检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Hu, Xuemin Chen, Pan Wen, Yijun Tang, Bo Chen, Long School of Artificial Intelligence Hubei University Wuhan430062 China Key Laboratory of Intelligent Sensing System and Security Hubei University Ministry of Education Hubei Wuhan430062 China Department of Electrical and Computer Engineering Worcester Polytechnic Institute WorcesterMA01609 United States State Key Laboratory of Multimodal Artificial Intelligence Systems State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences Beijing100190 China WAYTOUS Inc. Beijing100083 China Shenzhen518107 China Institute of Artificial Intelligence and Robotics Xi'an Jiaotong University Xi’an710049 China

Reinforcement learning (RL) has been widely used in decision-making and control tasks, but the risk is very high for the agent in the training process due to the requirements of interaction with the environment, which seriously limits its industrial applications such as autonomous driving systems. Safe RL methods are developed to handle this issue by constraining the expected safety violation costs as a training objective, but the occurring probability of an unsafe state is still high, which is unacceptable in autonomous driving tasks. Moreover, these methods are difficult to achieve a balance between the cost and return expectations, which leads to learning performance degradation for the algorithms. In this paper, we propose a novel algorithm based on the long and short-term constraints (LSTC) for safe RL. The short-term constraint aims to enhance the shortterm state safety that the vehicle explores, while the long-term constraint enhances the overall safety of the vehicle throughout the decision-making process, both of which are jointly used to enhance the vehicle safety in the training process. In addition, we develop a safe RL method with dual-constraint optimization based on the Lagrange multiplier to optimize the training process for end-to-end autonomous driving. Comprehensive experiments were conducted on the MetaDrive simulator. Experimental results demonstrate that the proposed method achieves higher safety in continuous state and action tasks, and exhibits higher exploration performance in long-distance decision-making tasks compared with state-of-the-art methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Lagrange multipliers

来源：评论

学校读者我要写书评

暂无评论

MFCLIP: Multi-modal Fine-grained CLIP for Generalizable Diffusion Face Forgery Detection

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Wang, Tianyi Yu, Zitong Gao, Zan Shen, Linlin Chen, Shengyong Jinan250353 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Jinan250014 China The Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen518060 China

The rapid development of photo-realistic face generation methods has raised significant concerns in society and academia, highlighting the urgent need for robust and generalizable face forgery detection (FFD) techniques. Although existing approaches mainly capture face forgery patterns using image modality, other modalities like fine-grained noises and texts are not fully explored, which limits the generalization capability of the model. In addition, most FFD methods tend to identify facial images generated by GAN, but struggle to detect unseen diffusion-synthesized ones. To address the limitations, we aim to leverage the cutting-edge foundation model, contrastive language-image pre-training (CLIP), to achieve generalizable diffusion face forgery detection (DFFD). In this paper, we propose a novel multi-modal fine-grained CLIP (MFCLIP) model, which mines comprehensive and fine-grained forgery traces across image-noise modalities via language-guided face forgery representation learning, to facilitate the advancement of DFFD. Specifically, we devise a fine-grained language encoder (FLE) that extracts fine global language features from hierarchical text prompts. We design a multi-modal vision encoder (MVE) to capture global image forgery embeddings as well as fine-grained noise forgery patterns extracted from the richest patch, and integrate them to mine general visual forgery traces. Moreover, we build an innovative plug-and-play sample pair attention (SPA) method to emphasize relevant negative pairs and suppress irrelevant ones, allowing cross-modality sample pairs to conduct more flexible alignment. Extensive experiments and visualizations show that our model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

CODH++: Macro-semantic differences oriented instance segmentation network

引用

Expert systems with Applications 2022年 202卷 1页

作者： Zhang, Wenchao Fu, Chong Cao, Lin Sham, Chiu-Wing School of Computer Science and Engineering Northeastern University Shenyang110819 China Engineering Research Center of Security Technology of Complex Network System Ministry of Education China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China School of Information and Communication Engineering Beijing Information Science and Technology University Beijing100101 China School of Computer Science The University of Auckland New Zealand

With the idea of divide and rule, there exist two different forms of semantic features flowing in the two stage instance segmentation paradigms. They are the global features at the image level and the instance features at the region-wise. The most significant distinction of the two macro-semantic morphological features lies in the different relevance of neighborhood features caused by background noise. Hence, we should consider different situations and make different schemes. Notice that the fields-of-view determines the range of local features that can be perceived in the convolution operation and implies the representation capability of the network. To this end, for FPN and Mask Head in two stage paradigms, we propose a more efficient methodology with Group-Inception and Asymmetric-Inception modules. This proposed methodology can act as a drop-in replacement to upgrade the plain convolution operation, which enables the network to look more via modeling long-range dependencies. Our method is simple yet effective. Quantitatively, we can significantly improve the state-of-the-art frameworks, including Mask R-CNN, Mask Scoring R-CNN, Cascade Mask R-CNN, and HTC by about 1.2%–2.2% AP on MS COCO test-dev yet with fewer parameters and FLOPs. Moreover, the proposed approach achieves competitive performances on the Scapes, KINS and SBD datasets. The source code of our method will be made available. © 2022 Elsevier Ltd

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Adaptive Backdoor Attacks with Reasonable Constraints on Graph Neural Networks

arXiv

引用

arXiv 2025年

作者： Dong, Xuewen Li, Jiachen Li, Shujun You, Zhichao Qu, Qiang Kholodov, Yaroslav Shen, Yulong School of Computer Science and Technology Xidian University The Engineering Research Center of Blockchain Technology Application and Evaluation Ministry of Education China The Shaanxi Key Laboratory of Blockchain and Secure Computing Xi’an710071 China University of Kent CanterburyCT2 7NP United Kingdom Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Intelligent Transportation Systems Lab Innopolis University Innopolis Russia School of Computer Science and Technology Xidian University China The Shaanxi Key Laboratory of Network and System Security Xi’an710071 China

Recent studies show that graph neural networks (GNNs) are vulnerable to backdoor attacks. Existing backdoor attacks against GNNs use fixed-pattern triggers and lack reasonable trigger constraints, overlooking individual graph characteristics and rendering insufficient evasiveness. To tackle the above issues, we propose ABARC, the first Adaptive Backdoor Attack with Reasonable Constraints, applying to both graph-level and node-level tasks in GNNs. For graph-level tasks, we propose a subgraph backdoor attack independent of the graph’s topology. It dynamically selects trigger nodes for each target graph and modifies node features with constraints based on graph similarity, feature range, and feature type. For node-level tasks, our attack begins with an analysis of node features, followed by selecting and modifying trigger features, which are then constrained by node similarity, feature range, and feature type. Furthermore, an adaptive edge-pruning mechanism is designed to reduce the impact of neighbors on target nodes, ensuring a high attack success rate (ASR). Experimental results show that even with reasonable constraints for attack evasiveness, our attack achieves a high ASR while incurring a marginal clean accuracy drop (CAD). When combined with the state-of-the-art defense randomized smoothing (RS) method, our attack maintains an ASR over 94%, surpassing existing attacks by more than 7%. Copyright © 2025, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Noise-enhanced graph contrastive learning for multimodal recommendation systems

引用

Knowledge-Based systems 2025年 324卷

作者： Ke Shi Yan Zhang Miao Zhang Kui Xiao Xiaoju Hou Zhifei Li School of Computer Science Hubei University Wuhan 430062 China Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 China Hubei Key Laboratory of Big Data Intelligent Analysis and Application (Hubei University) Wuhan 430062 China Institute of Vocational Education Guangdong Industry Polytechnic University Guangzhou 510300 China

Multimodal recommendation systems enhance recommendation accuracy through the fusion of different types of information. Graph Contrastive Learning (GCL) has recently been widely applied in recommendation systems. However, the application of GCL mainly focuses on general user–item interactions, and few models apply it to multimodal information learning. This limitation may hinder the full potential of GCL in more complex multimodal scenarios. To address this issue, we propose a N oise- E nhanced G raph C ontrastive L earning for Multimodal Recommendation systems (NEGCL). As different data augmentation strategies yield distinct outcomes in GCL, we have examined their relative strengths and weaknesses. Introducing innovative contrastive learning into the multimodal information extraction process helps address the limitations of this method in multimodal recommendation, supplemented by an improved transformer for learning in general interactions. A longitudinal comparison of contrastive learning across different methods reveals that noise-based contrastive learning substantially reduces the additional overhead potentially introduced by data augmentation. Furthermore, the introduction of appropriate noise allows contrastive learning to develop more robust nodes. Extensive experiments on three public datasets reveal that NEGCL surpasses previous benchmark models, achieving performance improvements ranging from 8.46% to 11.62% on the Clothing dataset. The source code is publicly available at https://***/HubuKG/NEGCL .

关键词：

来源：评论

学校读者我要写书评

暂无评论

Poisoning as a Post-Protection: Mitigating Membership Privacy Leakage From Gradient and Prediction of Federated Models

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Liu, Gaoyang Xu, Tianlong Yang, Yang Abdelmoniem, Ahmed M. Wang, Chen Liu, Jiangchuan Huazhong University of Science and Technology Hubei Key Laboratory of Internet of Intelligence School of Electronic Information and Communications Wuhan430074 China Simon Fraser University School of Computing Science BurnabyBCV5A 1S6 Canada Ministry of Education Key Laboratory of Intelligent Sensing System and Security China Hubei University School of Artificial Intelligence Wuhan430062 China Queen Mary University of London School of Electronic Engineering and Computer Science United Kingdom

Federated learning (FL) is a distributed learning paradigm that enables multiple clients to train a unified model without sharing their private data. However, recent works demonstrate that FL models are vulnerable to membership inference attacks (MIAs), which can infer whether a data sample was used to train a given FL model. Existing countermeasures either require far-reaching modifications of FL training process or enforce extra processing in prediction phase, yielding them unlikely to be applied well in practice. In this paper, we design a post-protection mechanism, dubbed P2-Protection, which degrades the inference performance of MIAs by simultaneously poisoning the prediction and gradient of the target FL model to reduce the privacy leakage of training data while keeping the model prediction accuracy. P2-Protection only involves one additional training round to embed the poisoned prediction and gradient into the target FL model, without requiring model retraining or training process modification. We evaluate P2-Protection and compare it with two state-of-the-art defenses against three MIAs on five realistic datasets. Experimental results show that P2-Protection outperforms the existing defenses by offering limited implement overhead and improved utility-privacy trade-off. © 2004-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Cross-Domain Alignment Network for Video Moment Retrieval

arXiv

引用

arXiv 2022年

作者： Fang, Xiang Liu, Daizong Zhou, Pan Hu, Yuchong Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Hubei Wuhan430074 China Wangxuan Institute of Computer Technology Peking University No. 128 Zhongguancun North Street Beijing China School of Computer Science and Technology Key Laboratory of Information Storage System Ministry of Education of China Huazhong University of Science and Technology Wuhan430074 China

As an increasingly popular task in multimedia information retrieval, video moment retrieval (VMR) aims to localize the target moment from an untrimmed video according to a given language query. Most previous methods depend heavily on numerous manual annotations (i.e., moment boundaries), which are extremely expensive to acquire in practice. In addition, due to the domain gap between different datasets, directly applying these pre-trained models to an unseen domain leads to a significant performance drop. In this paper, we focus on a novel task: cross-domain VMR, where fully-annotated datasets are available in one domain ("source domain"), but the domain of interest ("target domain") only contains unannotated datasets. As far as we know, we present the first study on cross-domain VMR. To address this new task, we propose a novel Multi-Modal Cross-Domain Alignment (MMCDA) network to transfer the annotation knowledge from the source domain to the target domain. However, due to the domain discrepancy between the source and target domains and the semantic gap between videos and queries, directly applying trained models to the target domain generally leads to a performance drop. To solve this problem, we develop three novel modules: (i) a domain alignment module is designed to align the feature distributions between different domains of each modality;(ii) a cross-modal alignment module aims to map both video and query features into a joint embedding space and to align the feature distributions between different modalities in the target domain;(iii) a specific alignment module tries to obtain the fine-grained similarity between a specific frame and the given query for optimal localization. By jointly training these three modules, our MMCDA can learn domain-invariant and semantic-aligned cross-modal representations. Extensive experiments on three challenging benchmarks (ActivityNet Captions, Charades-STA and TACoS) illustrate that our cross-domain method MMCDA outperforms a

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Dual topology and versatile Rashba-split surface state configurations in 2M−WS2 and 2M−WSe2

引用

Physical Review B 2025年第11期111卷 115151-115151页

作者： Lixuan Xu Yuqiang Fang Fuqiang Huang Shihao Zhang Shiheng Liang Yulin Chen Lexian Yang Zhongkai Liu Nan Xu Department of Physics Hubei University Wuhan 430062 China Key Laboratory of Intelligent Sensing System and Security (Hubei University) Ministry of Education Wuhan 430062 China School of Materials Science and Engineering Shanghai Jiao Tong University Shanghai 200240 China School of Physics and Electronics Hunan University Changsha 410082 China School of Physical Science and Technology ShanghaiTech University Shanghai 201210 China ShanghaiTech Laboratory for Topological Physics Shanghai 201210 China Department of Physics University of Oxford Oxford OX1 3PU United Kingdom State Key Laboratory of Low Dimensional Quantum Physics Department of Physics Tsinghua University Beijing 100084 China Institute for Advanced Studies (IAS) Wuhan University Wuhan 430072 China Wuhan Institute of Quantum Technology Wuhan 430206 China

The 2M-phase transition metal dichalcogenides have recently attracted intensive research interest due to their rich topological and superconducting phase diagrams. Apart from the topological surface states of 2M−WS2 near Γ that originated from the strong topological order, using angle-resolved photoemission spectroscopy, we discover additional Rashba-split states on the surfaces of both 2M−WS2 and 2M−WSe2, which extend in large momentum-energy regions. First-principles calculations well reproduce these states and attribute them to the weak topological orders. The calculations further indicate that the surface state connecting configurations are tunable under moderate pressure, suggesting that 2M−WS2 and WSe2 are promising platforms to study topological phase transition and explore topological superconductivity.

关键词： Photoacoustic spectroscopy

来源：评论

学校读者我要写书评

暂无评论

EC²Detect: Real-Time Online Video Object Detection in Edge-Cloud Collaborative IoT

引用

IEEE Internet of Things Journal 2022年第20期9卷 20382-20392页

作者： Siyan Guo Cong Zhao Guiqin Wang Jiaqing Yang Shusen Yang National Engineering Laboratory for Big Data Analytics and the School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China Department of Computing Imperial College London London U.K. National Engineering Laboratory for Big Data Analytics and the School of Computer Science and Technology Xi’an Jiaotong University Xi’an China School of Mathematics and Statistics Xi’an Jiaotong University Xi’an China National Engineering Laboratory for Big Data Analytics and Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an Jiaotong University Xi’an China Industrial Artificial Intelligence Center Pazhou Laboratory Guangzhou China

Video object detection is a fundamental technology of intelligent video analytics for Internet of Things (IoT) applications. However, even with extraordinary detection accuracy, predominating solutions based on deep convolutional neural networks (DCNNs) cannot achieve real-time online object detection on video streams with a low end-to-end (E2E) response latency and therefore cannot be applied to proliferating latency-sensitive IoT applications like autonomous driving requiring large-scale intelligent video analytics. To address this issue, we present EC2Detect, an edge-cloud collaborative real-time online video object detection method. Specifically, we propose a tracking-assisted object detection architecture based on edge-cloud collaboration with keyframe selection, where the accurate but heavy object detection is conducted by the Cloud on sparse keyframes adaptively selected according to their semantic variation, and the lightweight object tracking is used to localize and identify objects in other frames at edge devices. Extensive experiments of our real-world prototype demonstrate that, EC2Detect significantly outperforms state-of-the-art methods in terms of processing speed (up to $4.77\times $ faster), E2E latency (up to $8.12 \times $ lower), and edge-cloud bandwidth occupation ( $17 \times $ lower) with an acceptable mAP, which can effectively support large-scale intelligent video analytics in practice. Source code of EC2Detect is available at https://***/ECCDetect/ECCDetect .

关键词： Object detection Image edge detection Streaming media Internet of Things Collaboration Visual analytics Feature extraction

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：