检索结果-内蒙古大学图书馆

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

Exploring multi-loss function based attention framework for vehicle re-identification 10

Exploring multi-loss function based attention framework for ...

引用

10th International Conference on information Technology in Medicine and Education, ITME 2019

作者： Liu, Wei Zhang, Yi Luo, Zhiming Li, Shaozi East China Jiaotong University Jiangxi China Cognitive Science Department Xiamen University Fujian China Postdoc Center of Information and Communication Engineering Xiamen University China Key Lab. of Cogn. Computing and Intelligent Information Processing of Fujian Education Institutions Wuyishan China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering Yi Chang China

ISBN: (纸本)9781728139173

Vehicle Re-identification(Re-ID) refers to the task of matching a specific vehicle across multiple non-overlapping cameras. Precise vehicle Re-ID suffers from two main challenges: (1) different vehicle identities with a similar appearance of the same type have a subtle inter-instance discrepancy, (2) one vehicle usually has large intra-instance differences due to viewpoint and illumination variations. To address these challenges, in this paper, we proposed an Attention-based Framework for Vehicle Re-ID named AFVR, which combines the benefits of both the cross-entropy loss function and the triplet loss function. Experimental results on two popular vehicle Re-ID benchmarks demonstrate the effectiveness of our proposed method, compared with the state of the arts. © 2019 IEEE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

Earlier attention? Aspect-aware LSTM for aspect-based sentiment analysis

arXiv

引用

arXiv 2019年

作者： Xing, Bowen Liao, Lejian Song, Dandan Wang, Jingang Zhang, Fuzhen Wang, Zhongyuan Huang, Heyan Lab of High Volume Language Information Processing & Cloud Computing Beijing Lab of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology Meituan-Dianping Group

Aspect-based sentiment analysis (ABSA) aims to predict fine-grained sentiments of comments with respect to given aspect terms or categories. In previous ABSA methods, the importance of aspect has been realized and verified. Most existing LSTM-based models take aspect into account via the attention mechanism, where the attention weights are calculated after the context is modeled in the form of contextual vectors. However, aspect-related information may be already discarded and aspect-irrelevant information may be retained in classic LSTM cells in the context modeling process, which can be improved to generate more effective context representations. This paper proposes a novel variant of LSTM, termed as aspect-aware LSTM (AA-LSTM), which incorporates aspect information into LSTM cells in the context modeling stage before the attention mechanism. Therefore, our AA-LSTM can dynamically produce aspect-aware contextual representations. We experiment with several representative LSTM-based models by replacing the classic LSTM cells with the AA-LSTM cells. Experimental results on SemEval-2014 Datasets demonstrate the effectiveness of AA-LSTM. Copyright © 2019, The Authors. All rights reserved.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

CTSpine1K: A Large-Scale Dataset for Spinal Vertebrae Segmentation in Computed Tomography

arXiv

引用

arXiv 2021年

作者： Deng, Yang Wang, Ce Hui, Yuan Li, Qian Li, Jun Luo, Shiwei Sun, Mengke Quan, Quan Yang, Shuxin Hao, You Liu, Pengbo Xiao, Honghu Zhao, Chunpeng Wu, Xinbao Zhou, S. Kevin Key Lab of Intelligent Information Processing of Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China Suzhou Institute of Intelligent Computing Technology Chinese Academy of Sciences Suzhou215028 China School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou China Department of Radiology Guangzhou First People’s Hospital School of Medicine South China University of Technology Guangzhou510006 China Beijing Jishuitan Hospital Beijing100035 China

Spine-related diseases have high morbidity and cause a huge burden of social cost. Spine imaging is an essential tool for noninvasively visualizing and assessing spinal pathology. Segmenting vertebrae in computed tomography (CT) images has always been the base of quantitative medical image analysis for clinical diagnosis and surgery planning of spine diseases. Current publicly available annotated datasets on spinal vertebrae are small in size. Due to the lack of a large-scale annotated spine image dataset, the mainstream deep learning-based segmentation methods, which are data-driven, are heavily restricted. In this paper, we introduce a large-scale spine CT dataset called CTSpine1K, curated from multiple sources for vertebra segmentation, which contains 1,005 CT volumes with over 500,000 labeled vertebrae slices and 11,172 vertebrae belonging to different spinal conditions. Based on this dataset, we conducted several spinal vertebrae segmentation experiments to set the first benchmark. We believe that this large-scale dataset will facilitate further research in many spine-related image analysis tasks, including but not limited to vertebrae segmentation, labeling, 3D spine reconstruction from biplanar radiographs, and image superresolution and enhancement. Our dataset are publically available at https://***/data/archive/projects/africai_miccai2024_ctspine1k and https://***/MIRACLE-Center/CTSpine1K. . © 2021, CC BY.

关键词： Computerized tomography

来源：评论

学校读者我要写书评

暂无评论

Meta-Path Hierarchical Heterogeneous Graph Convolution Network for High Potential Scholar Recognition

Meta-Path Hierarchical Heterogeneous Graph Convolution Netwo...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Yiqing Wu Ying Sun Fuzhen Zhuang Deqing Wang Xiangliang Zhang Qing He Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology University of Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University China King Abdullah University of Science and Technology Saudi Arabia

ISBN: (数字)9781728183169

ISBN: (纸本)9781728183176

Recognizing high potential scholars has become an important problem in recent years. However, conventional scholar evaluating methods based on hand-crafted metrics can not profile the scholars in a dynamic and comprehensive way. With the development of online academic databases, large-scale academic activity data become available, which implies detailed information on the scholars' achievement and academic activities. Inspired by the recent success of deep graph neural networks (GNNs), we propose a novel solution to recognize high potential scholars on the dynamic heterogeneous academic network. Specifically, we propose a novel Mate-path Hierarchical Heterogeneous Graph Convolution Network (MHHGCN) to effectively model the heterogeneous graph information. MHHGCN hierarchically aggregates entity and relational information on a set of meta-paths, and can alleviate the information loss problem in the previous heterogenous GNN models. Then to capture the dynamic scholar feature, we combine MHHGCN with Long Short Term Memory (LSTM) network with attention mechanism to model the temporal information and predict the potential scholar. Extensive experimental results on real-world high potential scholar data demonstrate the effectiveness of our approach. Moreover, the model shows high interpretability by visualization of the attention layers.

关键词： Measurement Convolution Aggregates Data visualization Predictive models Graph neural networks Long short term memory

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

Interference-assisted kaleidoscopic meta-plexer for arbitrary spin-wavefront manipulation

引用

Light(Science & Applications) 2019年第1期8卷 1141-1150页

作者： He-Xiu Xu Guangwei Hu Ying Li Lei Han Jianlin Zhao Yunming Sun Fang Yuan Guang-Ming Wang Zhi Hao Jiang Xiaohui Ling Tie Jun Cui Cheng-Wei Qiu Department of Electrical and Computer Engineering National University of SingaporeSingapore 117583Singapore Air and Missile Defense College Air force Engineering University710051 Xi’anChina Hunan Provincial Key Laboratory of Intelligent Information Processing and Applications College of Physics and Electronics EngineeringHengyang Normal University421008 HengyangChina School of Natural and Applied Sciences Northwestern Polytechnical University710072 Xi’anChina Advanced Technique Department Key Lab of Aeronautics Computing Technique710075 Xi’anChina State Key Laboratory of Millimeter Waves Southeast University210096 NanjingChina

Achieving simultaneous polarization and wavefront control,especially circular polarization with the auxiliary degree of freedom of light and spin angular momentum,is of fundamental importance in many optical *** are typically undesirable in highly integrated photonic circuits and ***,we propose an interference-assisted metasurface-multiplexer(meta-plexer)that counterintuitively exploits constructive and destructive interferences between hybrid meta-atoms and realizes independent spin-selective wavefront *** kaleidoscopic meta-plexers are experimentally demonstrated via two types of single-layer spinwavefront multiplexers that are composed of spatially rotated anisotropic *** type generates a spinselective Bessel-beam wavefront for spin-down light and a low scattering cross-section for stealth for spin-up *** other type demonstrates versatile control of the vortex wavefront,which is also characterized by the orbital angular momentum of light,with frequency-switchable numbers of beams under linearly polarized wave *** findings offer a distinct interference-assisted concept for realizing advanced multifunctional photonics with arbitrary and independent spin-wavefront features.A variety of applications can be readily anticipated in optical diodes,isolators,and spin-Hall meta-devices without cascading bulky optical elements.

关键词： arbitrary momentum versatile

来源：评论

学校读者我要写书评

暂无评论

TOP: Towards Better Toxicity Prediction by Deep Molecular Representation Learning

TOP: Towards Better Toxicity Prediction by Deep Molecular Re...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Yuzhong Peng Ziqiao Zhang Qizhi Jiang Jihong Guan Shuigeng Zhou Key Lab of Scientific Computing Intelligent Information Processing in Universities of Guangxi Nanning Normal University Nanning China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China Tongji University Shanghai China

At the early stages of the drug discovery, molecule toxicity prediction is crucial to excluding drug candidates that are likely to fail in clinical trials. In this paper, we presented a novel molecular representation method and developed a corresponding deep learning-based framework called TOP (the abbreviation of TOxicity Prediction). TOP integrated a serial special data processing methods, a bidirectional gated recurrent unit-based RNN (BiGRU) and a fully connected neural network for end-to-end molecular representation learning and chemical toxicity prediction. TOP can automatically learn a mixed molecular representation from not only SMILES contextual information that describes the molecule structure, but also physiochemical properties. Therefore, TOP can overcome the drawbacks of existing methods that use either of them, thus greatly promotes toxicity prediction. We conducted extensive experiments over 14 classic toxicity prediction tasks on three different benchmark datasets, including balanced and imbalanced ones. The results show that, with the help of the novel molecular representation method, TOP significantly outperforms not only three baseline machine learning methods, but also five state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Click-iG: Simultaneous Enrichment and Profiling of Intact N-linked, O-GalNAc, and O-GlcNAcylated Glycopeptides

引用

Angewandte Chemie 2023年第36期135卷

作者： Dr. Jialin Liu Dr. Bo Cheng Dr. Xinqi Fan Xinyue Zhou Jiankun Wang Dr. Wen Zhou Hengyu Li Dr. Wenfeng Zeng Prof. Pengyuan Yang Prof. Xing Chen College of Chemistry and Molecular Engineering Beijing National Laboratory for Molecular Sciences Peking-Tsinghua Center for Life Sciences Synthetic and Functional Biomolecules Center and Key Laboratory of Bioorganic Chemistry and Molecular Engineering of Ministry of Education Peking University Beijing 100871 China Institute of Biomedical Sciences and Department of Chemistry Fudan University Shanghai 200433 China Key Lab of Intelligent Information Processing of Chinese Academy of Sciences (CAS) and Institute of Computing Technology CAS Beijing 100190 China Deseased

Proteins are ubiquitously modified with glycans of varied chemical structures through distinct glycosidic linkages, making the landscape of protein glycosylation challenging to map. Profiling of intact glycopeptides with mass spectrometry (MS) has recently emerged as a powerful tool for revealing matched information of the glycosylation sites and attached glycans (i.e., intact glycosites), but is largely limited to individual glycosylation types. Herein, we describe Click-iG, which integrates metabolic labeling of glycans with clickable unnatural sugars, an optimized MS method, and a tailored version of pGlyco3 software to enable simultaneous enrichment and profiling of three types of intact glycopeptides: N-linked, mucin-type O-linked, and O-GlcNAcylated glycopeptides. We demonstrate the utility of Click-iG by the identification of thousands of intact glycosites in cell lines and living mice. From the mouse lung, heart, and spleen, a total of 2053 intact N-glycosites, 262 intact O-GalNAc glycosites, and 1947 O-GlcNAcylation sites were identified. Click-iG-enabled comprehensive coverage of the protein glycosylation landscape lays the foundation for interrogating crosstalk between different glycosylation pathways.

关键词： Glycoproteomics Glycosylation Intact Glycosites Metabolic labeling Unnatural Glycans

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：