检索结果-内蒙古大学图书馆

Robust Bidirectional Generative Network For Generalized Zero-Shot Learning

学校读者我要写书评

暂无评论

Robust Bidirectional Generative Network For Generalized Zero...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yun Xing Sheng Huang Luwen Huangfu Feiyu Chen Yongxin Ge Ministry of Education Key Laboratory of Dependable Service Computing in Cyber Physical Society School of Big Data and Software Engineering at Chongqing University Chongqing P.R.China Fowler College of Business at San Diego State University San Diego USA

ISBN: (数字)9781728113319

ISBN: (纸本)9781728113326

In this work, we propose a novel generative approach named Robust Bidirectional Generative Network (RBGN) based on Conditional Generative Adversarial Network (CGAN) for Generalized Zero-shot Learning (GZSL). RBGN employs the adversarial attack to train a more rigorous discriminator, thus enhancing the generalizability and robustness of the feature generator under minimax strategy. Moreover, RBGN decodes the generated visual features back to their semantic representations to further improve the representational ability of generated visual features and alleviate the hubness problem. The experimental results of GZSL on four datasets, i.e. CUB, SUN, AWA1, AWA2, demonstrate that our model achieves competitive performance compared to state-of-the-art approaches and owns better generalizability to the unseen classes over conventional generative GZSL models. Further robustness analysis also validates the strong robustness of our model to the different types of semantic disturbance.

关键词： Semantics Visualization Robustness Generators Training Decoding Gallium nitride

Predicting long-term skeletal motions by a spatio-temporal hierarchical recurrent network

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Hu, Junfeng Fan, Zhencheng Liao, Jun Liu, Li School of Big Data & Software Engineering Chongqing University China School of Computing National University of Singapore 117417 Singapore

The primary goal of skeletal motion prediction is to generate future motion by observing a sequence of 3D skeletons. A key challenge in motion prediction is the fact that a motion can often be performed in several different ways, with each consisting of its own configuration of poses and their spatio-temporal dependencies, and as a result, the predicted poses often converge to the motionless poses or non-human like motions in long-term prediction. This leads us to define a hierarchical recurrent network model that explicitly characterizes these internal configurations of poses and their local and global spatio-temporal dependencies. The model introduces a latent vector variable from the Lie algebra to represent spatial and temporal relations simultaneously. Furthermore, a structured stack LSTM-based decoder is devised to decode the predicted poses with a new loss function defined to estimate the quantized weight of each body part in a pose. Empirical evaluations on benchmark datasets suggest our approach significantly outperforms the state-of-the-art methods on both short-term and long-term motion prediction. Copyright © 2019, The Authors. All rights reserved.

关键词： Motion estimation

Personalizing search results using hierarchical RNN with query-aware attention

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Ge, Songwei Dou, Zhicheng Jiang, Zhengbao Nie, Jian-Yun Wen, Ji-Rong School of Information Renmin University of China DIRO Université de Montréal Beijing Key Laboratory of Big Data Management and Analysis Methods National Engineering Laboratory of Big Data System Software Beijing Institute of Technology Key Laboratory of Data Engineering and Knowledge Engineering MOE

Search results personalization has become an effective way to improve the quality of search engines. Previous studies extracted information such as past clicks, user topical interests, query click entropy and so on to tailor the original ranking. However, few studies have taken into account the sequential information underlying previous queries and sessions. Intuitively, the order of issued queries is important in inferring the real user interests. And more recent sessions should provide more reliable personal signals than older sessions. In addition, the previous search history and user behaviors should influence the personalization of the current query depending on their relatedness. To implement these intuitions, in this paper we employ a hierarchical recurrent neural network to exploit such sequential information and automatically generate user profile from historical data. We propose a query-aware attention model to generate a dynamic user profile based on the input query. Significant improvement is observed in the experiment with data from a commercial search engine when compared with several traditional personalization models. Our analysis reveals that the attention model is able to attribute higher weights to more related past sessions after fine training. Copyright © 2019, The Authors. All rights reserved.

关键词： Search engines

PC-RGNN: Point cloud completion and graph neural network for 3D object detection

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Zhang, Yanan Huang, Di Wang, Yunhong Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100191 China State Key Laboratory of Software Development Environment Beihang University Beijing100191 China School of Computer Science and Engineering Beihang University Beijing100191 China

LiDAR-based 3D object detection is an important task for autonomous driving and current approaches suffer from sparse and partial point clouds of distant and occluded objects. In this paper, we propose a novel two-stage approach, namely PC-RGNN, dealing with such challenges by two specific solutions. On the one hand, we introduce a point cloud completion module to recover high-quality proposals of dense points and entire views with original structures preserved. On the other hand, a graph neural network module is designed, which comprehensively captures relations among points through a local-global attention mechanism as well as multi-scale graph based context aggregation, substantially strengthening encoded features. Extensive experiments on the KITTI benchmark show that the proposed approach outperforms the previous state-of-the-art baselines by remarkable margins, highlighting its effectiveness. Copyright © 2020, The Authors. All rights reserved.

关键词： Graph neural networks

On PID control for synchronization of complex dynamical network with delayed nodes

学校读者我要写书评

暂无评论

Science China(Technological Sciences) 2019年第8期62卷 1412-1422页

作者： GU HaiBo Lv JinHu LIN ZongLi Key Laboratory of Systems and Control Academy of Mathematics and Systems Science Chinese Academy of Sciences Beijing 100190 China School of Mathematical Sciences University of Chinese Academy of Sciences Beijing 100049 China School of Automation Science and Electrical Engineering State Key Laboratory of Software Development Environment and Beijing Advanced Innovation Center for Big Data and Brain Machine Intelligence Beihang University Beijing 100083 China Charles L. Brown Department of Electrical and Computer Engineering University of Virginia Charlottesville VA 22904-4743 USA

Over the past two decades, synchronization, as an interesting collective behavior of complex dynamical networks, has been attracting much attention. To reveal and analyze the inherent mechanism of synchronization in complex dynamical networks with time delays in nodes, this paper attempts to use PD and PI control protocols to achieve synchronization. Based on a classical network model, we investigate the PD and PI control for synchronization of complex dynamical networks with delayed nodes and obtain some sufficient conditions. By using Lyapunov functions and appropriate state transformations, we prove that global synchronization can be achieved via the above control protocols. Finally, some simulation examples are illustrated to validate the effectiveness of the proposed theoretical results.

关键词： synchronization PID control complex dynamical network networked control system delayed node

Binary neural networks: A survey

学校读者我要写书评

暂无评论

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

Spatio-temporal propagation of COVID-19 pandemics

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Gross, Bnaya Zheng, Zhiguo Liu, Shiyan Chen, Xiaoqi Sela, Alon Li, Jianxin Li, Daqing Havlin, Shlomo Department of Physics Bar-Ilan University Ramat-Gan52900 Israel School of Reliability and Systems Engineering Beihang University Beijing100191 China Department of Industrial Engineering Ariel University Ariel Israel Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing100083 China State Key Laboratory of Software Development Environment Beihang University Beijing100083 China Beijing Advanced Innovation Center for Big Data-Based Precision Medicine Beihang University Beijing100191 China

The new coronavirus known as COVID-19 is rapidly spreading since December 2019. Without any vaccination or medicine, the means of controlling it are limited to quarantine and social distancing. Here we study the spatio-temporal propagation of the COVID-19 virus in China and compare it to other global locations. Our results suggest that the disease propagation is highly related to population migration from Hubei resembling a Lévy flight which is characteristic of human mobility and thus could be controlled by efficient quarantines. Since quarantine is usually applied on a city level, more insight can be obtained in analyzing the epidemic in cities. Our results suggest that the disease spread in a city in China is characterized by two-stages process. At early times, at order of few days, the infection rate in the city is close to constant probably due to the lack of means to detect infected individuals before infection signs are observed and at later times it decays approximately exponentially due to quarantines. These two stages can explain the significant differences between the propagation in China and in other world-wide locations. While most cities in China control the disease which resulted in the decaying stage, in other world-wide countries the situation is still becoming worse probably due to less social interactions control and overloaded health systems which reflects in the death and recovery rates. Copyright © 2020, The Authors. All rights reserved.

关键词： Population dynamics

Text Cover Steganography Using Font Color of the Invisible Characters and Optimized Primary Color-intensities

学校读者我要写书评

暂无评论

Text Cover Steganography Using Font Color of the Invisible C...

International Conference on Communication Technology (ICCT)

作者： Feno Heriniaina Rabevohitra Yantao Li School of Big Data and Software Engineering Chongqing University Chongqing China College of Computer Science Chongqing University Chongqing China

Text cover steganography is concerned with using text support for hiding information. Despite its long and old history, the art of cover writing is still attracting the attention of researchers in the domain of information hiding. Unfortunately, only a few related works exist in terms of text-covered writing. We present a visual attack on the previous related work. Then, we use invisible characters to hide secret data within the text support. We further use a combination and variation of the three primary colors intensities to vehiculate the message when painting non-printing characters. The proposed algorithm makes use of the low-value color spaces to decrease the color variations of the embedded secret message. It also further strengthens the hiddenness of the non-printing characters even when replaced by visible characters.

关键词： Color Image color analysis Painting software Text processing Visualization Writing

LCL-AKA: Lightweight Authentication and Key Agreement Protocol for Power IoT

学校读者我要写书评

暂无评论

IEEE Transactions on Smart Grid 2025年

作者： Liu, Zewei Hu, Chunqiang Ruan, Conghao Pu, Yuwen Hu, Pengfei Yu, Jiguo Cyber Physical Society Ministry of Education Key Laboratory of Dependable Service Computing Chongqing University China Chongqing University School of Big Data and Software Engineering Chongqing China China Southern Power Grid Joint Laboratory on Cyberspace Security China Shandong University School of Computer Science and Technology Shandong China Qilu University of Technology Shandong Academy of Sciences School of Computer Science and Technology Jinan250353 China Shandong Laboratory of Computer Networks Jinan250014 China

The rapid adoption of power Internet of Things (PIoT) systems has made security a critical concern, particularly as existing certificateless authentication and key agreement (CL-AKA) protocols face three fundamental limitations that hinder their practical deployment: excessive computational overhead from multi-round interactions, inadequate protection against advanced cryptanalytic attacks, and inflexible architectures unsuitable for dynamic grid environments. To tackle the previously mentioned challenges, this paper proposes lightweight authentication and key agreement protocol (LCL-AKA) for PIoT. Firstly, this protocol efficiently completes the process of identity authentication and session key agreement within a single round of communication interaction, significantly reducing computational costs and improving communication efficiency. Security is rigorously validated through formal proofs under the eCK model and comprehensive analysis showing resistance to key compromise impersonation, unknown key-share attack. Ultimately, comparative experiments are executed to delve into the security and performance characteristics of the proposed protocol. Compared to benchmark protocols deployed in PIoT, the authentication delay of LCL-AKA is decreased by at least 14.88%;in addition, the energy consumption of LCL-AKA is decreased by at least 11.28%. © 2010-2012 IEEE.

关键词： certificateless authentication and key agreement communication efficiency PIoT security proofs