检索结果-内蒙古大学图书馆

25th International Joint Conference on Artificial Intelligence, IJCAI 2016

作者： Gao, Junning Yamada, Makoto Kaski, Samuel Mamitsuka, Hiroshi Zhu, Shanfeng School of Computer Science Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Bioinformatics Center Institute for Chemical Research Kyoto University Uji Japan Department of Computer Science Aalto University Finland

We formulate ensemble clustering as a regularization problem over nuclear norm and cluster-wise group norm, and present an efficient optimization algorithm, which we call Robust Convex Ensemble Clustering (RCEC). A key feature of RCEC allows to remove anomalous cluster assignments obtained from component clustering methods by using the group-norm regularization. Moreover, the proposed method is convex and can find the globally optimal solution. We first showed that using synthetic data experiments, RCEC could learn stable cluster assignments from the input matrix including anomalous clusters. We then showed that RCEC outperformed state-of-the-art ensemble clustering methods by using real-world data sets.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Learning label-Specific Features and Class-Dependent labels for Multi-label Classification

引用

IEEE Transactions on Knowledge and Data Engineering 2016年第99期PP卷 3309-3323页

作者： Huang, Jun Li, Guorong Huang, Qingming Wu, Xindong School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing101480 China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Department of Computer Science University of Vermont 33 Colchester Avenue BurlingtonVT05405 United States

Binary Relevance is a well-known framework for multi-label classification, which considers each class label as a binary classification problem. Many existing multi-label algorithms are constructed within this framework and utilize identical data representation in the discrimination of all the class labels. In multi-label classification, however, each class label might be determined by some specific characteristics of its own. In this paper, we seek to learn label-specific data representation for each class label, which is composed of label-specific features. Our proposed method LLSF can not only be utilized for multi-label classification directly, but also be applied as a feature selection method for multi-label learning and a general strategy to improve multi-label classification algorithms comprising a number of binary classifiers. Inspired by the research works on modeling high-order label correlations, we further extend LLSF to learn class-Dependent labels in a sparse stacking way, denoted as LLSFDL. It incorporates both second-order and high-order label correlations. A comparative study with the state-of-the-art approaches manifests the effectiveness and efficiency of our proposed methods. © 2016 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

One-shot fine-grained instance retrieval

arXiv

引用

arXiv 2017年

作者： Yao, Hantao Zhang, Shiliang Zhang, Yongdong Li, Jintao Tian, Qi Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Electronic Engineering and Computer Science Peking University Beijing100871 China Department of Computer Science University of Texas at San Antonio San Antonio United States

Fine-Grained Visual Categorization (FGVC) has achieved significant progress recently. However, the number of fine-grained species could be huge and dynamically increasing in real scenarios, making it difficult to recognize unseen objects under the current FGVC framework. This raises an open issue to perform large-scale fine-grained identification without a complete training set. Aiming to conquer this issue, we propose a retrieval task named One-Shot Fine-Grained Instance Retrieval (OSFGIR). "One-Shot" denotes the ability of identifying unseen objects through a fine-grained retrieval task assisted with an incomplete auxiliary training set. This paper first presents the detailed description to OSFGIR task and our collected OSFGIR-378K dataset. Next, we propose the Convolutional and Normalization Networks (CN-Nets) learned on the auxiliary dataset to generate a concise and discriminative representation. Finally, we present a coarse-to-fine retrieval framework consisting of three components, i.e., coarse retrieval, fine-grained retrieval, and query expansion, respectively. The framework progressively retrieves images with similar semantics, and performs fine-grained identification. Experiments show our OSFGIR framework achieves significantly better accuracy and efficiency than existing FGVC and image retrieval methods, thus could be a better solution for large-scale fine-grained object identification. Copyright © 2017, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Probabilistic autoreductions 42nd

Probabilistic autoreductions

引用

42nd International Conference on Current Trends in Theory and Practice of computer science, SOFSEM 2016

作者： Zhang, Liyu Yuan, Chen Kan, Haibin Department of Computer Science University of Texas Rio Grande Valley BrownsvilleTX78520 United States School of Physical Mathematical Sciences Nanyang Technological University Singapore Singapore Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai200433 China

ISBN: (纸本)9783662491911

We consider autoreducibility of complete sets for the two common types of probabilistic polynomial-time reductions: RP reductions containing one-sided errors on positive input instances only, and BPP reductions containing two-sided errors. Specifically, we focus on the probabilistic counterparts of the deterministic many-one and truthtable autoreductions. We prove that non-trivial complete sets of NP are autoreducible for the RP many-one reduction. This extends the result by Glaßer et al. [9] that complete sets of NP are autoreducible for the deterministic many-one reduction. We also prove that complete sets of classes in the truth-table Polynomial Hierarchy, which is the polynomial hierarchy defined using the truth-table reduction instead of the general Turing reduction, are autoreducible with respect to the BPP truth-table reductions. This generalizes the result by Buhrman et al. [3] that truthtable- complete sets for NP are probabilistically truth-table autoreducible to multiple classes of higher complexity although for a weaker reduction. © Springer-Verlag Berlin Heidelberg 2016.

关键词： Polynomial approximation

来源：评论

学校读者我要写书评

暂无评论

Ambient carbon monoxide and daily mortality: a global time-series study in 337 cities

引用

The Lancet. Planetary health 2021年第4期5卷 e191-e199页

作者： Kai Chen Susanne Breitner Kathrin Wolf Massimo Stafoggia Francesco Sera Ana M Vicedo-Cabrera Yuming Guo Shilu Tong Eric Lavigne Patricia Matus Nicolás Valdés Haidong Kan Jouni J K Jaakkola Niilo R I Ryti Veronika Huber Matteo Scortichini Masahiro Hashizume Yasushi Honda Baltazar Nunes Joana Madureira Iulian Horia Holobâcă Simona Fratianni Ho Kim Whanhee Lee Aurelio Tobias Carmen Íñiguez Bertil Forsberg Christofer Åström Martina S Ragettli Yue-Liang Leon Guo Bing-Yu Chen Shanshan Li Ai Milojevic Antonella Zanobetti Joel Schwartz Michelle L Bell Antonio Gasparrini Alexandra Schneider Department of Environmental Health Sciences Yale School of Public Health New Haven CT USA. Electronic address: kai.chen@yale.edu. Institute of Epidemiology Helmholtz Zentrum München-German Research Center for Environmental Health Neuherberg Germany Institute for Medical Information Processing Biometry and Epidemiology Ludwig-Maximilians-Universität München Munich Germany. Institute of Epidemiology Helmholtz Zentrum München-German Research Center for Environmental Health Neuherberg Germany. Department of Epidemiology Lazio Regional Health Service Rome Italy. Department of Public Health Environments and Society London School of Hygiene & Tropical Medicine London UK Department of Statistics Computer Science and Applications "G. Parenti" University of Florence Florence Italy. Institute of Social and Preventive Medicine University of Bern Bern Switzerland Oeschger Center for Climate Change Research University of Bern Bern Switzerland. Climate Air Quality Research Unit School of Public Health and Preventive Medicine Monash University Melbourne VIC Australia. Shanghai Children's Medical Center Shanghai Jiao Tong University School of Medicine Shanghai China School of Public Health Institute of Environment and Population Health Anhui Medical University Hefei China School of Public Health and Social Work Queensland University of Technology Brisbane QLD Australia Center for Global Health School of Public Health Nanjing Medical University Nanjing China. Air Health Science Division Health Canada Ottawa ON Canada School of Epidemiology and Public Health University of Ottawa Ottawa ON Canada. Department of Public Health Universidad de los Andes Santiago Chile. Faculty of Nursing and Midwifery Universidad de los Andes Santiago Chile. School of Public Health Key Lab of Public Health Safety of the Ministry of Education and Key Lab of Health Technology Assessment of the Ministry of Health Fudan University Shanghai China Shanghai Key Laboratory of Atmospheric Part

BACKGROUND:Epidemiological evidence on short-term association between ambient carbon monoxide (CO) and mortality is inconclusive and limited to single cities, regions, or countries. Generalisation of results from previous studies is hindered by potential publication bias and different modelling approaches. We therefore assessed the association between short-term exposure to ambient CO and daily mortality in a multicity, multicountry setting. METHODS:We collected daily data on air pollution, meteorology, and total mortality from 337 cities in 18 countries or regions, covering various periods from 1979 to 2016. All included cities had at least 2 years of both CO and mortality data. We estimated city-specific associations using confounder-adjusted generalised additive models with a quasi-Poisson distribution, and then pooled the estimates, accounting for their statistical uncertainty, using a random-effects multilevel meta-analytical model. We also assessed the overall shape of the exposure-response curve and evaluated the possibility of a threshold below which health is not affected. FINDINGS:Overall, a 1 mg/m increase in the average CO concentration of the previous day was associated with a 0·91% (95% CI 0·32-1·50) increase in daily total mortality. The pooled exposure-response curve showed a continuously elevated mortality risk with increasing CO concentrations, suggesting no threshold. The exposure-response curve was steeper at daily CO levels lower than 1 mg/m, indicating greater risk of mortality per increment in CO exposure, and persisted at daily concentrations as low as 0·6 mg/m or less. The association remained similar after adjustment for ozone but was attenuated after adjustment for particulate matter or sulphur dioxide, or even reduced to null after adjustment for nitrogen dioxide. INTERPRETATION:This international study is by far the largest epidemiological investigation on short-term CO-related mortality. We found significant associations between ambient

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cached long short-term memory neural networks for document-level sentiment classification

Cached long short-term memory neural networks for document-l...

引用

2016 Conference on Empirical Methods in Natural Language processing, EMNLP 2016

作者： Xu, Jiacheng Chen, Danlu Qiu, Xipeng Huang, Xuanjing Software School Fudan University 825 Zhangheng Road Shanghai China School of Computer Science Fudan University 825 Zhangheng Road Shanghai China Shanghai Key Laboratory of Intelligent Information Processing Fudan University 825 Zhangheng Road Shanghai China

ISBN: (纸本)9781945626258

Recently, neural networks have achieved great success on sentiment classification due to their ability to alleviate feature engineering. However, one of the remaining challenges is to model long texts in document-level sentiment classification under a recurrent architecture because of the deficiency of the memory unit. To address this problem, we present a Cached Long Short-Term Memory neural networks (CLSTM) to capture the overall semantic information in long texts. CLSTM introduces a cache mechanism, which divides memory into several groups with different forgetting rates and thus enables the network to keep sentiment information better within a recurrent unit. The proposed CLSTM outperforms the state-of-the-art models on three publicly available document-level sentiment analysis datasets. © 2016 Association for Computational Linguistics

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

GLAD: Global-local-alignment descriptor for pedestrian retrieval

arXiv

引用

arXiv 2017年

作者： Wei, Longhui Zhang, Shiliang Yao, Hantao Gao, Wen Tian, Qi School of Electronic Engineering and Computer Science Peking University Beijing100871 China Key Lab of Intelligent Information Processing of CAS Institute of Computing Technology CAS Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249-1604 United States

The huge variance of human pose and the misalignment of detected human images significantly increase the difficulty of person Re-Identification (Re-ID). Moreover, efficient Re-ID systems are required to cope with the massive visual data being produced by video surveillance systems. Targeting to solve these problems, this work proposes a Global-Local-Alignment Descriptor (GLAD) and an efficient indexing and retrieval framework, respectively. GLAD explicitly leverages the local and global cues in human body to generate a discriminative and robust representation. It consists of part extraction and descriptor learning modules, where several part regions are first detected and then deep neural networks are designed for representation learning on both the local and global regions. A hierarchical indexing and retrieval framework is designed to eliminate the huge redundancy in the gallery set, and accelerate the online Re-ID procedure. Extensive experimental results show GLAD achieves competitive accuracy compared to the state-of-the-art methods. Our retrieval framework significantly accelerates the online Re-ID procedure without loss of accuracy. Therefore, this work has potential to work better on person Re-ID tasks in real scenarios. Copyright © 2017, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Biogeography-based optimization for cluster analysis

Biogeography-based optimization for cluster analysis

引用

International Conference on computer, Communication and Computational sciences, ICCCCS 2016

作者： Wu, Xueyan Wang, Hainan Chen, Zhimin Lu, Zhihai Phillips, Preetha Wang, Shuihua Zhang, Yudong School of Computer Science and Technology Nanjing Normal University NanjingJiangsu210023 China Key Laboratory of Statistical Information Technology & Data Mining State Statistics Bureau ChengduSichuan610225 China School of Computer and Information Engineering Henan Normal University XinxiangHenan453000 China School of Electronic Information Shanghai Dianji University Shanghai200240 China Key Laboratory of Symbolic Computation & Knowledge Engineering of Ministry of Education Jilin University ChangchunJilin130012 China Guangxi Key Laboratory of Manufacturing System & Advanced Manufacturing Technology GuilinGuangxi541004 China School of Natural Sciences and Mathematics Shepherd University ShepherdstownWV25443 United States West Virginia School of Osteopathic Medicine 400 N Lee St LewisburgWV24901 United States Department of Electrical Engineering The City College of New York CUNY New YorkNY10031 United States State Key Lab of CAD & CG Zhejiang University HangzhouZhejiang310027 China Manchester Metropolitan University ManchesterM156BH United Kingdom

ISBN: (纸本)9789811037696

With the aim of resolving the issue of cluster analysis more precisely and validly, a new approach was proposed based on biogeography-based optimization (abbreviated as BBO) algorithm. (Method) First, we reformulated the problem with an optimization model based on the variance ratio criterion (VARAC). Then, BBO was presented to search the optimal solution of the VARAC. There are 400 data of four groups in the experimental dataset, which have the degrees of overlapping of three distinct scales. The first one is nonoverlapping, the second one is partial overlapping, and the last is severely overlapping. BBO algorithm was compared with three different state-of-the-art approaches. We ran every algorithm 20 times. In this experiment, our results demonstrate the maximum VARAC values that can be found by BBO. The conclusion is that BBO is predominant which is extremely quick for the issue of clustering analysis. © Springer Nature Singapore Pte Ltd. 2017.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

Extending the nested parallel model to the nested dataflow model with provably efficient schedulers 16

Extending the nested parallel model to the nested dataflow m...

引用

28th ACM Symposium on Parallelism in Algorithms and Architectures, SPAA 2016

作者： Dinh, David Simhadri, Harsha Vardhan Tang, Yuan Computer Science Division Univ. of California Berkeley BerkeleyCA94720 United States Computer Science Dept. Lawrence Berkeley National Lab. BerkeleyCA94720 United States School of Software Fudan Univ. Shanghai Key Lab. of Intelligent Information Processing Shanghai200433 China

ISBN: (纸本)9781450342100

The nested parallel (a.k.a. fork-join) model is widely used for writing parallel programs. However, the two composition constructs, i.e. "k" (parallel) and "k" (serial), that comprise the nested-parallel model are insufficient in expressing "partial dependencies" in a program. We propose a new dataflow composition construct "" to express partial dependencies in algorithms in a processorand cache-oblivious way, thus extending the Nested Parallel (NP) model to the Nested Dataflow (ND) model. We redesign several divide-and-conquer algorithms ranging from dense linear algebra to dynamic-programming in the ND model and prove that they all have optimal span while retaining optimal cache complexity. We propose the design of runtime schedulers that map ND programs to multicore processors with multiple levels of possibly shared caches (i.e, Parallel Memory Hierarchies) and prove guarantees on their ability to balance nodes across processors and preserve locality. For this, we adapt space-bounded (SB) schedulers for the ND model. We show that our algorithms have increased "parallelizability" in the ND model, and that SB schedulers can use the extra parallelizability to achieve asymptotically optimal bounds on cache misses and running time on a greater number of processors than in the NP model. The running time for the algorithms in this paper is(Equation presented on a p-processor machine, where Q∗ is the parallel cache complexity of task t, Ci is the cost of cache miss at level-i cache which is of size Mi, and σ ∈ (0,1) is a constant.

关键词： Parallel processing systems

来源：评论

学校读者我要写书评

暂无评论

Large-scale person re-identification as retrieval

Large-scale person re-identification as retrieval

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Hantao Yao Shiliang Zhang Dongming Zhang Yongdong Zhang Jintao Li Yu Wang Qi Tian University of Chinese Academy of Sciences Beijing China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China School of Electronic Engineering and Computer Science Peking University Beijing China National Computer Network Emergency Response Technical Team/Coordination Center of China Department of Computer Science University of Texas at San Antonio San Antonio USA

ISBN: (纸本)9781509060689

This paper targets to bring together the research efforts on two fields that are growing actively in the past few years: multicamera person Re-Identification (ReID) and large-scale image retrieval. We demonstrate that the essentials of image retrieval and person ReID are the same, i.e., measuring the similarity between images. However, person ReID requires more discriminative and robust features to identify the subtle differences of different persons and overcome the large variance among images of the same person. Specifically, we propose a coarse-to-fine (C2F) framework and a Convolutional Neural Network structure named as Conv-Net to tackle the large-scale person ReID as an image retrieval task. Given a query person image, the C2F firstly employ Conv-Net to extract a compact descriptor and perform the coarse-level search. A robust descriptor conveying more spatial cues is hence extracted to perform the fine-level search. Extensive experimental results show that the proposed method outperforms existing methods on two public datasets. Further, the evaluation on a large-scale Person-520K dataset demonstrates that our work is significantly more efficient than existing works, e.g., only needs 180ms to identify a query person from 520K images.

关键词： Training Feature extraction Cameras Robustness Image retrieval Linear programming

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：