检索结果-内蒙古大学图书馆

Weakly supervised open-set domain adaptation by dual-domain collaboration

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Tan, Shuhan Jiao, Jiening Zheng, Wei-Shi School of Data and Computer Science Sun Yat-sen University China School of Electronics and Information Technology Sun Yat-sen University China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Accuvision Technology Co. Ltd.

In conventional domain adaptation, a critical assumption is that there exists a fully labeled domain (source) that contains the same label space as another unlabeled or scarcely labeled domain (target). However, in the real world, there often exist application scenarios in which both domains are partially labeled and not all classes are shared between these two domains. Thus, it is meaningful to let partially labeled domains learn from each other to classify all the unlabeled samples in each domain under an open-set setting. We consider this problem as weakly supervised open-set domain adaptation. To address this practical setting, we propose the Collaborative Distribution Alignment (CDA) method, which performs knowledge transfer bilaterally and works collaboratively to classify unlabeled data and identify outlier samples. Extensive experiments on the Office benchmark and an application on person reidentification show that our method achieves state-of-theart performance. Copyright © 2019, The Authors. All rights reserved.

关键词： Knowledge management

Deep dual relation modeling for egocentric interaction recognition

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Li, Haoxin Cai, Yijun Zheng, Wei-Shi School of Electronics and Information Technology Sun Yat-sen University China School of Data and Computer Science Sun Yat-sen University China Peng Cheng Laboratory Shenzhen518005 China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China

Egocentric interaction recognition aims to recognize the camera wearer’s interactions with the interactor who faces the camera wearer in egocentric videos. In such a human-human interaction analysis problem, it is crucial to explore the relations between the camera wearer and the interactor. However, most existing works directly model the interactions as a whole and lack modeling the relations between the two interacting persons. To exploit the strong relations for egocentric interaction recognition, we introduce a dual relation modeling framework which learns to model the relations between the camera wearer and the interactor based on the individual action representations of the two persons. Specifically, we develop a novel interactive LSTM module, the key component of our framework, to explicitly model the relations between the two interacting persons based on their individual action representations, which are collaboratively learned with an interactor attention module and a global-local motion module. Experimental results on three egocentric interaction datasets show the effectiveness of our method and advantage over state-of-the-arts. Copyright © 2019, The Authors. All rights reserved.

关键词： Cameras

Detect camouflaged spam content via stoneskipping: Graph and text joint embedding for Chinese character variation representation

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Jiang, Zhuoren Gao, Zhe He, Guoxiu Kang, Yangyang Sun, Changlong Zhang, Qiong Si, Luo Liu, Xiaozhong School of Data and Computer Science Sun Yat-sen University Guangzhou China Alibaba Group Hangzhou and Sunnyvale and Seattle China United States School of Information Management Wuhan University Wuhan China School of Informatics Computing and Engineering Indiana University Bloomington Bloomington United States

The task of Chinese text spam detection is very challenging due to both glyph and phonetic variations of Chinese characters. This paper proposes a novel framework to jointly model Chinese variational, semantic, and contextualized representations for Chinese text spam detection task. In particular, a Variation Family-enhanced Graph Embedding (VFGE) algorithm is designed based on a Chinese character variation graph. The VFGE can learn both the graph embeddings of the Chinese characters (local) and the latent variation families (global). Furthermore, an enhanced bidirectional language model, with a combination gate function and an aggregation learning function, is proposed to integrate the graph and text information while capturing the sequential information. Extensive experiments have been conducted on both SMS and review datasets, to show the proposed method outperforms a series of state-of-the-art models for Chinese spam detection. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

A survey on edge computing systems and tools

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Liu, Fang Tang, Guoming Li, Youhuizi Cai, Zhiping Zhang, Xingzhou Zhou, Tongqing School of Data and Computer Science Sun Yat-sen University GuangzhouGuangdong China Key Laboratory of Science and Technology on Information System Engineering National University of Defense Technology ChangshaHunan China School of Compute Science and Technology Hangzhou Dianzi University China College of Computer National University of Defense Technology ChangshaHunan China State Key Laboratory of Computer Architecture Institute of Computing Technology Chinese Academy of Sciences China

—Driven by the visions of Internet of Things and 5G communications, the edge computing systems integrate computing, storage and network resources at the edge of the network to provide computing infrastructure, enabling developers to quickly develop and deploy edge applications. Nowadays the edge computing systems have received widespread attention in both industry and academia. To explore new research opportunities and assist users in selecting suitable edge computing systems for specific applications, this survey paper provides a comprehensive overview of the existing edge computing systems and introduces representative projects. A comparison of open source tools is presented according to their applicability. Finally, we highlight energy efficiency and deep learning optimization of edge computing systems. Open issues for analyzing and designing an edge computing system are also studied in this survey. Copyright © 2019, The Authors. All rights reserved.

关键词： Energy efficiency

Unsupervised Person Re-Identification by Camera-Aware Similarity Consistency Learning

学校读者我要写书评

暂无评论

Unsupervised Person Re-Identification by Camera-Aware Simila...

International Conference on computer Vision (ICCV)

作者： Ancong Wu Wei-Shi Zheng Jian-Huang Lai School of Electronics and Information Technology Sun Yat-sen University China School of Data and Computer Science Sun Yat-sen University China Peng Cheng Laboratory China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangdong Province Key Laboratory of Information Security China

ISBN: (数字)9781728148038

ISBN: (纸本)9781728148045

For matching pedestrians across disjoint camera views in surveillance, person re-identification (Re-ID) has made great progress in supervised learning. However, it is infeasible to label data in a number of new scenes when extending a Re-ID system. Thus, studying unsupervised learning for Re-ID is important for saving labelling cost. Yet, cross-camera scene variation is a key challenge for unsupervised Re-ID, such as illumination, background and viewpoint variations, which cause domain shift in the feature space and result in inconsistent pairwise similarity distributions that degrade matching performance. To alleviate the effect of cross-camera scene variation, we propose a Camera-Aware Similarity Consistency Loss to learn consistent pairwise similarity distributions for intra-camera matching and cross-camera matching. To avoid learning ineffective knowledge in consistency learning, we preserve the prior common knowledge of intra-camera matching in the pretrained model as reliable guiding information, which does not suffer from cross-camera scene variation as cross-camera matching. To learn similarity consistency more effectively, we further develop a coarse-to-fine consistency learning scheme to learn consistency globally and locally in two steps. Experiments show that our method outperformed the state-of-the-art unsupervised Re-ID methods.

关键词： Cameras Feature extraction Reliability Computational modeling Labeling data models Lighting

Defending against advanced persistent threat: A risk management perspective 1st

学校读者我要写书评

暂无评论

Defending against advanced persistent threat: A risk managem...

1st International Conference on science of Cyber Security, SciSec 2018

作者： Zhong, Xiang Yang, Lu-Xing Yang, Xiaofan Xiong, Qingyu Wen, Junhao Tang, Yuan Yan School of Big Data and Software Engineering Chongqing University Chongqing400044 China School of Information Technology Deakin University MelbourneVIC3125 Australia Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China Department of Computer and Information Science The University of Macau China

ISBN: (纸本)9783030030254

Advanced persistent threat (APT) as a new form of cyber attack has posed a severe threat to modern organizations. When an APT has been detected, the target organization has to develop a response resource allocation strategy to mitigate her potential loss. This paper suggests a risk management approach to solving this APT response problem. First, we present three state evolution models. Thereby we assess the organization’s potential loss. On this basis, we propose two kinds of game-theoretic models of the APT response problem. This work initiates the study of the APT response problem. © Springer Nature Switzerland AG 2018.

关键词： Game theory

Strict pattern matching under non-overlapping condition

学校读者我要写书评

暂无评论

science China(information sciences) 2017年第1期60卷 5-20页

作者： Youxi WU Cong SHEN He JIANG Xindong WU School of Computer Science and Engineering Hebei University of Technology Hebei Province Key Laboratory of Big Data Calculation School of Computer Science and Technology Tianjin University School of Software Dalian University of Technology School of Computer Science and Information Engineering Hefei University of Technology School of Computing and Informatics University of Louisiana at Lafayette

Pattern matching(or string matching) is an essential task in computer science, especially in sequential pattern mining, since pattern matching methods can be used to calculate the support(or the number of occurrences) of a pattern and then to determine whether the pattern is frequent or not. A state-of-the-art sequential pattern mining with gap constraints(or flexible wildcards) uses the number of non-overlapping occurrences to denote the frequency of a pattern. Non-overlapping means that any two occurrences cannot use the same character of the sequence at the same position of the pattern. In this paper, we investigate strict pattern matching under the non-overlapping condition. We show that the problem is in P at first. Then we propose an algorithm, called NETLAP-Best, which uses Nettree structure. NETLAP-Best transforms the pattern matching problem into a Nettree and iterates to find the rightmost root-leaf path, to prune the useless nodes in the Nettree after removing the rightmost root-leaf path. We show that NETLAP-Best is a complete algorithm and analyse the time and space complexities of the algorithm. Extensive experimental results demonstrate the correctness and efficiency of NETLAP-Best.

关键词： pattern matching sequential pattern mining gap constraint flexible wildcard non-overlapping occurrence Nettree

Residual Networks for Light Field Image Super-Resolution

学校读者我要写书评

暂无评论

Residual Networks for Light Field Image Super-Resolution

IEEE/CVF Conference on computer Vision and Pattern Recognition

作者： Shuo Zhang Youfang Lin Hao Sheng Beijing Key Lab of Traffic Data Analysis and Mining School of Computer and Information Technology Beijing Jiaotong University Key Laboratory of Intelligent Passenger Service of Civil Aviation CAAC State Key Laboratory of Software Development Environment School of Computer Science and Engineering Beihang University Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University

Light field cameras are considered to have many potential applications since angular and spatial information is captured simultaneously. However, the limited spatial resolution has brought lots of difficulties in developing related applications and becomes the main bottleneck of light field cameras. In this paper, a learning-based method using residual convolutional networks is proposed to reconstruct light fields with higher spatial resolution. The view images in one light field are first grouped into different image stacks with consistent sub-pixel offsets and fed into different network branches to implicitly learn inherent corresponding relations. The residual information in different spatial directions is then calculated from each branch and further integrated to supplement high-frequency details for the view image. Finally, a flexible solution is proposed to super-resolve entire light field images with various angular resolutions. Experimental results on synthetic and real-world datasets demonstrate that the proposed method outperforms other state-of-the-art methods by a large margin in both visual and numerical evaluations. Furthermore, the proposed method shows good performances in preserving the inherent epipolar property in light field images.

关键词：

Lattice Blind Signatures with Forward Security

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Le, Huy Quoc Duong, Dung Hoang Susilo, Willy Tran, Ha Thanh Nguyen Trinh, Viet Cuong Pieprzyk, Josef Plantard, Thomas Institute of Cybersecurity and Cryptology School of Computing and Information Technology University of Wollongong Northfields Avenue WollongongNSW2522 Australia Department of Mathematical and Physical Sciences Concordia University of Edmonton 7128 Ada Blvd NW EdmontonABT5B 4E4 Canada Faculty of Information and Communication Technology Hong Duc University 565 Quang Trung Thanh Hoa Viet Nam CSIRO Data61 SydneyNSW Australia Institute of Computer Science Polish Academy of Sciences Warsaw Poland

Blind signatures play an important role in both electronic cash and electronic voting systems. Blind signatures should be secure against various attacks (such as signature forgeries). The work puts a special attention to secret key exposure attacks, which totally break digital signatures. Signatures that resist secret key exposure attacks are called forward secure in the sense that disclosure of a current secret key does not compromise past secret keys. This means that forward-secure signatures must include a mechanism for secret-key evolution over time periods. This paper gives a construction of the first blind signature that is forward secure. The construction is based on the SIS assumption in the lattice setting. The core techniques applied are the binary tree data structure for the time periods and the trapdoor delegation for the key-evolution mechanism. Copyright © 2020, The Authors. All rights reserved.

关键词： Network security