检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Chao, Xianjin Bin, Yanrui Chu, Wenqing Cao, Xuan Ge, Yanhao Wang, Chengjie Li, Jilin Huang, Feiyue Leung, Howard City University of Hong Kong Hong Kong Hong Kong Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Tencent Youtu Lab Shanghai China

Human motion prediction aims to predict future 3D skeletal sequences by giving a limited human motion as inputs. Two popular methods, recurrent neural networks and feed-forward deep networks, are able to predict rough motion trend, but motion details such as limb movement may be lost. To predict more accurate future human motion, we propose an Adversarial Refinement Network (ARNet) following a simple yet effective coarse-to-fine mechanism with novel adversarial error augmentation. Specifically, we take both the historical motion sequences and coarse prediction as input of our cascaded refinement network to predict refined human motion and strengthen the refinement network with adversarial error augmentation. During training, we deliberately introduce the error distribution by learning through the adversarial mechanism among different subjects. In testing, our cascaded refinement network alleviates the prediction error from the coarse predictor resulting in a finer prediction robustly. This adversarial error augmentation provides rich error cases as input to our refinement network, leading to better generalization performance on the testing dataset. We conduct extensive experiments on three standard benchmark datasets and show that our proposed ARNet outperforms other state-of-the-art methods, especially on challenging aperiodic actions in both short-term and long-term predictions. © 2020, CC-BY.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Bilingual Word Embedding with Sentence Combination CNN for 1-to-N Sentence Alignment 20

Bilingual Word Embedding with Sentence Combination CNN for 1...

引用

Proceedings of the 4th International Conference on Natural Language processing and information Retrieval

作者： Xinyuan Ren Xiangling Fu Xuesi Zhou Chunsheng Liu Songfeng Gao Lei Peng School of Software Engineering Beijing University of Posts and Telecommunications Beijing China and Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education Beijing University of Posts and Telecommunications Beijing China Department of Electronic Engineering Tsinghua University Hai Dian Beijing China and Multimedia Signal and Intelligent Information Processing Lab Tsinghua University Hai Dian Beijing China BUPT and Huarong Joint lab of Smart Finance Beijing P. R. China and HuaRong RongTong (Beijing) Technology Co. Ltd Beijing P. R. China

ISBN: (纸本)9781450377607

Sentence alignment, as one of the most active and fundamental tasks in the field of natural language processing (NLP), is usually realized in two categories of methods. One is traditional methods which are firstly proposed, the other, which are adopted later, is based on the Neural Network method. Presently, under the limitation that the existing mainstream data corpora are mostly in the form of 1-to-1, the alignment models with relatively good performance mainly apply to the cases of 1-to-1 sentence alignment. However, under the circumstance that a sentence contains too much information, 1-to-N sentence alignment can actually have a better effect on sentence translation tasks, compared with the 1-to-1 form, since it is more flexible and can reduce the complexity of the original sentence. As a result, we attempt to exploit neural networks with relatively good performance in the cases of 1-to-1 to fit in the cases of 1-to-N. In this paper, a novel 1-N Bilingual word Embedding with Sentence Combination CNN Improved Framework (1-NBESCC) is proposed in order to align 1-to-N sentences more precisely. Experiments show that our proposed model performs as good as the traditional methods such as BLEUALIGN in 1-to-1 situation, but much better in 1-to-N situation.

关键词： Convolutional Neural Network

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Diabetic Retinopathy Segmentation System from Diagnosis to Therapeutic Decision-Making: A Real-World Multi-Center Study

SSRN

引用

SSRN 2025年

作者： Dong, Li Deng, Zhuo Li, He-Yan Gao, Wei-Hao Wang, Hai-Bo Shao, Lei Yan, Yan-Ni Yang, Jing-Yan Wang, Shan-Shan Yin, Shi-Yi Shi, Xu-Han Gong, Zheng Yu, Wei-Hong Chen, You-Xin Zhao, Jing Dai, Hong Zhao, Xin-Yu Zhang, Guo-Ming Jin, Kai Ye, Juan Yuan, Hui-Ping Li, Fang Zhang, Li-Gang Xiong, Jian-Hao Zhang, Da-Lei Jonas, Jost B. Ma, Lan Wei, Wen-Bin Beijing Tongren Eye Center Beijing key Laboratory of Intraocular Tumor Diagnosis and Treatment Beijing Ophthalmology＆Visual Sciences Key Lab Medical Artificial Intelligence Research and Verification Key Laboratory The Ministry of Industry and Information Technology Beijing Key Laboratory of Intelligent Diagnosis Treatment and Prevention of Blinding Eye Diseases Beijing Tongren Hospital Capital Medical University Beijing China Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China Department of Ophthalmology The Third People’s Hospital of Dalian China Key Laboratory of Ocular Fundus Diseases Peking Union Medical College Hospital Chinese Academy of Medical Sciences Beijing China Department of Ophthalmology Peking Union Medical College Hospital Chinese Academy of Medical Sciences Peking Union Medical College Beijing100730 China Beijing Key Laboratory of Fundus Diseases Intelligent Diagnosis & Drug/Device Development and Translation Beijing100730 China Key Laboratory of Ocular Fundus Diseases Chinese Academy of Medical Sciences Beijing100730 China State Key Laboratory of Complex Severe and Rare Diseases China Beijing Hospital Beijing China Shenzhen Eye Hospital Shenzhen Eye Medical Center Southern Medical University Shenzhen518040 China Eye Center The Second Affiliated Hospital of Zhejiang University Hangzhou China The Second Affiliated Hospital of Harbin Medical University Harbin China iKang Guobin Healthcare Group Co. Ltd China Beijing Airdoc Technology Co. Ltd Beijing China Rothschild Foundation Hospital Institut Français de Myopie Paris France Singapore Eye Research Institute Singapore National Eye Center Singapore Privatpraxis Prof Jonas und Dr. Panda-Jonas Heidelberg Germany Beijing Tsinghua Changgung Hospital Tsinghua Medicine Tsinghua University Beijing China L V Prasad Eye Institute Telangana Hyderabad India Dalian No.3 People's Hospital China Department of Ophthalmology

Background: Diabetic retinopathy (DR) is a common complication of diabetes with the risk of vision impairment if not diagnosed and treated adequately. This study aimed to develop an artificial intelligence (AI)-based early diagnosis system for DR, called Diabetic Retinopathy Segmentation System (DRSS).Methods: DRSS, based on a UNet++ model, was trained and developed using four public datasets and a dataset from several hospitals to segment DR fundus features, i.e., hard exudates, soft exudates, retinal hemorrhages, and retinal microaneurysms on fundus images. We conducted a multi-center prospective validation, an AI versus ophthalmologist efficiency comparison, and a clinical application (follow-up management) to explore robustness and potential of the DRSS in real-world ***: The DRSS achieved mIoU scores of 0.624 for microaneurysms (MA), 0.797 for soft exudates (SE), 0.782 for hard exudates (EX), and 0.719 for retinal hemorrhage (HE), with mDice scores of 0.699 (MA), 0.862 (SE), 0.860 (EX), and 0.805 (HE), respectively. External validation on 1800 fundus images showed a robust performance, with average IoU and Dice scores ranging from 0.845–0.868 and 0.876–0.903, respectively. In AI versus human comparisons, AI-assisted clinicians achieved higher accuracy, especially for MAs, while AI excelled in segmenting larger lesions like EXs and SEs. AI-assisted segmentation took 61 seconds per image, significantly faster than manual segmentation but slower than standalone AI, which saved 94.5% time compared to ***: The DRSS demonstrated robust performance in segmenting diabetic retinopathy lesions, achieving high mIoU and mDice scores across multiple datasets, with particularly strong results for larger lesions like exudates. The model's ability to quantify treatment response highlights its potential for optimizing anti-VEGF therapy management in clinical practice. © 2025, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Improving Cross-database Face Presentation Attack Detection via Adversarial Domain Adaptation

Improving Cross-database Face Presentation Attack Detection ...

引用

IAPR International Conference on Biometrics (ICB)

作者： Guoqing Wang Hu Han Shiguang Shan Xilin Chen Key Laboratory of Intelligent Information Processing of Chinese Academy of Sciences (CAS) Institute of Computing Technology CAS Beijing China

Face recognition (FR) is being widely used in many applications from access control to smartphone unlock. As a result, face presentation attack detection (PAD) has drawn increasing attentions to secure the FR systems. Traditional approaches for PAD mainly assume that training and testing scenarios are similar in imaging conditions (illumination, scene, camera sensor, etc.), and thus may lack good generalization capability into new application scenarios. In this work, we propose an end-to-end learning approach to improve PAD generalization capability by utilizing prior knowledge from source domain via adversarial domain adaptation. We first build a source domain PAD model optimized with triplet loss. Subsequently, we perform adversarial domain adaptation w.r.t. the target domain to learn a shared embedding space by both the source and target domain models, in which the discriminator cannot reliably predict whether a sample is from the source or target domain. Finally, PAD in the target domain is performed with k-nearest neighbors (k-NN) classifier in the embedding space. The proposed approach shows promising generalization capability in a number of public-domain face PAD databases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploiting Multi-domain Visual information for Fake News Detection

Exploiting Multi-domain Visual Information for Fake News Det...

引用

IEEE International Conference on Data Mining (ICDM)

作者： Peng Qi Juan Cao Tianyun Yang Junbo Guo Jintao Li Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS University of Chinese Academy of Sciences Beijing China

The increasing popularity of social media promotes the proliferation of fake news. With the development of multimedia technology, fake news attempts to utilize multimedia content with images or videos to attract and mislead readers for rapid dissemination, which makes visual content an important part of fake news. Fake-news images, images attached to fake news posts, include not only fake images that are maliciously tampered but also real images that are wrongly used to represent irrelevant events. Hence, how to fully exploit the inherent characteristics of fake-news images is an important but challenging problem for fake news detection. In the real world, fake-news images may have significantly different characteristics from real-news images at both physical and semantic levels, which can be clearly reflected in the frequency and pixel domain, respectively. Therefore, we propose a novel framework Multi-domain Visual Neural Network (MVNN) to fuse the visual information of frequency and pixel domains for detecting fake news. Specifically, we design a CNN-based network to automatically capture the complex patterns of fake-news images in the frequency domain; and utilize a multi-branch CNN-RNN model to extract visual features from different semantic levels in the pixel domain. An attention mechanism is utilized to fuse the feature representations of frequency and pixel domains dynamically. Extensive experiments conducted on a real world dataset demonstrate that MVNN outperforms existing methods with at least 9.2% in accuracy, and can help improve the performance of multi-modal fake news detection by over 5.2%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multifractal temporally weighted detrended partial cross-correlation analysis to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors

arXiv

引用

arXiv 2020年

作者： Li, Bao-Gen Ling, Dian-Yi Yu, Zu-Guo Key Laboratory of Intelligent Computing and Information Processing Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering Xiangtan University Xiangtan Hunan411105 China School of Electrical Engineering and Computer Science Queensland University of Technology GPO Box 2434 BrisbaneQ4001 Australia

When common factors strongly influence two cross-correlated time series recorded in complex natural and social systems, the results will be biased if we use multifractal detrended cross-correlation analysis (MF-DXA) without considering these common factors. Based on multifractal temporally weighted detrended cross-correlation analysis (MF-TWXDFA) proposed by our group and multifractal partial cross-correlation analysis (MF-DPXA) proposed by Qian et al., we propose a new method-multifractal temporally weighted detrended partial cross-correlation analysis (MF-TWDPCCA) to quantify intrinsic power-law cross-correlation of two non-stationary time series affected by common external factors in this paper. We use MF-TWDPCCA to characterize the intrinsic cross-correlations between the two simultaneously recorded time series by removing the effects of other potential time series. To test the performance of MF-TWDPCCA, we apply it, MF-TWXDFA and MF-DPXA on simulated series. Numerical tests on artificially simulated series demonstrate that MF-TWDPCCA can accurately detect the intrinsic cross-correlations for two simultaneously recorded series. To further show the utility of MF-TWDPCCA, we apply it on time series from stock markets and find that there exists significantly multifractal power-law cross-correlation between stock returns. A new partial cross-correlation coefficient is defined to quantify the level of intrinsic cross-correlation between two time series. Copyright © 2020, The Authors. All rights reserved.

关键词： Fractals

来源：评论

学校读者我要写书评

暂无评论

Efficient differentiated storage architecture for large-scale flow tables in openflow networks 21

Efficient differentiated storage architecture for large-scal...

引用

21st IEEE International Conference on High Performance Computing and Communications, 17th IEEE International Conference on Smart City and 5th IEEE International Conference on Data Science and Systems, HPCC/SmartCity/DSS 2019

作者： Xiong, Bing Wu, Rengeng Liao, Zhuofan Wang, Jin School of Computer AND Communication Engineering Changsha University of Science AND Technology Changsha410114 China Department of Computer and Information Sciences Temple University Philadelphia19122 United States Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science AND Technology Changsha China

ISBN: (纸本)9781728120584

As a novel network paradigm, Software Defined Networking (SDN) decouples control logic functions from data forwarding devices, and introduces a separate control plane to manipulate underlying switches via southbound interfaces like OpenFlow. However, it leads to large-scale flow tables and poses serious challenges on their storage resources and lookup performance in OpenFlow switches. This paper is thus motivated to propose an efficient differentiated storage architecture for large-scale flow tables in OpenFlow networks. Firstly, we investigate into the impact of wildcards in match fields on packet-in-batch property within a flow based on network traffic locality. Then, packet flows are dynamically distinguished into active ones and idle ones in terms of their short-term states. Subsequently, we store the match fields of active flows and idle flows respectively in TCAM and SRAM, and the content fields of both types of flows in DRAM, to effectively relieve the insufficiency of TCAM capacity. Finally, we evaluate the performance of our proposed flow table storage architecture with real network traffic traces by experiments. The experimental results indicate that our proposed storage architecture obviously outperforms the traditional one applying the elephant/mice flow differentiation method in terms of TCAM hit rates and average flow table access time. © 2019 IEEE.

关键词： Software defined networking

来源：评论

学校读者我要写书评

暂无评论

Multi-view Based Pose Alignment Method for Person Re-identification

Multi-view Based Pose Alignment Method for Person Re-identif...

引用

2019中国智能自动化大会(CIAC 2019)

作者： Yulei Zhang Qingjie Zhao You Li Beijing Key Lab of Intelligent Information Technology School of Computer Science Beijing Institute of Technology

This paper proposes a Multi-View based Pose Alignment（MVPA）method for person re-identification（re-id）.Most recent methods solve re-id as a matching process based on single ***,when poses vary or viewpoints change,the performance seriously *** paper aims to learn a representation insensitive to view and ***,we establish a set of Multi-view based Person Pose Templates（MPPT） and propose a Pose-Guided Person image Generation（iPG） model to synthesize multi-view and uniformpose based *** representation learned from multi-view images can significantly enhances the accuracy of *** evaluate our method on two popular datasets,i.e.,Market-1501 and *** results show that our framework promotes the performance of re-id a lot and surpass other methods.

关键词： Person re-identification Pose Alignment Generative Adversarial Networks

来源：评论

学校读者我要写书评

暂无评论

Box-particle Bernoulli Filter for Multipath Target Tracking in OTHR

Box-particle Bernoulli Filter for Multipath Target Tracking ...

引用

International Conference on information Systems and Computer Aided Education (ICISCAE)

作者： Yong Qin Jiangxi Province Key Laboratory of Water Information Cooperative Sensing and Intelligent Processing Nanchang Institute of Technology Nanchang China

ISBN: (数字)9781728130668

ISBN: (纸本)9781728130675

This paper proposes a novel box-particle multipath Bernoulli filter (BP-MPBF) for the problem of single target tracking in Over-the-horizon radar (OTHR) under the clutter environment. The proposed algorithm combines the multipath Bernoulli filter (MPBF) with interval analysis to solve the problems of nonlinear measurement models and high computational complexity. First, the OTHR measurement model is established based on interval analysis, and then the box-particle filter is used to derive the BP-MPBF based on the original MPBF. Eventually, simulation results are provided to demonstrate the effectiveness of the BP-MPBF.

关键词： Filtering algorithms Target tracking Radio frequency Computational modeling information filters Clutter

来源：评论

学校读者我要写书评

暂无评论

Adversarial Attacks and Defenses in Physiological Computing: A Systematic Review

arXiv

引用

arXiv 2021年

作者： Wu, Dongrui Xu, Jiaxin Fang, Weili Zhang, Yi Yang, Liuqing Xu, Xiaodong Luo, Hanbin Yu, Xiang The Ministry of Education Key Laboratory of Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China Zhejiang Lab Hangzhou311121 China The School of Civil and Hydraulic Engineering Huazhong University of Science and Technology Wuhan430074 China The College of Public Administration Huazhong University of Science and Technology Wuhan430074 China The University of Michigan Ann ArborMI48109 United States The School of Management and Sino European Institute for Intellectual Property Huazhong University of Science and Technology Wuhan430074 China

Physiological computing uses human physiological data as system inputs in real time. It includes, or significantly overlaps with, brain-computer interfaces, affective computing, adaptive automation, health informatics, and physiological signal based biometrics. Physiological computing increases the communication bandwidth from the user to the computer, but is also subject to various types of adversarial attacks, in which the attacker deliberately manipulates the training and/or test examples to hijack the machine learning algorithm output, leading to possible user confusion, frustration, injury, or even death. However, the vulnerability of physiological computing systems has not been paid enough attention to, and there does not exist a comprehensive review on adversarial attacks to them. This paper fills this gap, by providing a systematic review on the main research areas of physiological computing, different types of adversarial attacks and their applications to physiological computing, and the corresponding defense strategies. We hope this review will attract more research interests on the vulnerability of physiological computing systems, and more importantly, defense strategies to make them more secure. Copyright © 2021, The Authors. All rights reserved.

关键词： Machine learning

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：