检索结果-内蒙古大学图书馆

29th British Machine Vision Conference, BMVC 2018

作者： Li, Yu Tang, Sheng Lin, Min Guo, Junbo Li, Jintao Yan, Shuicheng Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China University of the Chinese Academy of Sciences Beijing China AI institute Qihoo 360 Beijing China

In order to alleviate the exposure bias problem caused by the discrepancy between training and testing strategies, we propose an Inverse Reinforcement Learning (IRL) based learning and thinking strategy for sequence generation. First, a task-agnostic reward is learned to evaluate the appropriateness of the generated tokens at each time step with the knowledge of ground truth token and current RNN models. With this reward, a deep SARSA network is then designed to meditate among the whole space. Therefore, it can fill in the space that has not been exposed during training with a better policy than the original RNN model. Sequence generation experiments on various text corpus show significant improvements over strong baseline and demonstrate the effectiveness of our method. © 2018. The copyright of this document resides with its authors.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Graph Decoupling Attention Markov Networks for Semi-supervised Graph Node Classification

arXiv

引用

arXiv 2021年

作者： Chen, Jie Chen, Shouzhen Bai, Mingyuan Pu, Jian Zhang, Junping Gao, Junbin Shanghai Key Lab of Intelligent Information Processing The School of Computer Science Fudan University Shanghai200433 China The Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai200433 China The University of Sydney Business School The University of Sydney DarlingtonNSW2006 Australia

Graph neural networks (GNN) have been ubiquitous in graph node classification tasks Most of GNN methods update the node embedding iteratively by aggregating its neighbors’ information However, they often suffer from negative disturbance, due to edges connecting nodes with different lab.ls One approach to alleviate this negative disturbance is to use attention to learn the weights of aggregation, but current attention-based GNNs only consider feature similarity and also suffer from the lack of supervision In this paper, we consider the lab.l dependency of graph nodes and propose a decoupling attention mechanism to learn both hard and soft attention The hard attention is learned on lab.ls for a refined graph structure with fewer inter-class edges, so that the aggregation’s negative disturbance can be reduced The soft attention aims to learn the aggregation weights based on features over the refined graph structure to enhance information gains during message passing Particularly, we formulate our model under the EM framework, and the learned attention is used to guide the lab.l propagation in the M-step and the feature propagation in the E-step, respectively Extensive experiments are performed on six well-known benchmark graph datasets to verify the effectiveness of the proposed method. Copyright © 2021, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Extracting variable-depth logical document hierarchy from long documents: Method, evaluation, and application

arXiv

引用

arXiv 2021年

作者： Cao, Rong-Yu Cao, Yi-Xuan Zhou, Gan-Bin Luo, Ping Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China WeChat Search Application Department Tencent Holdings Ltd. Beijing100080 China Peng Cheng Laboratory Shenzhen518066 China

In this paper, we study the problem of extracting variable-depth "logical document hierarchy" from long documents, namely organizing the recognized "physical document objects" into hierarchical structures. The discovery of logical document hierarchy is the vital step to support many downstream applications (e.g. passage-based retrieval and high-quality information extraction). However, long documents, containing hundreds or even thousands of pages and variable-depth hierarchy, challenge the existing methods. To address these challenges, we develop a framework, namely Hierarchy Extraction from Long Document (HELD), where we "sequentially" insert each physical object at the proper on of the current tree. Determining whether each possible position is proper or not can be formulated as a binary classification problem. To further improve its effectiveness and efficiency, we study the design variants in HELD, including traversal orders of the insertion positions, heading extraction explicitly or implicitly, tolerance to insertion errors in predecessor steps, and so on. As for evaluations, we find that previous studies ignore the error that the depth of a node is correct while its path to the root is wrong. Since such mistakes may worsen the downstream applications seriously, a new measure is developed for more careful evaluation. The empirical experiments based on thousands of long documents from Chinese, English financial market and English scientific publication show that the HELD model with the "root-to-leaf" traversal order and explicit heading extraction is the best choice to achieve the tradeoff between effectiveness and efficiency with the accuracy of 0.9726, 0.7291 and 0.9578 in Chinese financial, English financial and arXiv datasets, respectively. Finally, we show that logical document hierarchy can be employed to significantly improve the performance of the downstream passage retrieval task. In summary, we conduct a systematic study on this task in terms of meth

关键词： Finance

来源：评论

学校读者我要写书评

暂无评论

Mutual information Maximization for Effective Lip Reading

Mutual Information Maximization for Effective Lip Reading

引用

International Conference on Automatic Face and Gesture Recognition

作者： Xing Zhao Shuang Yang Shiguang Shan Xilin Chen Zhejiang University of Technology Hangzhou China Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9781728130798

ISBN: (纸本)9781728130804

Lip reading has received an increasing research interest in recent years due to the rapid development of deep learning and its widespread potential applications. One key point to obtain good performance for the lip reading task depends heavily on how effective the representation can be used to capture the lip movement information and meanwhile to resist the noises resulted by the change of pose, lighting conditions, speaker's appearance, speaking speed and so on. Towards this target, we propose to introduce the mutual information constraints on both the local feature's level and the global sequence's level to enhance the relations of them with the speech content. On the one hand, we require the features generated at each time step to carry a strong relation with the speech content by imposing the local mutual information maximization constraint (LMIM), so as to improve the model's ability to discover fine-grained lip movements and the finegrained differences between words with similar pronunciation, such as “spend” and “spending”. On the other hand, we introduce the mutual information maximization constraint on the global sequence's level (GMIM), to make the model be able to pay more attention to discriminate key frames related with the speech content, and less to various noises appeared in the speaking process. By combining these two advantages together, the proposed method is expected to be both discriminative and robust for effective lip reading. To verify this method, we evaluate on two large-scale benchmarks whose videos are collected from several TV shows with a wide coverage of the speaking conditions. We perform a detailed analysis and comparison on several aspects, including the comparison with the baseline of the LMIM and GMIM, and the visualization of the learned representation. The results not only prove the effectiveness of the proposed method but also report new state-of-the-art performance on both the two benchmarks.

关键词： Lips Hidden Markov models Mutual information Task analysis Visualization Feature extraction Deep learning

来源：评论

学校读者我要写书评

暂无评论

Single-Side Domain Generalization for Face Anti-Spoofing

Single-Side Domain Generalization for Face Anti-Spoofing

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yunpei Jia Jie Zhang Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Existing domain generalization methods for face anti-spoofing endeavor to extract common differentiation features to improve the generalization. However, due to large distribution discrepancies among fake faces of different domains, it is difficult to seek a compact and generalized feature space for the fake faces. In this work, we propose an end-to-end single-side domain generalization framework (SSDG) to improve the generalization ability of face anti-spoofing. The main idea is to learn a generalized feature space, where the feature distribution of the real faces is compact while that of the fake ones is dispersed among domains but compact within each domain. Specifically, a feature generator is trained to make only the real faces from different domains undistinguishable, but not for the fake ones, thus forming a single-side adversarial learning. Moreover, an asymmetric triplet loss is designed to constrain the fake faces of different domains separated while the real ones aggregated. The above two points are integrated into a unified framework in an end-to-end training manner, resulting in a more generalized class boundary, especially good for samples from novel domains. Feature and weight normalization is incorporated to further improve the generalization ability. Extensive experiments show that our proposed approach is effective and outperforms the state-of-the-art methods on four public databases. The code is released online.

关键词： Face Feature extraction Generators Training Aggregates Databases Face recognition

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation With Hierarchical Gradient Synchronization

Unsupervised Domain Adaptation With Hierarchical Gradient Sy...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Lanqing Hu Meina Kan Shiguang Shan Xilin Chen Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China University of Chinese Academy of Sciences Beijing China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai China

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

Domain adaptation attempts to boost the performance on a target domain by borrowing knowledge from a well established source domain. To handle the distribution gap between two domains, the prominent approaches endeavor to extract domain-invariant features. It is known that after a perfect domain alignment the domain-invariant representations of two domains should share the same characteristics from perspective of the overview and also any local piece. Inspired by this, we propose a novel method called Hierarchical Gradient Synchronization to model the synchronization relationship among the local distribution pieces and global distribution, aiming for more precise domain-invariant features. Specifically, the hierarchical domain alignments including class-wise alignment, group-wise alignment and global alignment are first constructed. Then, these three types of alignment are constrained to be consistent to ensure better structure preservation. As a result, the obtained features are domain invariant and intrinsically structure preserved. As evaluated on extensive domain adaptation tasks, our proposed method achieves state-of-the-art classification performance on both vanilla unsupervised domain adaptation and partial domain adaptation.

关键词： Feature extraction Synchronization Entropy Task analysis Training Adaptation models

来源：评论

学校读者我要写书评

暂无评论

A review on vision-based analysis for automatic dietary assessment

arXiv

引用

arXiv 2021年

作者： Wang, Wei Min, Weiqing Li, Tianhao Dong, Xiaoxiao Li, Haisheng Jiang, Shuqiang School of Computer and Engineering Beijing Technology and Business University Beijing100048 China The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Beijing Key Laboratory of Big Data Technology for Food Safety Beijing100048 China National Engineering Laboratory for Agri-product Quality Traceability Beijing100048 China University of Chinese Academy of Sciences Beijing100049 China

Background: Maintaining a healthy diet is vital to avoid health-related issues, e.g., undernutrition, obesity and many non-communicable diseases. An indispensable part of the health diet is dietary assessment. Traditional manual recording methods are not only burdensome but timeconsuming, and contain substantial biases and errors. Recent advances in Artificial Intelligence (AI), especially computer vision technologies, have made it possible to develop automatic dietary assessment solutions, which are more convenient, less time-consuming and even more accurate to monitor daily food intake. Scope and approach: This review presents Vision-Based Dietary Assessment (VBDA) architectures, including multi-stage architecture and end-to-end one. The multi-stage dietary assessment generally consists of three stages: food image analysis, volume estimation and nutrient derivation. The prosperity of deep learning makes VBDA gradually move to an end-to-end implementation, which applies food images to a single network to directly estimate the nutrition. The recently proposed end-to-end methods are also discussed. We further analyze existing dietary assessment datasets, indicating that one large-scale benchmark is urgently needed, and finally highlight critical challenges and future trends for VBDA. key findings and conclusions: After thorough exploration, we find that multi-task end-to-end deep learning approaches are one important trend of VBDA. Despite considerable research progress, many challenges remain for VBDA due to the meal complexity. We also provide the latest ideas for future development of VBDA, e.g., fine-grained food analysis and accurate volume estimation. This review aims to encourage researchers to propose more practical solutions for VBDA. Copyright © 2021, The Authors. All rights reserved.

关键词： Nutrition

来源：评论

学校读者我要写书评

暂无评论

Glycan immunogenicity prediction based on Graph neural network

Glycan immunogenicity prediction based on Graph neural netwo...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yu Wang Hui Wang Meijie Hou Yaojun Wang Dongbo Bu Chunming Zhang Chuncui Huang Shiwei Sun Key Lab of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences 6 Kexueyuan South Road Beijing China 19 Yuquan Road University of Chinese Academy of Sciences Beijing China College of Information and Electrical Engineering China Agricultural University 17 Qinghua Donglu Beijing China Zhongke Big Data Academy Zhengzhou Henan China Phil Rivers Technology Beijing China 15 Datun Road Institute of Biophysics Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665429825

Glycans play important roles in a great variety of biological processes, and these roles are closely determined by the details of their structures. It becomes possible to acquire hidden features from glycan structures using deep learning method with the great progress in recent years. Unlike the linear chain of proteins and DNAs, branching is a unique feature of glycan structures, which makes it very difficult to directly apply deep learning models on glycans. Thus, how to comprehensively and efficiently describe glycans and use them as input to deep learning models still remains challenging. Here, a graph neural network (GNN) called GlyNet was used to obtain high-dimensional representation of glycans and predict their immunogenicity. Our method was applied in SugarBase, and it works more superiorly than the state-of-art method with accuracy increased from 91.7% to 95.6%.

关键词： Deep learning Proteins Spectroscopy Databases Conferences Biological processes Ions

来源：评论

学校读者我要写书评

暂无评论

Mechanical properties of individual core-shell-structured Sn O2@C nanofibers investigated by atomic force microscopy and finite element method

引用

Science China(Technological Sciences) 2018年第8期61卷 1144-1149页

作者： LIU Xing LI KeFeng DUAN XiaoLu HUANG YuTing LI Shuai LIU YiLin XU Fu LI Zheng ZHANG Ping DING YanHuai Institute of Rheological Mechanics Xiangtan University School of Science Harbin Institute of Technology at Shenzhen Key Laboratory of Intelligent Computing & Information Processing of Ministry of Education Xiangtan University

Although SnO_2-based nanomaterials used to be considered as being extraordinarily versatile for application to nanosensors,microelectronic devices, lithium-ion batteries, supercapacitors and other devices, the functionalities of SnO_2-based nanomaterials are severely limited by their intrinsic vulnerabilities. Facile electrospinning was used to prepare SnO_2 nanofibers coated with a protective carbon layer. The mechanical properties of individual core-shell-structured SnO_2@C nanofibers were investigated by atomic force microscopy and the finite element method. The elastic moduli of the carbon-coated SnO_2 nanofibers remarkably increased, suggesting that coating SnO_2 nanofibers with carbon could be an effective method of improving their mechanical properties.

关键词： SnO2 nanofiber core-shell structure elastic modulus atomic force microscopy finite element method

来源：评论

学校读者我要写书评

暂无评论

A Wideband Millimeter Wave E-shape Antenna in Package with Embedded Wafer Level Ball Grid Array technology

A Wideband Millimeter Wave E-shape Antenna in Package with E...

引用

International Conference on Numerical Electromagnetic Modeling and Optimization for RF, Microwave, and Terahertz Applications (NEMO)

作者： Bin Lu Haoran Zhu Zongming Duan Yuefei Dai Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhu University Hefei China Key Lab of Intelligent Computing & Signal Processing Ministry of Education Anhui University Hefei China Anhui Province Engineer Laboratory for Antennas and Microwave The 38th Research Institute of China Electronic Technology Group Corporationy Hefei China

ISBN: (数字)9781728169668

ISBN: (纸本)9781728169675

The feasibility of an antenna-in-package (AiP) concept is demonstrated for automotive radar sensors at the 77 GHz-band. Infineon's embedded wafer level ball grid array (eWLB) is employed as packaging technology. We developed a E-shape patch antenna in 6×6 mm 2 eWLB package that include 2×2 mm 2 dummy Si chips. From the simulated results of the proposed E-plane patch antenna, provides a wide bandwidth of 19.2% (|S 11 |

关键词： Patch antennas Radar antennas Sensors Broadband antennas Wideband Antenna arrays Electronics packaging

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：