检索结果-内蒙古大学图书馆

3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015

作者： Song, Lingxiao Zhang, Man Li, Qi Sun, Zhenan He, Ran Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

ISBN: (纸本)9781479961009

Many kinds of efficient greedy subspace clustering methods have been proposed to cut down the computation time in clustering large-scale multimedia datasets. However, these methods are easy to fall into local optimum due to the inherent characteristic of greedy algorithms, which are stepoptimal only. To alleviate this problem, this paper proposes a novel greedy subspace clustering strategy based on floating search, called Float Greedy Subspace Clustering (FloatGSC). In order to control the complexity, the nearest subspace neighbor is added in a greedy way, and the subspace is updated by adding an orthogonal basis involved with the newly added data points in each iteration. Besides, a backtracking mechanism is introduced after each iteration to reject wrong neighbors selected in previous iterations. Extensive experiments on motion segmentation and face clustering show that our algorithm can significantly improve the clustering accuracy without sacrificing much computational time, compared with previous greedy subspace clustering methods. © 2015 IEEE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Supervised topology preserving hashing 3

Supervised topology preserving hashing

引用

3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015

作者： Zhang, Shu Zhang, Man Li, Qi Tan, Tieniu He, Ran Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS China

ISBN: (纸本)9781479961009

Learning based hashing is gaining traction in large-scale retrieval systems. It aims to learn compact binary codes that can preserve semantic similarity in the hamming space. This paper presents a supervised topology hashing (SPTH) algorithm to learn compact binary codes that can exploit both the supervisory information as well as the local topology structure of datasets. To build a connection between the original space and the resultant hamming space, we minimize the quantization errors together with a classification error term and a topology preserving term. A nonlinear kernel feature space is further used to improve the generalization power. An alternating iterative algorithm is developed to minimize the complex objective function that contains both continuous and discrete variables. Experimental results on three benchmark datasets demonstrate the effectiveness of the proposed method on image retrieval tasks. © 2015 IEEE.

关键词： Binary codes

来源：评论

学校读者我要写书评

暂无评论

Global and local consistent multi-view subspace clustering 3

Global and local consistent multi-view subspace clustering

引用

3rd IAPR Asian Conference on Pattern Recognition, ACPR 2015

作者： Fan, Yanbo He, Ran Hu, Bao-Gang Center for Research on Intelligent Perception and Computing CASIA China National Laboratory of Pattern Recognition CASIA China Center for Excellence in Brain Science and Intelligence Technology CAS CASIA China

ISBN: (纸本)9781479961009

Multi-view clustering aims to cluster data with multiple sources of information. Comparing with single view clustering, it is challenging to make use of the extra information embedded in multiple views. This paper presents a multi-view subspace clustering method (MSC-GL) by simultaneously combining both the global low-rank constraint and local cross topology preserving constraints. The global constraint maximizes the correlation between representational matrices while encouraging each of them to be low rank. The local constraints enable representational matrices under different views to share local structure information. An efficiently iterative algorithm is developed to minimize the proposed joint learning problem, and extensive experiments on five multi-view benchmarks demonstrate that the proposed model outperforms the state-of-the-art multiview clustering methods. © 2015 IEEE.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation

Bi-Shifting Auto-Encoder for Unsupervised Domain Adaptation

引用

International Conference on Computer Vision (ICCV)

作者： Meina Kan Shiguang Shan Xilin Chen CAS Institute of Computing Technology Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology

ISBN: (纸本)9781467383929

In many real-world applications, the domain of model learning (referred as source domain) is usually inconsistent with or even different from the domain of testing (referred as target domain), which makes the learnt model degenerate in target domain, i.e., the test domain. To alleviate the discrepancy between source and target domains, we propose a domain adaptation method, named as Bi-shifting Auto-Encoder network (BAE). The proposed BAE attempts to shift source domain samples to target domain, and also shift the target domain samples to source domain. The non-linear transformation of BAE ensures the feasibility of shifting between domains, and the distribution consistency between the shifted domain and the desirable domain is constrained by sparse reconstruction between them. As a result, the shifted source domain is supervised and follows similar distribution as target domain. Therefore, any supervised method can be applied on the shifted source domain to train a classifier for classification in target domain. The proposed method is evaluated on three domain adaptation scenarios of face recognition, i.e., domain adaptation across view angle, ethnicity, and imaging sensor, and the promising results demonstrate that our proposed BAE can shift samples between domains and thus effectively deal with the domain discrepancy.

关键词： Decoding Manifolds Testing Image reconstruction Adaptation models Imaging Training

来源：评论

学校读者我要写书评

暂无评论

An effective real-time fingertip positioning system based on gradient information extraction from frame image sequences

An effective real-time fingertip positioning system based on...

引用

8th International Congress on Image and Signal Processing, CISP 2015

作者： Wang, An H., Lu H., Lu Institute of Semiconductors Chinese Academy of Sciences Beijing China Research Institute of Information Technology Tsinghua University Beijing China Institute of Semiconductors CAS Center for Excellence in Brain Science and Intelligence Technology Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781467390989

This paper presents a writing-in-the-air fingertip positioning system using a camera as an input to a computer. The frame difference method is employed to extract the finger movement area and the vertical gradient is calculated in this area to extract the fingertip contour information. Then the fingertip is located by finger geometric properties. 1000-photos library is built to stimulate various operating environments and test the effectiveness of this system. The system achieves a speed of 100 frames per second (fps) with an accuracy rate of 97.0%. © 2015 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Dissecting the hypothalamic pathways that underlie innate behaviors

引用

Neuroscience Bulletin 2015年第6期31卷 629-648页

作者： Xi Zha Xiaohong Xu Institute of Neuroscience State Key Laboratory of NeuroscienceCAS Center for Excellence in Brain Science and Intelligence TechnologyShanghai Institutes for Biological SciencesChinese Academy of Sciences University of the Chinese Academy of Sciences

Many complex behaviors that do not require learning are displayed and are termed innate. Although traditionally the subject matter of ethology, innate behaviors offer a unique entry point for neuroscientists to dissect the physiological mechanisms governing complex behaviors. Since the last century, converging evidence has implicated the hypothalamus as the central brain area that controls innate behaviors. Recent studies using cutting-edge tools have revealed that genetically-defined populations of neurons residing in distinct hypothalamic nuclei and their associated neural pathways regulate the initiation and maintenance of diverse behaviors including feeding, sleep, aggression, and parental care. Here, we review the newly-defined hypothalamic pathways that regulate each innate behavior. In addition, emerging general principles of the neural control of complex behaviors are discussed.

关键词： hypothalamus innate behaviors neural circuit optogenetics neural network

来源：评论

学校读者我要写书评

暂无评论

A Motion Interference-insensitive Flexible Dry Electrode

A Motion Interference-insensitive Flexible Dry Electrode

引用

2015年中国生物医学工程联合学术年会

作者： He Zhang Weihua Pei Yuanfang Chen Xuhong Guo Xian Wu Xiaowei Yang Hongda Chen State Key Laboratory on Integrated Optoelectronics CAS Center for Excellence in Brain Science and Intelligence TechnologyInstitute of SemiconductorsChinese Academy of Sciences Beijing100083 CAS Center for Excellence in Brain Science

Objective: A novel dry electrode is developed to improve comfortability and the capability of alleviating motion interference by combining micro-needles array(MNA)with flexible ***: Silicon MNA with sharp tips and limited height is fabricated and transferred on a flexible Poly-dimethylsiloxane(PDMS)substrate through ***(3,4-ethylenedioxythiophene)doped with poly(styrenesulfonate)(PEDOT/PSS)is coated on the surface of flexible MNA to form a conductive ***: Flexible dry electrode with 1.2 centimeter diameter is successfully *** mean impedance magnitudes(measured on skin)at 10 Hz is 61.2 ± 31.3 kΩ·cm2 for flexible dry electrode,while the values are 114.9 ± 36.1 kΩ·cm2 for wet electrode and 335.7 ± 110.5 kΩ·cm2 for flexible planar dry electrode *** the process of biopotential recording,the flexible dry electrode has the similar performance as that of wet *** exhibits more stable recording stability than rigid dry electrode in the movement ***: By integrating flexible PDMS substrate,sharp and hard MNA structure,as well as PEDOT/PSS coated surface together,a novel dry electrode is developed to meet the comfortable and anti-motion interference requirement of wearable ***: The novel flexible dry electrode provides a simple and comfortable method to record biopotential signals in daily life.

关键词： anti-motion interference biopotential recording dry electrode flexible micro-needles array (MNA)

来源：评论

学校读者我要写书评

暂无评论

Principal affinity based cross-modal retrieval

Principal affinity based cross-modal retrieval

引用

Asian Conference on Pattern Recognition (ACPR)

作者： Jian Liang Dong Cao Ran He Zhenan Sun Tieniu Tan Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology

ISBN: (纸本)9781479961016

Multimedia content is increasingly available in multiple modalities. Each modality provides a different representation of the same entity. This paper studies the problem of joint representation of the text and image components of multimedia documents. However, most existing algorithms focus more on inter-modal connection rather than intramodal feature extraction. In this paper, a simple yet effective principal affinity representation (PAR) approach is proposed to exploit the affinity representations of different modalities with local cluster samples. Afterwards, multi-class logistic regression model is adopted to learn the projections from principal affinity representation to semantic labels vectors. Inner product distance is further used to improve cross-modal retrieval performance. Extensive experiments on three benchmark datasets illustrate that our proposed method obtains significant improvements over the state-of-the-art subspace learning based cross-modal methods.

关键词： Logistics Semantics Training Extraterrestrial measurements Testing Internet

来源：评论

学校读者我要写书评

暂无评论

Wrinkle Image Registration for Serial Microscopy Sections

Wrinkle Image Registration for Serial Microscopy Sections

引用

International IEEE Conference on Signal-Image Technologies and Internet-Based System

作者： Xi Chen Qiwei Xie Lijun Shen Hua Han Research Center for Brain-inspired Intelligence Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology Beijing China

3D Reconstruction from the microscopy images of serial sections plays an important role in analysis structure of biological specimens, such as neuronal circuits in brain tissue. During specimen sectioning and collecting, it is very hard to prevent wrinkle from these sections, which introduce distortion when imaging in electron microscopy and cause failure of structure reconstruction. In this paper, we propose a pipeline for registration of serial sections with wrinkle. First, Scale Invariant Feature Transform (SIFT) is used to detect corresponding landmarks across adjacent sections. Second, wrinkle areas are labeled manually in microscopy images, which is easy to distinguish by eye. Finally, a modified Moving-Least-Square deformation algorithm is applied to register adjacent sections with wrinkle. The algorithm reflects the discontinuity around wrinkle areas while keeps the smoothness in other regions. Experimental results demonstrate the effectiveness of our method.

关键词： Distortion Image reconstruction Scanning electron microscopy Biology

来源：评论

学校读者我要写书评

暂无评论

Mirrored non-maximum suppression for accurate object part localization

Mirrored non-maximum suppression for accurate object part lo...

引用

Asian Conference on Pattern Recognition (ACPR)

作者： Lianrui Fu Junge Zhang Kaiqi Huang National Laboratory of Pattern Recognition Center for Research on Intelligent Perception and Computing Institute of Automation Chinese Academy of Sciences CAS Center for Excellence in Brain Science and Intelligence Technology

ISBN: (纸本)9781479961016

There has been significant progress in object part localization such as human pose estimation and facial landmark detection. In most of the previous methods, two phenomena are ignored. Firstly, they usually output a set of candidate pose hypotheses but the hypothesis with the highest score obtained by Non-Maximum Suppression (NMS) is not always the optimal result. Secondly, they can not get exactly bilaterally symmetric keypoints on the mirrored images even though the training data is always augmented with mirrored images. In fact, the intrinsic relationship between the original image and the mirrored one is helpful for object part localization. In this paper, we propose Mirrored Non-Maximum Suppression (Mirrored NMS) which can utilize mirrored detections to improve the accuracy of object part localization. Experimental results show that our method can improve the state-of-the-art accuracy by 1.3~3.0% in PCP for human pose estimation and can produce more accurate results than averaging multiple hypotheses for facial landmark detection.

关键词： Mirrors Face Robustness Pattern recognition Training data

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：