检索结果-内蒙古大学图书馆

Unsupervised neural machine translation with SMT as posterior regularization

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ren, Shuo Zhang, Zhirui Liu, Shujie Zhou, Ming Ma, Shuai SKLSDE Lab Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing China University of Science and Technology of China Hefei China Microsoft Research Asia

Without real bilingual corpus available, unsupervised Neural Machine Translation (NMT) typically requires pseudo parallel data generated with the back-translation method for the model training. However, due to weak supervision, the pseudo data inevitably contain noises and errors that will be accumulated and reinforced in the subsequent training process, leading to bad translation performance. To address this issue, we introduce phrase based Statistic Machine Translation (SMT) models which are robust to noisy data, as posterior regularizations to guide the training of unsupervised NMT models in the iterative back-translation process. Our method starts from SMT models built with pre-trained language models and word-level translation tables inferred from cross-lingual embeddings. Then SMT and NMT models are optimized jointly and boost each other incrementally in a unified EM framework. In this way, (1) the negative effect caused by errors in the iterative back-translation process can be alleviated timely by SMT filtering noises from its phrase tables;meanwhile, (2) NMT can compensate for the deficiency of fluency inherent in SMT. Experiments conducted on en-fr and en-de translation tasks show that our method outperforms the strong baseline and achieves new state-of-the-art unsupervised machine translation performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Neural machine translation

Corrigendum to “Understanding the urban mobility community by taxi travel trajectory” [Commun. Nonlinear Sci. Numer. Simul. 101(2021) 105863/6]

学校读者我要写书评

暂无评论

Communications in Nonlinear science and Numerical Simulation 2022年 104卷

作者： Wei-Peng Nie Zhi-Dan Zhao Shi-Min Cai Tao Zhou Complex Lab School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu 610054 China Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Chengdu 610054 China Big Data Research Center University of Electronic Science and Technology of China Chengdu 610054 China Complexity Computation Laboratory Department of Computer Science School of Engineering Shantou University Shantou 515063 China Key Laboratory of Intelligent Manufacturing Technology (Ministry of Education) Shantou University Shantou 515063 China

GIscience in the Era of Artificial Intelligence: A Research Agenda Towards Autonomous GIS

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Li, Zhenlong Ning, Huan Gao, Song Janowicz, Krzysztof Li, Wenwen Arundel, Samantha T. Yang, Chaowei Bhaduri, Budhendra Wang, Shaowen Zhu, A. Xing Gahegan, Mark Shekhar, Shashi Ye, Xinyue McKenzie, Grant Cervone, Guido Hodgson, Michael E. Geoinformation and Big Data Research Lab Department of Geography The Pennsylvania State University University ParkPA United States Department of Geography University of Wisconsin – Madison WI United States STKO Lab Department of Geography and Regional Research University of Vienna Vienna Austria Spatial Analysis Research Center School of Geographical Sciences and Urban Planning Arizona State University AZ United States Center of Excellence for Geospatial Information Science U.S. Geological Survey VA United States NSF Spatiotemporal Innovation Center Department of Geography & Geoinformation Science George Mason University VA United States TN United States CyberGIS Center for Advanced Digital and Spatial Studies Department of Geography and Geographic Information Science University of Illinois Urbana-Champaign IL United States School of Computer Science University of Auckland New Zealand Department of Computer Science & Engineering University of Minnesota MN United States Department of Landscape Architecture & Urban Planning Center for Geospatial Sciences Applications & Technology Texas A&M University TX United States Platial Analysis Lab Department of Geography McGill University Quebec Canada Institute for Computational and Data Sciences Department of Geography The Pennsylvania State University University ParkPA United States Department of Geography University of South Carolina SC United States

The advent of generative AI exemplified by large language models (LLMs) opens new ways to represent and compute geographic information and transcends the process of geographic knowledge production, driving geographic information systems (GIS) towards autonomous GIS. Leveraging LLMs as the decision core, autonomous GIS can independently generate and execute geoprocessing workflows to perform spatial analysis. In this vision paper, we further elaborate on the concept of autonomous GIS and present a conceptual framework that defines its five autonomous goals, five autonomous levels, five core functions, and three operational scales. We demonstrate how autonomous GIS could perform geospatial data retrieval, spatial analysis, and map making with four proof-of-concept GIS agents. We conclude by identifying critical challenges and future research directions, including fine-tuning and self-growing decision-cores, autonomous modeling, and examining the societal and practical implications of autonomous GIS. By establishing the groundwork for a paradigm shift in GIscience, this paper envisions a future where GIS moves beyond traditional workflows to autonomously reason, derive, innovate, and advance geospatial solutions to pressing global challenges. Meanwhile, as we design and deploy increasingly intelligent geospatial systems, we carry a responsibility to ensure they are developed in socially responsible ways, serve the public good, and support the continued value of human geographic insight in an AI-augmented future. © 2025, CC BY.

关键词： Image retrieval

Distraction-aware feature learning for human attribute recognition via coarse-to-fine attention mechanism

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Wu, Mingda Huang, Di Guo, Yuanfang Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China IRIP Lab School of Computer Science and Engineering Beihang University Beijing China

Recently, Human Attribute Recognition (HAR) has become a hot topic due to its scientific challenges and application potentials, where localizing attributes is a crucial stage but not well handled. In this paper, we propose a novel deep learning approach to HAR, namely Distraction-aware HAR (Da-HAR). It enhances deep CNN feature learning by improving attribute localization through a coarse-to-fine attention mechanism. At the coarse step, a self-mask block is built to roughly discriminate and reduce distractions, while at the fine step, a masked attention branch is applied to further eliminate irrelevant regions. Thanks to this mechanism, feature learning is more accurate, especially when heavy occlusions and complex backgrounds exist. Extensive experiments are conducted on the WIDER-Attribute and RAP databases, and state-of-the-art results are achieved, demonstrating the effectiveness of the proposed approach. Copyright © 2019, The Authors. All rights reserved.

关键词： Deep learning

Unsupervised image super-resolution with an indirect supervised path

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Han, Zhen Dai, Enyan Jia1y, Xu Ren, Xiaoying Chen, Shuaijun Xu, Chunjing Liu, Jianzhuang Tian, Qi Huawei Noah's Ark Lab Institute of Statistics and Big Data Renmin University of China College of Information Science and Technology Pennsylvania State University School of Computer Science and Technology University of Science and Technology of China

The task of single image super-resolution (SISR) aims at reconstructing a high-resolution (HR) image from a low-resolution (LR) image. Although significant progress has been made by deep learning models, they are trained on synthetic paired data in a supervised way and do not perform well on real data. There are several attempts that directly apply unsupervised image translation models to address such a problem. However, unsupervised low-level vision problem poses more challenge on the accuracy of translation. In this work, we propose a novel framework which is composed of two stages: 1) unsupervised image translation between real LR images and synthetic LR images;2) supervised super-resolution from approximated real LR images to HR images. It takes the synthetic LR images as a bridge and creates an indirect supervised path from real LR images to HR images. Any existed deep learning based image super-resolution model can be integrated into the second stage of the proposed framework for further improvement. In addition it shows great flexibility in balancing between distortion and perceptual quality under unsupervised setting. The proposed method is evaluated on both NTIRE 2017 and 2018 challenge datasets and achieves favorable performance against supervised methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Optical resolving power

A simple image encryption algorithm based on logistic map 5th

学校读者我要写书评

暂无评论

A simple image encryption algorithm based on logistic map

5th Euro-China Conference on Intelligent data Analysis and Applications, ECC 2018

作者： Wu, Tsu-Yang Wang, King-Hang Chen, Chien-Ming Wu, Jimmy Ming-Tai Pan, Jeng-Shyang Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou350118 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong Shenzhen518055 China College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9783030037659

Based on the better properties of chaotic maps, the studies of chaotic-based image encryption have received much attentions by researchers in recent years. In this paper, an image encryption algorithm based on logistic map with substitution approach is proposed. Meanwhile, we make the line chart, histogram, and pixel loss analysis to show the performance of our algorithm. © Springer Nature Switzerland AG 2019.

关键词： Cryptography

Hierarchical semantic approximate multi-keyword ranked search over encrypted data 2nd

学校读者我要写书评

暂无评论

Hierarchical semantic approximate multi-keyword ranked searc...

2nd International Conference on Smart Vehicular Technology, Transportation, Communication and Applications, VTCA 2018

作者： Chen, Chien-Ming Zhang, Wenhao Wu, Tsu-Yang Wang, King-Hang Wu, Jimmy Ming-Tai Pan, Jeng-Shyang Shenzhen518055 China Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou350118 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9783030045845

With the rapid development of Cloud Computing, how to improve users search experience over encrypted data just like plaintext search has become a challenging task. In this paper, we propose a hierarchical semantic approximate multi-keyword ranked search (HSAMS) scheme over encrypted data. Performance analysis is demonstrated that our proposed scheme is efficient and effective while supporting semantic approximate match. © Springer Nature Switzerland AG 2019.

关键词： Semantics

A Public Auditing Scheme with data Recovery 12th

学校读者我要写书评

暂无评论

A Public Auditing Scheme with Data Recovery

12th International Conference on Genetic and Evolutionary Computing, ICGEC 2018

作者： Wu, Tsu-Yang Chen, Chien-Ming Wang, King-Hang Wu, Jimmy Ming-Tai Pan, Jeng-Shyang Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China National Demonstration Center for Experimental Electronic Information and Electrical Technology Education Fujian University of Technology Fuzhou350118 China Shenzhen518055 China Department of Computer Science and Engineering Hong Kong University of Science and Technology Clear Water Bay Hong Kong College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China

ISBN: (纸本)9789811358401

In order to solve the integrity verification of outsourced file in cloud, we based on the concept of regenerating code (RC) to propose a new public auditing scheme with data recovery in this paper. With the advantage of RC, our scheme provides a (k,n) recovery functionality, i.e., only encoded data blocks from any k cloud servers, user can recover the original data files, where n denotes the total number of cloud servers and k ≤ n. © 2019, Springer Nature Singapore Pte Ltd.

关键词： Recovery

Security analysis of a public key authenticated encryption with keyword search scheme 14th

学校读者我要写书评

暂无评论

Security analysis of a public key authenticated encryption w...

14th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2018

In order to solve the security problem that off-line keyword guessing attacks existed in PEKS or dPEKS scheme, Huang and Li introduced a new security model called PAEKS. In this paper, we show that their scheme didn’... 详细信息

ISBN: (纸本)9783030037444

关键词： Search engines