检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Dong, Jianfeng Li, Xirong Xu, Chaoxi Yang, Xun Yang, Gang Wang, Xun Wang, Meng College of Computer and Information Engineering Zhejiang Gongshang University Hangzhou310035 China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China The AI and Media Computing Lab School of Information Renmin University of China Beijing100872 China School of Computing National University of Singapore Singapore37580 Singapore School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China

This paper attacks the challenging problem of video retrieval by text. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described exclusively in the form of a natural-language sentence, with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is crucial. To that end, the two modalities need to be first encoded into real-valued vectors and then projected into a common space. In this paper we achieve this by proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Our novelty is two-fold. First, different from prior art that resorts to a specific single-level encoder, the proposed network performs multi-level encoding that represents the rich content of both modalities in a coarse-to-fine fashion. Second, different from a conventional common space learning algorithm which is either concept based or latent space based, we introduce hybrid space learning which combines the high performance of the latent space and the good interpretability of the concept space. Dual encoding is conceptually simple, practically effective and end-to-end trained with hybrid space learning. Extensive experiments on four challenging video datasets show the viability of the new method. Code is available at https://***/danieljf24/hybrid_space. Copyright © 2020, The Authors. All rights reserved.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Applications of Game Theory in Vehicular Networks: A Survey

arXiv

引用

arXiv 2021年

作者： Sun, Zemin Liu, Yanheng Wang, Jian Li, Guofa Anil, Carie Li, Keqiang Guo, Xinyu Sun, Geng Tian, Daxin Cao, Dongpu College of Computer Science and Technology Jilin University Changchun130012 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Institute of Human Factors and Ergonomics College of Mechatronics and Control Engineering Shenzhen University Guangdong Shenzhen518060 China School of Computer Science and Engineering VIT-AP Andhra Pradesh Amaravati522237 India College of Engineering Nanjing Agricultural University Nanjing210031 China State Key Laboratory of Automotive Safety and Energy Department of Automotive Engineering Tsinghua University Beijing100084 China Beijing Advanced Innovation Center for Big Data and Brain Computing Beijing Key Laboratory for Cooperative Vehicle Infrastructure Systems and Safety Control School of Transportation Science and Engineering Beihang University Beijing100191 China Waterloo Cognitive Autonomous Driving Lab University of Waterloo N2L 3G1 Canada

In the Internet of things (IoT) era, vehicles and other intelligent components in an intelligent transportation system (ITS) are connected, forming vehicular networks (VNs) that provide efficient and safe traffic and ubiquitous access to various applications. However, as the number of nodes in an ITS increases, it is challenging to satisfy a varied and large number of service requests with different quality of service (QoS) and security requirements in highly dynamic VNs. Intelligent nodes in VNs can compete or cooperate for limited network resources to achieve the objective for either an individual or a group. Game theory (GT), a theoretical framework designed for strategic interactions among rational decision makers sharing scarce resources, can be used to model and analyze individual or group behaviors of communicating entities in VNs. This paper primarily surveys the recent developments of GT in solving various challenges of VNs. This survey starts with an introduction to the background of VNs. A review of GT models studied in the VNs is then introduced, including the basic concepts, classifications, and applicable vehicular issues. After discussing the requirements of VNs and the motivation of using GT, a comprehensive literature review on GT applications in dealing with the challenges of current VNs is provided. Furthermore, recent contributions of GT to VNs that are integrated with diverse emerging 5G technologies are surveyed. Finally, the lessons learned are given, and several key research challenges and possible solutions of applying GT in VNs are outlined. Copyright © 2021, The Authors. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

An Effective Framework for Identifying Good XML Feedback Fragments

An Effective Framework for Identifying Good XML Feedback Fra...

引用

12th KIPS International Conference on Ubiquitous Information Technologies and Applications (CUTE) / 9th International Conference on Computer Science and its Applications (CSA)

作者： Zhong, Minjuan Zou, Beiji Wang, Lei Liao, Shumei Xiong, Naixue South Cent Univ Sch Informat Sci & Engn Changsha Hunan Peoples R China Jiangxi Univ Finance & Econ Sch Informat Technol Jiangxi Key Lab Data & Knowledge Engn Nanchang Jiangxi Peoples R China Northeastern State Univ Dept Math & Comp Sci Tahlequah OK USA

ISBN: (纸本)9789811076053;9789811076046

In Pseudo relevance feedback, It is often crucial to identify those good feedback documents from which useful expansion terms can be added to the query. For Extensible Markup Language (XML) data, this paper proposes an approach for identifying good feedback fragments by a complete framework in which two phrases are included. (1) The first phase is about XML search results clustering. We performed a k-medoid clustering algorithm to XML fragments based on an extended latent semantic indexing model. (2) The second phase is a two-stage ranking. Cluster ranking is performed in the first stage to select relevant clusters on the basis of cluster labelling, which is determined by extracted fragment keywords based on a combination of weight and context;fragment ranking is performed during the second stage where multiple features are used to identify high quality fragments from the previously obtained relevant clusters. Experimental results on standard INEX test data show that the proposed approach achieves statistically significant improvements over a strong original query results mechanism, ensuring high quality fragments for feedback.

关键词： XML fragment Clustering search results Two-stage ranking model Pseudo relevance feedback

来源：评论

学校读者我要写书评

暂无评论

Binary neural networks: A survey

arXiv

引用

arXiv 2020年

作者： Qin, Haotong Gong, Ruihao Liu, Xianglong Bai, Xiao Song, Jingkuan Sebe, Nicu State Key Lab of Software Development Environment Beihang University Beijing China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing China Center for Future Media School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Information Engineering and Computer Science University of Trento Trento Italy School of Computer Science and Engineering Beijing Advanced Innovation Center for Big Data and Brain Computing Jiangxi Research Institute Beihang University Beijing China

The binary neural network, largely saving the storage and computation, serves as a promising technique for deploying deep models on resource-limited devices. However, the binarization inevitably causes severe information loss, and even worse, its discontinuity brings difficulty to the optimization of the deep network. To address these issues, a variety of algorithms have been proposed, and achieved satisfying progress in recent years. In this paper, we present a comprehensive survey of these algorithms, mainly categorized into the native solutions directly conducting binarization, and the optimized ones using techniques like minimizing the quantization error, improving the network loss function, and reducing the gradient error. We also investigate other practical aspects of binary neural networks such as the hardware-friendly design and the training tricks. Then, we give the evaluation and discussions on different tasks, including image classification, object detection and semantic segmentation. Finally, the challenges that may be faced in future research are prospected. Copyright © 2020, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Dual Encoding for Zero-Example Video Retrieval

Dual Encoding for Zero-Example Video Retrieval

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition

作者： Jianfeng Dong Xirong Li Chaoxi Xu Shouling Ji Yuan He Gang Yang Xun Wang College of Computer and Information Engineering Zhejiang Gongshang University Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AI & Media Computing Lab School of Information Renmin University of China College of Computer Science Zhejiang University Alibaba Group

ISBN: (纸本)9781728132945

This paper attacks the challenging problem of zero-example video retrieval. In such a retrieval paradigm, an end user searches for unlabeled videos by ad-hoc queries described in natural language text with no visual example provided. Given videos as sequences of frames and queries as sequences of words, an effective sequence-to-sequence cross-modal matching is required. The majority of existing methods are concept based, extracting relevant concepts from queries and videos and accordingly establishing associations between the two modalities. In contrast, this paper takes a concept-free approach, proposing a dual deep encoding network that encodes videos and queries into powerful dense representations of their own. Dual encoding is conceptually simple, practically effective and end-to-end. As experiments on three benchmarks, i.e. MSR-VTT, TRECVID 2016 and 2017 Ad-hoc Video Search show, the proposed solution establishes a new state-of-the-art for zero-example video retrieval.

关键词： Videotapes video retrieval End users end-to-end Dual coding

来源：评论

学校读者我要写书评

暂无评论

A Decentralized Collaborative Approach to Online Edge User Allocation in Edge Computing Environments

A Decentralized Collaborative Approach to Online Edge User A...

引用

IEEE International Conference on Web Services (ICWS)

作者： Qinglan Peng Yunni Xia Yan Wang Chunrong Wu Wanbo Zheng Xin Luo Shanchen Panz Yong Ma Chunxu Jiang Software Theory and Technology Chongqing Key Lab Chongqing University Chongqing China Macquarie University Sydney NSW Australia Data Science Research Center Kunming University of Science and Technology Kunming China Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing China School of Computer and Communication Engineering China University of Petroleum Qingdao China School of Computer and Information Engineering Jiangxi Normal University Nanchang China Chongqing Key Laboratory of Smart Electronics Reliability Technology Chongqing China

ISBN: (数字)9781728187860

ISBN: (纸本)9781728187877

Edge computing is a promising paradigm that can boost the performance of novel mobile applications and energize the real-time governance of Internet-of-Things (IoT) big data. In edge computing, mobile application vendors are allowed to employ edge resources to speed up end-users' applications in an elastic and on-demand manner. However, due to the complex geographical distribution of edge servers and users, how to decide the most appropriate destination edge server to hire and how to decide the corresponding user-server allocation plan with as-low-as-possible monetary cost are the key problems for application vendors. Instead of assuming a simultaneous-batch-arrival pattern of incoming users and considering static optimization of the Edge User Allocation (EUA) problem by most existing studies, in this paper, we consider an online EUA problem where users' arrival and departure follow a general pattern. We take the long-term edge user allocation rate and edge server leasing cost as scheduling targets and propose a decentralized collaborative and fuzzy-control-based approach to yielding real-time user-edge-server allocation schedules. In this approach, edge users are allowed to independently make their own allocation decision only based on local information (i.e., the status of nearby edge servers). Experiments on real-world edge datasets demonstrate our approach outperforms state-of-the-art approaches in terms of long-term allocation rate and system cost.

关键词： Web services Collaboration Real-time systems Mobile applications Resource management Servers Edge computing

来源：评论

学校读者我要写书评

暂无评论

Trajectory simplification: An experimental study and quality analysis 44th

Trajectory simplification: An experimental study and quality...

引用

44th International Conference on Very Large data Bases, VLDB 2018

作者： Zhang, Dongxiang Ding, Mengting Yang, Dingy Liu, Yi Fan, Ju Shen, Heng Tao Center for Future Media School of Computer Science and Engineering UESTC China School of Electronics and Information Shanghai Dian Ji University China The Key Lab of Data Engineering and Knowledge Engineering Renmin University of China China

The ubiquitousness of GPS sensors in smart-phones, vehicles and wearable devices has enabled the collection of massive volumes of trajectory data from tracing moving objects. Consequently, an unprecedented scale of timestamped GPS data has been generated and posed an urgent demand for an effective storage mechanism for trajectory databases. The mainstream compression technique is called trajectory simplification, that finds a subsequence to approximate the original trajectory and attempts to minimize the information loss under a distance measure. Even though various simplification algorithms have been proposed in the past decades, there still lacks a thorough comparison to cover all the state-of-the-art algorithms and evaluate their quality using datasets in diversified motion patterns. Hence, it still remains a challenge for GPS data collectors to determine a proper algorithm in a concrete application. In addition, almost the entire line of previous methods uses error-based metrics to evaluate the compression quality, while ignoring their usability in supporting spatio-temporal queries on top of the reduced database. To bridge these gaps, we conduct so far the most comprehensive evaluation on trajectory simplification techniques. We compare the performance of 25 algorithms in total using five real datasets in different motion patterns. According to the experimental findings, we present useful guidance for the selection or development of effective trajectory simplification algorithms. © VLDB Endowment 21508097/18/05

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

Mining Dual Emotion for Fake News Detection

arXiv

引用

arXiv 2019年

作者： Zhang, Xueyao Cao, Juan Li, Xirong Sheng, Qiang Zhong, Lei Shu, Kai Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences China Key Lab of Data Engineering and Knowledge Engineering Renmin University of China Beijing China Illinois Institute of Technology ChicagoIL United States

Emotion plays an important role in detecting fake news online. When leveraging emotional signals, the existing methods focus on exploiting the emotions of news contents that conveyed by the publishers (i.e., publisher emotion). However, fake news often evokes high-arousal or activating emotions of people, so the emotions of news comments aroused in the crowd (i.e., social emotion) should not be ignored. Furthermore, it remains to be explored whether there exists a relationship between publisher emotion and social emotion (i.e., dual emotion), and how the dual emotion appears in fake news. In this paper, we verify that dual emotion is distinctive between fake and real news and propose Dual Emotion Features to represent dual emotion and the relationship between them for fake news detection. Further, we exhibit that our proposed features can be easily plugged into existing fake news detectors as an enhancement. Extensive experiments on three real-world datasets (one in English and the others in Chinese) show that our proposed feature set: 1) outperforms the state-of-the-art task-related emotional features;2) can be well compatible with existing fake news detectors and effectively improve the performance of detecting fake news.1 2 Copyright © 2019, The Authors. All rights reserved.

关键词： Fake detection

来源：评论

学校读者我要写书评

暂无评论

COCO-CN for cross-lingual image tagging, captioning and retrieval

arXiv

引用

arXiv 2018年

作者： Li, Xirong Xu, Chaoxi Wang, Xiaoxu Lan, Weiyu Jia, Zhengxiong Yang, Gang Xu, Jieping Key Lab of Data Engineering and Knowledge Engineering Renmin University of China AI & Media Computing Lab School of Information Renmin University of China Beijing100872 China

This paper contributes to cross-lingual image annotation and retrieval in terms of data and baseline methods. We propose COCO-CN, a novel dataset enriching MS-COCO with manually written Chinese sentences and tags. For more effective annotation acquisition, we develop a recommendation-assisted collective annotation system, automatically providing an annotator with several tags and sentences deemed to be relevant with respect to the pictorial content. Having 20,342 images annotated with 27,218 Chinese sentences and 70,993 tags, COCO-CN is currently the largest Chinese-English dataset that provides a unified and challenging platform for cross-lingual image tagging, captioning and retrieval. We develop conceptually simple yet effective methods per task for learning from cross-lingual resources. Extensive experiments on the three tasks justify the viability of the proposed dataset and methods. data and code are publicly available at https://***/li-xirong/coco-cn. Copyright © 2018, The Authors. All rights reserved.

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

Exploring Structural Sparsity of Deep Networks via Inverse Scale Spaces

arXiv

引用

arXiv 2019年

作者： Fu, Yanwei Liu, Chen Li, Donghao Zhong, Zuyuan Sun, Xinwei Zeng, Jinshan Yao, Yuan School of Data Science Shanghai Key Lab of Intelligent Information Processing Fudan University Fudan ISTBI-ZJNU Algorithm Centre for Brain-Inspired Intelligence Zhejiang Normal University Jinhua China The School of Computer and Information Engineering Jiangxi Normal University China Hong Kong University of Science and Technology Hong Kong

The great success of deep neural networks is built upon their over-parameterization, which smooths the optimization landscape without degrading the generalization ability. Despite the benefits of over-parameterization, a huge amount of parameters makes deep networks cumbersome in daily life applications. On the other hand, training neural networks without over-parameterization faces many practical problems, e.g., being trapped in the local optimal. Though techniques such as pruning and distillation are developed, they are expensive in fully training a dense network as backward selection methods;and there is still a void on systematically exploring forward selection methods for learning structural sparsity in deep networks. To fill in this gap, this paper proposes a new approach based on differential inclusions of inverse scale spaces. Specifically, our method can generate a family of models from simple to complex ones along the dynamics via coupling a pair of parameters, such that over-parameterized deep models and their structural sparsity can be explored simultaneously. This kind of differential inclusion scheme has a simple discretization, dubbed Deep structure splitting Linearized Bregman Iteration (DessiLBI), whose global convergence in learning deep networks could be established under the Kurdyka-Lojasiewicz framework. Particularly, we explore several applications of DessiLBI, including finding sparse structures of networks directly via the coupled structure parameter and growing networks from simple to complex ones progressively. Experimental evidence shows that our method achieves comparable and even better performance than the competitive optimizers in exploring the sparse structure of several widely used backbones on the benchmark datasets. Remarkably, with early stopping, our method unveils "winning tickets" in early epochs: the effective sparse network structures with comparable test accuracy to fully trained over-parameterized models, that are further t

关键词： Linearization

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：