vector machines trained on imageNet, and finally transferred to textual information. For the latter visual information, human related concepts are extracted via face and facial attribute detection, and finally transferred to similarity information by using manually designed mapping rules, in order to enhance the performance of annotating human related concepts. Meanwhile, a late fusion strategy is developed to incorporate aforementioned various kinds of similarity information. Results validate that the combination of the textual and visual similarity information and the adopted late fusion strategy could yield significantly better performance.

关键词： image annotation

来源：评论

学校读者我要写书评

暂无评论

Corrections to "Relevance Metric Learning for Person Re-Identification by Exploiting Listwise Similarities" [Dec 15 4741-4755]

引用

IEEE transactions on image processing : a publication of the IEEE Signal processing Society 2016年第1期25卷 494页

作者： Jiaxin Chen Zhaoxiang Zhang Yunhong Wang Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing China

Corrections are presented for the above paper (ibid., vol. 24, no. 12, pp. 4741-4755, Dec. 2015).

关键词： Learning (artificial intelligence) Video surveillance Identification of persons Optimization methods

来源：评论

学校读者我要写书评

暂无评论

Action recognition based on kinematic representation of video data

Action recognition based on kinematic representation of vide...

引用

作者： Sun, Xin Huang, Di Wang, Yunhong Qin, Jie Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing100191 China

ISBN: (纸本)9781479957514

The local space-time feature is an effective way to represent video data and achieves state-of-the-art performance in action recognition. However, in majority of cases, it only captures the static or dynamic cues of the image sequence. In this paper, we propose a novel kinematic descriptor, namely Static and Dynamic fEature Velocity (SDEV), which models the changes of both static and dynamic information with time for action recognition. It is not only discriminative itself, but also complementary to the existing descriptors, thus leading to more comprehensive representation of actions by their combination. Evaluated on two public databases, i.e. UCF sports and Olympic Sports, the results clearly illustrate the competency of SDEV. © 2014 IEEE.

关键词： Kinematics

来源：评论

学校读者我要写书评

暂无评论

Binary pattern flavored feature extractors for Facial Expression recognition: An overview

Binary pattern flavored feature extractors for Facial Expres...

引用

Proceedings of the International Convention MIPRO

作者： Rasmus Lyngby Kristensen Zheng-Hua Tan Zhanyu Ma Jun Guo Section of Image Analysis and Computer Graphics Technical University of Denmark Kgs. Lyngby Denmark Signal and Information Processing section (SIP) Aalborg University Aalborg Denmark Pattern Recognition and Intelligent System Lab. Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9781479981748

This paper conducts a survey of modern binary pattern flavored feature extractors applied to the Facial Expression recognition (FER) problem. In total, 26 different feature extractors are included, of which six are selected for in depth description. In addition, the paper unifies important FER terminology, describes open challenges, and provides recommendations to scientific evaluation of FER systems. Lastly, it studies the facial expression recognition accuracy and blur invariance of the Local Frequency Descriptor. The paper seeks to bring together disjointed studies, and the main contribution is to provide a solid overview for future research.

关键词： Feature extraction Face Face recognition Databases Three-dimensional displays Accuracy Gold

来源：评论

学校读者我要写书评

暂无评论

Age invariant face recognition based on texture embedded discriminative graph model

Age invariant face recognition based on texture embedded dis...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Hongyu Yang Di Huang Yunhong Wang Laboratory of Intelligent Recognition and Image Processing Beihang University Beijing China

In an automatic face recognition system, it still remains a challenge to improve the robustness to aging. In this paper, we present a novel approach to address age invariant face recognition, by formulating it as a graph matching problem. In contrast to the majority of tasks in the literature that only make use of robust texture features, this method generates a graph from a set of fiducial landmarks of each face, which captures the texture clues that tend to be stable in a period as well as the common facial geometry configuration. The nodes of the graph denote the texture of a face area around a landmark, and the edges correspond to the geometry topology of the face. For each area, the age invariant texture information is extracted by a discriminative and compact feature encoded in the Local Gabor Binary Pattern Histogram Sequence (LGBPHS) projected in an LDA subspace. An objective function is then designed to match graphs for the purpose of registration and identification. Experiments are carried out on the FG-NET Aging database, and the results achieved outperform the state of the art ones, which clearly demonstrate the effectiveness and robustness of the proposed method in face recognition across age variations.

关键词： Face Face recognition Probes Aging Feature extraction Robustness Geometry

来源：评论

学校读者我要写书评

暂无评论

ACTION recognition BASED ON KINEMATIC REPRESENTATION OF VIDEO DATA

ACTION RECOGNITION BASED ON KINEMATIC REPRESENTATION OF VIDE...

引用

IEEE International Conference on image processing

作者： Xin Sun Di Huang Yunhong Wang Jie Qin Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University

ISBN: (纸本)9781479957521

关键词： Action recognition Kinematic description Motion feature

来源：评论

学校读者我要写书评

暂无评论

Efficient human parsing based on sketch representation

Efficient human parsing based on sketch representation

引用

11th Asian Conference on Computer Vision, ACCV 2012

作者： Wang, Meng Zhang, Zhaoxiang Wang, Yunhong Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing China

ISBN: (纸本)9783642373305

In this paper, we present an efficient human parsing method which estimates human body poses from 2D images. Firstly we propose an edge sketch representation, which enhance critical information for pose estimation and prune the redundant. The sketch representation is generated by employing two sets of filters on extracted edges. Based on sketch representation, body part candidates can be located easily using parallel lines detection in Hough space. Then we use specifically trained linear SVM classifiers to detect each body part candidates based on parallel line feature. A dynamic programming algorithm is applied to calculate the MAP estimation based on standard pictorial structure model, which use a kinematic tree to describe human pose. To evaluate the representing ability of proposed sketch representation, as well as the accuracy and efficiency of our entire human pose estimation method, we run two sets of experiments on a sports image dataset respectively. Experimental results demonstrate that the human body parts in the images can be well described by our proposed sketch representation. Furthermore, our human pose estimation method is efficient and achieves comparable accuracy against the state-of-the-art. © 2013 Springer-Verlag.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

Hand dorsal vein recognition based on shape representation of the venous network

Hand dorsal vein recognition based on shape representation o...

引用

14th Pacific-Rim Conference on Multimedia, PCM 2013

作者： Zhu, Xiangrong Huang, Di Wang, Yunhong Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing 100191 China

ISBN: (纸本)9783319037301

In recent years, the hand dorsal vein has received increasing attentions in the domain of biometrics. This paper presents a novel approach for hand dorsal vein identification based on shape description of the venous network. In order to generate robust data for shape feature extraction, an effective segmentation method is first proposed which makes use of the enhanced detail of blood vessels. The global and local shape representation are then hierarchically combined according to a coarse-to-fine strategy to encode the distinctiveness. The global one is described as the graph composed by endpoints and crossing points of the skeleton of the vein regions;while the local one is represented by a patch based binary coding scheme. The proposed method was evaluated on the NCUT database that contains 2,040 hand dorsal vein (Near Infrared) images of 102 subjects and achieved a rank-one recognition rate of 98.53%, clearly highlighting its effectiveness. © Springer International Publishing Switzerland 2013.

关键词： Matched filters

来源：评论

学校读者我要写书评

暂无评论

Biometric information hiding: Promoting multimedia security with content and identity authentication

Biometric information hiding: Promoting multimedia security ...

引用

2013 IEEE China Summit and International Conference on Signal and Information processing, ChinaSIP 2013

作者： Ma, Bin Li, Chunlei Zhang, Zhaoxiang Wang, Yunhong Intelligent Recognition and Image Processing Laboratory School of Computer Science and Engineering Beihang University Beijing China School of Electronic and Information Engineering Zhongyuan University of Technology Zhengzhou China

ISBN: (纸本)9781479910434

Biometrics and information hiding, as two different yet promising techniques for individual identification and digital media protection, have been extensively studied in the latest decade. Recently, hybrid approaches that combine these two techniques (i.e., biometric information hiding) for advanced information security have obtained increasing research interest. The principle idea is applying information hiding as data anti-counterfeit tool for secure biometric authentication, or introducing biometrics as identity token to information hiding applications such as: owner identification, traitor tracing. In this paper, we present a brief classification of existing biometric information hiding approaches and discuss the corresponding emerged requirements. Meanwhile, two typical application cases proposed in our previous work, which adopted face and fingerprint as watermarks respectively are further discussed and analysed. © 2013 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

LPQ based static and dynamic modeling of facial expressions in 3D videos

引用

2012 International Conference on Service-Oriented Computing, ICSOC 2012

作者： Zhen, Qingkai Huang, Di Wang, Yunhong Chen, Liming Laboratory of Intelligent Recognition and Image Processing School of Computer Science and Engineering Beihang University Beijing China Ecole Centrale de Lyon LIRIS UMR5205 F-69134 Lyon France

ISBN: (纸本)9783319029603

Automatic Facial Expression recognition (FER) is one of the most active topics in the domain of computer vision and pattern recognition. In this paper, we focus on discrete facial expression recognition by using 4D data (i.e. 3D range image sequences), and present a novel method to address such an issue. The Local Phase Quantisation from Three Orthogonal Planes (LPQ-TOP) descriptor is applied to extract both the static and dynamic clues conveyed in facial expressions. On the one hand, it locally captures the shape attributes in each 3D face model (facial range image). On the other hand, it detects the latent temporal information and represents dynamic changes occurred in facial muscle actions. The SVM classifier is finally used to predict the expression type. The experiments are carried out on the BU-4DFE database, and the achieved results demonstrate the effectiveness of the proposed method. © Springer International Publishing 2013.

关键词： Face recognition

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：