检索结果-内蒙古大学图书馆

26th International Conference on Computational Linguistics, COLING 2016

作者： Li, Wei He, Lei Zhuge, Hai Key Lab. of Intelligent Information Processing Institute of Computing Technology University of Chinese Academy of Sciences Beijing China Aston University Birmingham United Kingdom

ISBN: (纸本)9784879747020

This paper studies the abstractive multi-document summarization for event-oriented news texts through event information extraction and abstract representation. Fine-grained event mentions and semantic relations between them are extracted to build a unified and connected event semantic link network, an abstract representation of source texts. A network reduction algorithm is proposed to summarize the most salient and coherent event information. New sentences with good linguistic quality are automatically generated and selected through sentences over-generation and greedy-selection processes. Experimental results on DUC 2006 and DUC 2007 datasets show that our system significantly outperforms the state-of-the-art extractive and abstractive baselines under both pyramid and ROUGE evaluation metrics. © 1963-2018 ACL.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Evolving boxes for fast vehicle detection

Evolving boxes for fast vehicle detection

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Li Wang Yao Lu Hong Wang Yingbin Zheng Hao Ye Xiangyang Xue Shanghai Key Lab of Intelligent Information Processing Fudan University Shanghai China Chinese Academy of Sciences Shanghai Advanced Research Institute Shanghai China School of Computer Science and Engineering University of Washington Seattle USA

ISBN: (纸本)9781509060689

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our framework is embedded with a light-weight proposal network to generate initial anchor boxes as well as to early discard unlikely regions; a fine-turning network produces detailed features for these candidate boxes. We show intriguingly that by applying different feature fusion techniques, the initial boxes can be refined for both localization and recognition. We evaluate our network on the recent DETRAC benchmark and obtain a significant improvement over the state-of-the-art Faster RCNN by 9.5% mAP. Further, our network achieves 9-13 FPS detection speed on a moderate commercial GPU.

关键词： Proposals Vehicle detection Machine learning Training Detectors Object detection Surveillance

来源：评论

学校读者我要写书评

暂无评论

Live cell single molecule-guided Bayesian localization super resolution microscopy

引用

细胞研究（英文版） 2017年第5期27卷 713-716页

作者： Mingshu Zhang Wenting He Zhiyong Liu Fa Zhang Jennifer Lippincott-Schwartz Key Laboratory of RNA Biology Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China Beijing Key Laboratory of Noncoding RNA Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China Janelia Research Campus Howard Hughes Medical Institute Ashburn Virginia 20147 USA

Dear Editor,Many current super resolution (SR) microscopic techniques [1-6] have been successfully applied to image cellular dynamics in living cells,but their applications have remained technically *** cell stimulated emission depletion (STED)/reversible saturable optical linear fluorescence transitions (RESOLFT) microscopy and structured illumination microscopy (SIM)/nonlinear SIM require sophisticated expensive optical setups and specialized expertise for accurate optical *** cell photo-activated localization microscopy (PALM)/stochastic optical reconstruction microscopy (STORM)use less complicated setup;however,a scientific complementary metal-oxide-semiconductor (sCMOS) camera,whose pixel-dependent noise must be characterized and calibrated before use [7],is required for extremely high acquisition speed over tens of thousands of ***,wide field-based SR microscopies have been developed to improve temporal resolution using much fewer time-lapse images (hundreds to thousands) than PALM/STORM [8,9].One of them,Bayesian analysis of the blinking and bleaching (3B) [8],offers enormous potential to resolve ultrastructure and fast cellular dynamics in living cells beyond the diffraction *** its potential,3B analysis is impractical when imaging the nanoscale dynamics in large fields of view over long time periods,as the calculation is extremely time-consuming [8] and/or the analysis consumes large amounts of web resources [10].Another major problem of 3B imaging is the artificial thinning and thickening of structures both in simulated image data and in experimental data [8,10].

关键词： @@

来源：评论

学校读者我要写书评

暂无评论

Evolving boxes for fast vehicle detection

arXiv

引用

arXiv 2017年

作者： Wang, Li Lu, Yao Wang, Hong Zheng, Yingbin Ye, Hao Xue, Xiangyang Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Shanghai Advanced Research Institute Chinese Academy of Sciences Shanghai China School of Computer Science and Engineering University of Washington Seattle United States

We perform fast vehicle detection from traffic surveillance cameras. A novel deep learning framework, namely Evolving Boxes, is developed that proposes and refines the object boxes under different feature representations. Specifically, our framework is embedded with a light-weight proposal network to generate initial anchor boxes as well as to early discard unlikely regions;a fine-turning network produces detailed features for these candidate boxes. We show intriguingly that by applying different feature fusion techniques, the initial boxes can be refined for both localization and recognition. We evaluate our network on the recent DETRAC benchmark and obtain a significant improvement over the state-of-the-art Faster RCNN by 9.5% mAP. Further, our network achieves 9-13 FPS detection speed on a moderate commercial GPU. 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

Interactive attention for neural machine translation 26

Interactive attention for neural machine translation

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： Meng, Fandong Lu, Zhengdong Li, Hang Liu, Qun AI Platform Department Tencent Technology Co. Ltd. China Noah's Ark Lab. Huawei Technologies China ADAPT Centre School of Computing Dublin City University Ireland Key Lab. of Intelligent Information Processing Institute of Computing Technology CAS Ireland

ISBN: (纸本)9784879747020

Conventional attention-based Neural Machine Translation (NMT) conducts dynamic alignment in generating the target sentence. By repeatedly reading the representation of source sentence, which keeps fixed after generated by the encoder (Bahdanau et al., 2015), the attention mechanism has greatly enhanced state-of-the-art NMT. In this paper, we propose a new attention mechanism, called INTERACTIVE ATTENTION, which models the interaction between the decoder and the representation of source sentence during translation by both reading and writing operations. INTERACTIVE ATTENTION can keep track of the interaction history and therefore improve the translation performance. Experiments on NIST Chinese-English translation task show that INTERACTIVE ATTENTION can achieve significant improvements over both the previous attention-based NMT baseline and some state-of-the-art variants of attention-based NMT (i.e., coverage models (Tu et al., 2016)). And neural machine translator with our INTERACTIVE ATTENTION can outperform the open source attention-based NMT system Groundhog by 4.22 BLEU points and the open source phrase-based system Moses by 3.94 BLEU points averagely on multiple test sets. © 1963-2018 ACL.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Exploring differential topic models for comparative summarization of scientific papers 26

Exploring differential topic models for comparative summariz...

引用

26th International Conference on Computational Linguistics, COLING 2016

作者： He, Lei Li, Wei Zhuge, Hai System Analytics Research Institute Aston University Birmingham United Kingdom Key Lab. of Intelligent Information Processing ICT CAS University of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9784879747020

This paper investigates differential topic models (dTM) for summarizing the differences among document groups. Starting from a simple probabilistic generative model, we propose dTM-SAGE that explicitly models the deviations on group-specific word distributions to indicate how words are used differentially across different document groups from a background word distribution. It is more effective to capture unique characteristics for comparing document groups. To generate dTM-based comparative summaries, we propose two sentence scoring methods for measuring the sentence discriminative capacity. Experimental results on scientific papers dataset show that our dTM-based comparative summarization methods significantly outperform the generic baselines and the state-of-the-art comparative summarization methods under ROUGE metrics. © 1963-2018 ACL.

关键词： Probability distributions

来源：评论

学校读者我要写书评

暂无评论

Emotion detection from natural walking 1

引用

2nd International Conference on Human Centered computing, HCC 2016

作者： Cui, Liqing Li, Shun Zhu, Tingshao Beijing100101 China National Computer System Engineering Research Institute of China Beijing100083 China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China

ISBN: (数字)9783319318547

ISBN: (纸本)9783319318530

Emotion identification, which aims to determine a person’s affective state automatically, has immense potential value in many areas, such as action tendency, health care, psychological detection and human-computer (robot) interaction. In this paper, we propose a novel method for identifying emotion from natural walking. After obtaining the three-axis acceleration data of wrist and ankle recorded by smartphone, we run a moving average filter window with different length w, then cut actual data into slices. 114 features are extracted from each slice, and Principal Component Analysis (PCA) is used for feature selection. We train SVM, Decision Tree, Multilayerperception, Random Tree and Random Forest classifiers, and compare the accuracy of emotion identification using different datasets (wrist vs. ankle) on different models. Results show that acceleration data from ankle has better performance in emotion identification than wrist. Among these models, SVM has the highest accuracy of 90.31 % for identifying anger vs. neutral, 89.76 % for happy vs. neutral, and 87.10 % for anger vs. happy. The model for identifying anger/neutral/happy yields the best accuracy of 85 %-78 %-78 %. The results show that we could identify people’s emotional states through the gait of walking with high accuracy. © Springer International Publishing Switzerland 2016.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

A local-optimization refinement algorithm in single particle analysis for macromolecular complex with multiple rigid modules

引用

Protein & Cell 2016年第1期7卷 46-62页

作者： Hong Shan Zihao wang Fa Zhang Yong Xiong Chang-Cheng Yin Fei Sun Department of Biophysics College of Basic Medical Sciences Peking University Health Science Center Beijing 100191China National Laboratory of Biomacromolecules Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China Key Lab of Intelligent Information Processing and Advanced Computing Research Lab Institute of Computing TechnologyChinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China Department of Molecular Biophysics and Biochemistry Yale University New Haven CT 06511 USA Center for Biological Imaging Institute of Biophysics Chinese Academy of Sciences Beijing 100101 China

Single particle analysis, which can be regarded as an average of signals from thousands or even millions of particle projections, is an efficient method to study the three-dimensional structures of biological macro- molecules. An intrinsic assumption in single particle analysis is that all the analyzed particles must have identical composition and conformation. Thus specimen heterogeneity in either composition or conformation has raised great challenges for high-resolution analysis. For particles with multiple conformations, inaccurate align- ments and orientation parameters will yield an averaged map with diminished resolution and smeared density. Besides extensive classification approaches, here based on the assumption that the macromolecular complex is made up of multiple rigid modules whose relative orien- tations and positions are in slight fluctuation around equilibriums, we propose a new method called as local optimization refinement to address this conformational heterogeneity for an improved resolution. The key idea is to optimize the orientation and shift parameters of each rigid module and then reconstruct their three-dimen- sional structures individually. Using simulated data of 80S/70S ribosomes with relative fluctuations between the large （60S/50S） and the small （40S/30S） subunits, we tested this algorithm and found that the resolutions of both subunits are significantly improved. Our method provides a proof-of-principle solution for high-resolutionsingle particle analysis of macromolecular complexes with dynamic conformations.

关键词： cryo-electron microscopy single particleanalysis conformational heterogeneity rigid module Iocaoptimization refinement

来源：评论

学校读者我要写书评

暂无评论

Summarization of Related Work through Citations 12

Summarization of Related Work through Citations

引用

12th International Conference on Semantics, Knowledge and Grids, SKG 2016

作者： Chen, Jingqiang Zhuge, Hai Nanjing University of Posts and Telecommunications 210023 Nanjing China. Key Lab of Intelligent Information Processing Institute of Computing Technology University of Chinese Academy of Sciences 100190 Beijing China. Systems Analytics Research Institute Aston University Birmingham UK

ISBN: (纸本)9781509047956

Automatically generating the related work section for a writing paper is useful for researchers as it can save a lot of time and avoid missing related works. The related work section of scientific paper usually introduces other researchers' work published before and makes comparisons with the current author's work. This paper proposes an approach to automatically generating related work by comparing the main text of the writing paper with the citations to the references from other papers. Our approach firstly collects the papers that cite the reference papers of the writing paper and extracts the corresponding citation sentences to form a citation document. It then makes a summarization that makes a comparison between the citation document and the writing paper's abstract, introduction and conclusion. It extracts the representative keywords from the citation document and the writing paper, and constructs a graph of the keywords. The discriminated nodes in the graph are figured out, and then the minimum Steiner tree that covers the nodes is extracted. A summary is generated by extracting the sentences covering the Steiner tree. The experiments show that our approach outperforms three baselines MEAD, ReWoS and ARWG according to ROUGE evaluation results. © 2016 IEEE.

关键词： Trees (mathematics)

来源：评论

学校读者我要写书评

暂无评论

Category aggregation among region proposals for object detection 17th

Category aggregation among region proposals for object detec...

引用

17th Pacific-Rim Conference on Multimedia, PCM 2016

作者： Li, Linghui Tang, Sheng Zhou, Jianshe Wang, Bin Tian, Qi Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing100190 China Beijing Advanced Innovation Center for Imaging Technology Capital Normal University Beijing100048 China Department of Computer Science University of Texas at San Antonio San AntonioTX78249-1604 United States

ISBN: (纸本)9783319488950

Recently, an overwhelming majority of object detection methods have focused on how to reduce the number of region proposals while keeping high object recall without consideration of category information. It may lead to a lot of false positives due to the interferences between categories especially when the number of categories is very large. To eliminate such interferences, we propose a novel category aggregation approach based upon our observation that more frequently detected categories around an object have the higher probabilities to be present in an image. After further exploiting the co-occurrence relationship between categories, we can determine the most possible categories for an image in advance. Thus, many false positives can be greatly filtered out before subsequent classification process. Our extensive experiments on the well-known ILSVRC 2015 detection dataset show that our approach can achieve 49.0% of mAP in the validation dataset and 45.36% of mAP in the test dataset ranked 5th in the ILSVRC 2015 detection task. © Springer International Publishing AG 2016.

关键词： Object detection

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：