Authentication email has already been sent, please check your email box: and activate it as soon as possible.
You can login to My Profile and manage your email alerts.
If you haven’t received the email, please:
|
|
There are 954 papers published in subject: since this site started. |
Select Subject |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
1. Deep Reinforcement Learning-based Multi-Layer Cascaded Resilient Recovery for Cyber-Physical Systems | |||
ZHONG Kai,YANG Zhibang,YU Siyang,LI Kenli | |||
Computer Science and Technology 18 April 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Cyber-physical systems (CPS) are complex systems comprised of physical and computational components, which are susceptible to various disturbances and attacks, leading to system failures and security breaches. In recent years, CPS resilience has garnered increasing attention, with some studies proposing CPS resilience methods. However, existing methods overlook the interdependence between different components of the information and physical layers in the CPS network, and exhibit limitations in scalability, adaptability, and efficiency. To address these issues, this paper introduces a multilayer cascade resilience recovery framework based on deep reinforcement learning. Firstly, the high degree of interaction between the information and physical layers in CPS resilience recovery is comprehensively synthesized, and this correlation relationship is modeled using an association matrix. Secondly, a hybrid resilience recovery strategy is proposed to segment the association matrix into horizontal and vertical slices, treating its resilience strategy solution as an optimization problem. Finally, a deep reinforcement learning algorithm centered on resilience prioritization is presented to solve the optimal policy for hybrid resilient recovery. | |||
TO cite this article:ZHONG Kai,YANG Zhibang,YU Siyang, et al. Deep Reinforcement Learning-based Multi-Layer Cascaded Resilient Recovery for Cyber-Physical Systems[OL].[18 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763397 |
2. MU2MV: Efficient and Secure Task Offloading Framework in UAV-assisted Smart Networks | |||
ZHONG Kai,YANG Zhibang,LI Kenli | |||
Computer Science and Technology 18 April 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:UAV technology has emerged as a promising solution, introducing a new approach to smart grid inspection. This paper explores the safe and efficient task offloading of UAV cruise systems within smart grids. Specifically, it proposes a multi-UAV to multi-vehicle fog computing node task offloading framework named MU2MV. Firstly, a novel reputation incentive mechanism based on the behavior of vehicle fog computing nodes is introduced. This mechanism provides incentives or penalties based on the behaviors of these nodes to select suitable target fog computing nodes and encourage newly joined nodes to actively provide computing services as service providers. Secondly, a two-tier collaborative non-cooperative game model is proposed to simulate the cooperative-competitive relationships among UAVs and vehicle fog computing nodes, as well as among the vehicle fog computing nodes themselves, the optimal strategy combinations are determined by solving the Nash equilibrium solution within the game model. Finally, recognizing the challenges posed by the dynamic movement of UAVs and vehicle fog computing nodes in real environments, a deep reinforcement learning algorithm is proposed to seek the optimal strategy combination for UAVs and vehicle fog computing nodes. | |||
TO cite this article:ZHONG Kai,YANG Zhibang,LI Kenli. MU2MV: Efficient and Secure Task Offloading Framework in UAV-assisted Smart Networks[OL].[18 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763398 |
3. Research of License Plate Detection and Recognition in Complex Scene | |||
Wang Ying | |||
Computer Science and Technology 11 April 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:In The technology of license plate detection and recognition is very important in modern transportation system. However, in the real scene, bad weather and oblique shooting angles will affect the accuracy of detection and recognition. Therefore, this paper mainly studies license plate detection and recognition algorithms under complex conditions.The license plate detection in this article uses the RetinaNet detection algorithm. First, build a ResNet network and FPN combination for image feature extraction and feature fusion, and then use Focal Loss regression to get an accurate prediction frame. The data is the CCPD data, which includs photos of various scenes, and the number is large, which can make the detection model more adaptable to complex conditions.The license plate recognition uses the combination of STN and LPRNet. STN is a kind of image space change network, which can perform affine change processing on the image. In this paper, the STN network is added to the LPRNet network, so that the network can learn how to reduce Loss through the spatial change of the image, and then the network can correct the slanted license plate. LPRNet is an end-to-end network that can recognize license plate characters without cutting characters. It is mainly composed of convolutional neural networks and CTC Loss. Finally, the effectiveness of the methodology of this paper is demonstrated through experiments. | |||
TO cite this article:Wang Ying. Research of License Plate Detection and Recognition in Complex Scene[OL].[11 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763301 |
4. Granularized Dialogue Model of The Knowledge Graph | |||
Zhao Meiyong,Yu Wen | |||
Computer Science and Technology 10 April 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This paper designs a dialogue model based on the granulated knowledge graph (Granulation Knowledge aware Dialogue Model, GKDM). Through the method of structural granulation, the knowledge graph is divided into two modules: local knowledge graph and non-local knowledge graph, respectively capturing the local semantics adjacent to the knowledge entity and the overall semantic representation of the located knowledge sub-graph, which solves the problem of the division of the knowledge graph. This paper designs the static graph attention mechanism and the hierarchical dynamic graph attention mechanism to participate in the process of encoding and decoding in the model respectively, and aggregates the semantics of knowledge entities through multi-level attention weights, and fuses them into the text vector, which solves the problem of the fusion of multi-layer knowledge information. Based on the above two innovations, the model proposed in this paper alleviates the problems of the current knowledge graph-based dialogue model that cannot capture the reasoning meaning of the multi-hop paths of the knowledge graph and the inconsistent theme of the reply context. | |||
TO cite this article:Zhao Meiyong,Yu Wen. Granularized Dialogue Model of The Knowledge Graph[OL].[10 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763289 |
5. Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval | |||
ZHANG Bolin,YANG Chao,JIANG Bin,KOMAMIZU Takahiro,IDE Ichiro | |||
Computer Science and Technology 02 April 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:This study focuses on weakly-supervised Video Moment Retrieval (VMR), aiming to identify a moment semantically similar to the given query within an untrimmed video using only video-level correspondences, without relying on temporal annotations during training. Previous methods either aggregate predictions for all instances in the video, or indirectly address the task by proposing reconstructions for the query. However, these methods often produce low-quality temporal proposals, struggle with distinguishing misaligned moments in the same video, or lack stability due to a reliance on a single auxiliary task.To address these limitations, we present a novel weakly-supervised method called Multi-proposal Collaboration and Multi-task Training (MCMT). Initially, we generate multiple proposals and derive corresponding learnable Gaussian masks from them. These masks are then combined to create a high-quality positive sample mask, highlighting video clips most relevant to the query. Concurrently, we classify other clips in the same video as easy negative sample and the entire video as hard negative sample. During training, we introduce forward and inverse masked query reconstruction tasks to impose more substantial constraints on the network, promoting more robust and stable retrieval performance. Extensive experiments on two standard benchmarks affirm the effectiveness of the proposed method in VMR. | |||
TO cite this article:ZHANG Bolin,YANG Chao,JIANG Bin, et al. Multi-proposal Collaboration and Multi-task Training for Weakly-supervised Video Moment Retrieval[OL].[ 2 April 2024] http://en.paper.edu.cn/en_releasepaper/content/4763143 |
6. The Analysis of Adversarial Robustness in Federated Learning Based on Differential Privacy | |||
Li Qi,Li Li | |||
Computer Science and Technology 26 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Federated learning (FL) allows multiple participants to train models collaboratively by keeping their data local while exchanging updates, however, this also increases the risk of attack. Models in FL are as vulnerable as centrally trained models against adversarial examples. And with frequent data exchanging, the risk of data breaches increases. To enhance the robustness against adversarial examples, this paper introduces the differential privacy into FL, which is also an effective mechanism used for privacy protection.Many popular approaches that involve adversarial training in FL often compromise test accuracy while effect. In this work, a novel method is proposed which applies differential privacy to enhance both adversarial robustness and privacy protection level. Extensive experiments on multiple datasets demonstrate the proposed approach has a better performance compared with other baselines. | |||
TO cite this article:Li Qi,Li Li. The Analysis of Adversarial Robustness in Federated Learning Based on Differential Privacy[OL].[26 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4763096 |
7. GPALzz: A state-leading fuzzing framework via basic network communication interface | |||
HAO Wen-Peng,GUO Yan-Hui | |||
Computer Science and Technology 25 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Today, the rapid adoption of IoT devices has brought security risks while facilitating people's lives. Latest research focuses on information acquisition and state establishment, however exists the defects of relys on vendors and lacks universality; focuses on communication formats rather than device information; difficult to accurately guide fuzzing into specific states then in a stable state. To address the above issues, we propose an interactive leading fuzzing scheme, named GPALzz. It uses active automata learning to break free from vendor dependence, establishes device service state guidance fuzzy testing, and utilies interaction capabilities to establish an equivalent automaton that describes device service state information. Furthermore, we selected 9 devices to verify our scheme and discovered 24 crashes in 7 devices. | |||
TO cite this article:HAO Wen-Peng,GUO Yan-Hui. GPALzz: A state-leading fuzzing framework via basic network communication interface[OL].[25 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762868 |
8. Multi-Object Tracking with decoupled representations and unreliable detections in complex scenes | |||
XIAO Yuan, ZOU Qi | |||
Computer Science and Technology 21 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:Joint-Detection-and-Embedding paradigm achieves fast tracking by simultaneously learning detection and Re-ID features. However, it still faces performance degradation in complex scenes and the misalignment between detection and Re-ID features. In this paper, we propose a decoupling module based on channel-wise attention mechanism to obtain task-aligned features served for different demands of detection and Re-ID. To improve the performance of data association, we fuse motion, location, appearance information and perform a two-round matching for high and low confidence detections respectively by the Motion-GIoU matrix and the Embedding-GIoU matrix. Additionally, we apply the camera motion compensation to get a more accurate motion estimation, resulting in a more robust tracking in the scenes of camera motion and low-frame-rate. Extensive experiments show that our proposed method outperforms a wide range of existing methods on the MOTChallenge and HiEvE datasets. | |||
TO cite this article:XIAO Yuan, ZOU Qi. Multi-Object Tracking with decoupled representations and unreliable detections in complex scenes[OL].[21 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4763002 |
9. End-to-End Virtual Shadow Generation Based on Shadow Detection | |||
Xue Junsheng, Huang Hai | |||
Computer Science and Technology 21 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:With the rapid development of the augmented reality field, virtual shadow generation technology has garnered widespread attention. However, traditional methods involve complex computational requirements for environmental modeling and display, and the effectiveness of using fewer 3D parameter estimation methods is suboptimal. To address these issues, this paper proposes an end-to-end virtual shadow generation method based on shadow detection. Firstly, we introduce a shadow detector designed to identify real shadows and their corresponding occlusions in the background context, while also learning the mapping relationship between occlusions and shadows in the current scene. Secondly, we devise a virtual shadow generator. Utilizing the mapping relationship obtained from the detector as guidance information, it is encoded into the generator's input. Through feature extraction, encoding, and decoding of the input information, we ultimately obtain the virtual shadow image. Experimental results demonstrate the exceptional performance of the proposed virtual shadow generation method. In comparison to existing methods for direct virtual shadow generation, our approach significantly enhances the harmony and realism of the synthesized images. | |||
TO cite this article:Xue Junsheng, Huang Hai. End-to-End Virtual Shadow Generation Based on Shadow Detection[OL].[21 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762999 |
10. Causal-Proto SSRL: Learning Dynamic-Necessary State Variables for Multi-Environment Reinforcement Learning | |||
Zhang Meng,Zhang Chunhong,Hu Zheng,Zhuang Benhui | |||
Computer Science and Technology 19 March 2024 | |||
Show/Hide Abstract | Cite this paper︱Full-text: PDF (0 B) | |||
Abstract:The ability to learn directly from high-dimensional observations such as pixels allows reinforcement learning(RL) to achieve more widely applications. However, high-dimensional observations contain entangled task-relevant and task-irrelevant informations, as well as informations related to actions but unnecessary, which leads to non-essential dependencies and thus affects the generalization and robustness of the reinforcement learning. In order to learn abstract state representations from high-dimensional observations which generalized acorss multiple tasks and robust in environments with different task-unnecessary informations, this paper formulates the POMDP as Partially Observable Temporal Causal Dynamic Models (POTCDMs) and proposes a self-supervised RL with causal representation learning, Causal-Proto RL. This method seperates encoded observations into dynamic-necessary and dynamic-unnecessary state variables where only dynamic-necessary state variables are fed into RL by predicting the causal relationships simultaneously. This method is pretrained in absence of specific task rewards with an intrinsic rewards fo curiosity of causal relationships and are implemented in multiple difficult downstream tasks. This paper evaluate the algorithm in DeepMind Control Suit. This algorithm performs as well as other SOTA slef-supervised RL on a series of downstream tasks in environents as same as pretraining, and demonstrates generalization and robustness in downstream task environments different from pretraining. | |||
TO cite this article:Zhang Meng,Zhang Chunhong,Hu Zheng, et al. Causal-Proto SSRL: Learning Dynamic-Necessary State Variables for Multi-Environment Reinforcement Learning[OL].[19 March 2024] http://en.paper.edu.cn/en_releasepaper/content/4762946 |
Select/Unselect all | For Selected Papers |
Saved Papers
Please enter a name for this paper to be shown in your personalized Saved Papers list
|
|
About Sciencepaper Online | Privacy Policy | Terms & Conditions | Contact Us
© 2003-2012 Sciencepaper Online. unless otherwise stated