检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shuo Zhang Jiaming Huang Yan Wu Tao Hu Wenbing Tang Jing Liu Shanghai Key Laboratory of Trustworthy Computing East China Normal University Shanghai China Huolala Shenzhen China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Open-vocabulary semantic segmentation (OVSS) is a challenging computer vision task that labels each pixel within an image based on text descriptions. Recent advancements in OVSS are largely attributed to the increased model capacity. However, these models often struggle with unfamiliar images or unseen text, as their visual language understanding is limited to training data. Text-to-image (T2I) diffusion models have demonstrated strong image generation with diverse open-vocabulary descriptions. It prompted us to explore whether the comprehensive priors in T2I diffusion models could enhance the zero-shot generalization of OVSS. In this study, we define OVSS as a denoising diffusion task from noisy to object mask and introduce Seg-diffusion, a novel method based on Stable Diffusion that utilizes its extensive visual and linguistic prior knowledge. Specifically, the object mask diffuses from ground-truth to a random distribution in latent space. The model learns to reverse this noisy process to reconstruct object mask to segment objectives using text embeddings with our proposed Content Attention Module (CAM). Extensive experiments on popular OVSS benchmarks show that Seg-diffusion outperforms previous well-established methods and achieves impressive zero-shot generalization to unseen datasets.

关键词： Visualization Semantic segmentation Computational modeling Semantics Text to image Training data Signal processing Diffusion models Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

FragMangro: A cross-domain zero-shot model for monitoring fragmented mangrove ecosystems

引用

Journal of King Saud University - Computer and Information sciences 2025年第4期37卷 1-22页

作者： Zhang, Ruoxin An, Angela Cen, Mingcan Zhang, Chong Huangfu, Aimee Vinnakota, Sunny Song, Shuxiang Guangxi Key Laboratory of Brain-Inspired Computing and Intelligent Chips School of Electronic and Information Engineering Guangxi Normal University Guilin 541004 China Key Laboratory of Integrated Circuits and Microsystems (Guangxi Normal University) Education Department of Guangxi Zhuang Autonomous Region Guilin 541004 China Faculty of Science Engineering and Built Environment Deakin University Geelong VIC Australia Academies Australasia Polytechnic 628 Bourke Street Melbourne 3000 Australia

Monitoring fragmented mangrove ecosystems presents significant challenges due to their sparse distribution and the limitations of traditional detection methods, which often suffer from poor convergence and high rates of false positives and false negatives. To address these issues, we propose FragMangro, a cross-domain zero-shot detection model designed to enhance the accuracy and generalization of mangrove detection. FragMangro integrates parallel multi-scale convolution for progressive dimensional upscaling, improving spectral feature extraction. Additionally, it employs a dynamic learning rate and iterative control algorithm, which adaptively adjusts learning rates and training epochs based on loss monitoring to prevent suboptimal convergence. We conducted extensive experiments in three major mangrove reserves in Guangxi, China. The results demonstrate that FragMangro achieves over 98% accuracy, an average F1 Score exceeding 85%, and the Intersection over Union(IoU) surpassing 74%, significantly outperforming conventional methods such as support vector machines (SVM), random forests (RF), and k-nearest neighbors (KNN). Specifically, in the Beilun estuary, FragMangro exhibits a 0.96% improvement in accuracy over RF, a 17.24% higher F1 Score than SVM, and an 18.08% higher IoU than KNN. Furthermore, the model’s adaptive learning rate and dynamic adjustment strategy enhance convergence efficiency and feature representation. FragMangro serves as an effective tool for ecological monitoring and mangrove conservation, with broader implications for environmental protection and sustainable ecosystem management. © The Author(s) 2025.

关键词： Adaptive learning rate and iteration rounds Attention fully convolutional network Deep learning Scattered mangroves Zero-shot detection

来源：评论

学校读者我要写书评

暂无评论

AAMB: a cross-domain identity authentication scheme based on multilayered blockchains in IoMT

引用

Journal of Supercomputing 2025年第7期81卷 1-39页

作者： Zhang, Zheqing Li, Hongzhi Li, Dun Li, Kuan-Ching College of Big Data and Artificial Intelligence Chizhou University Chizhou247000 China Anhui Provincial Joint Construction Key Laboratory of Intelligent Education Equipment and Technology Chizhou247000 China Department of Industrial Engineering Tsinghua University Beijing China Department of Computer Science and Information Engineering Providence University Taichung City Taiwan

The internet of medical things (IoMT) integrates various sensors, smart devices, and fully utilizes medical data to provide high-quality medical services through the Internet of Things (IoT). Smart medical devices can be cross-domain shared in IoMT to provide health monitoring, disease diagnosis, rehabilitation training, etc. In IoMT, conventional authentication schemes struggle to meet cross-domain medical service sharing requirements due to resource constraints (computational/communication), confidentiality challenges, and strict latency demands. To address these issues, we propose a cross-domain authentication scheme based on dynamic accumulators and two-layer blockchains. First, a blockchain-based collaborative authentication framework is designed to realize secure and reliable intradomain and cross-domain authentication. Second, certificateless cryptography and dynamic accumulators are combined to guarantee both the confidentiality and efficiency of cross-domain authentication. Furthermore, we analyze the potential security threats that threaten the system’s stability and formally demonstrate the security of the proposed scheme using Burrows–Abadi–Needham logic. The formal and informal security analyses indicate that the proposed scheme is secure and can resist against known security threats. Finally, we evaluate the performance of the proposed authentication protocols in terms of computational and communication overhead. The corresponding performance analysis shows that compared with related protocols, it can reduce the computational and communication costs by more than 42.3% and 21.4%, respectively. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

AutoMiner: Reinforcement Learning-Based Mining Attack Simulator 24th

AutoMiner: Reinforcement Learning-Based Mining Attack Simula...

引用

24th International Conference on Algorithms and Architectures for Parallel Processing, ICA3PP 2024

作者： Li, Wei Xue, Lide Han, Ziyang Chen, Bingren Zhang, Xishan Zhou, Xuehai University of Science and Technology of China Hefei China ShangHai Municipal Big Data Center Shanghai China Anban Tech Co. Shanghai China State Key Laboratory of Processor Technologies Institute of Computing Technology Chinese Academy of Sciences Beijing China Cambricon Technologies Beijing China

ISBN: (纸本)9789819615247

As blockchain technology rapidly advances, it faces significant security threats from attacks like selfish mining, which exploit consensus algorithm vulnerabilities, undermining system security. Traditional analysis methods, primarily reliant on Markov models, are often utilized to address these complex threats. However, these methods frequently fall short in accurately simulating the multifaceted nature of blockchain attacks, leading to gaps in security measures. To bridge this gap, we introduce AutoMiner, an innovative reinforcement learning-based framework that integrates Miner Monte Carlo Tree Search (MMCTS) with Long Short-Term Memory (LSTM) networks for simulating and detecting potential mining attacks within the Proof of Work (PoW) framework. Our experimental results demonstrate AutoMiner’s capability to outperform traditional selfish and honest mining strategies, achieving up to 20% higher profits under specific scenarios. This highlights AutoMiner’s potential in enhancing blockchain security by providing a more comprehensive and effective approach to analyzing and mitigating mining attacks. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Blockchain Reinforcement learning Security analysis

来源：评论

学校读者我要写书评

暂无评论

POINTERGUESS: targeted password guessing model using pointer mechanism 24

POINTERGUESS: targeted password guessing model using pointer...

引用

Proceedings of the 33rd USENIX Conference on Security Symposium

作者： Kedong Xiu Ding Wang College of Cyber Science Nankai University Tianjin China and Key Laboratory of Data and Intelligent System Security (NKU) Ministry of Education Tianjin China and Tianjin Key Laboratory of Network and Data Security Technology Nankai University Tianjin China

ISBN: (纸本)9781939133441

Most existing targeted password guessing models view users' reuse behaviors as sequences of edit operations (e.g., insert and delete) performed on old passwords. These atomic edit operations are limited to modifying one character at a time and cannot fully cover users' complex password modification behaviors (e.g., modifying the password structure). This partially leads to a significant gap between the proportion of users' reused passwords and the success rates that existing targeted password models can achieve. To fill this gap, this paper models users' reuse behaviors by focusing on two key components: (1) What they want to copy/keep; (2) What they want to tweak. More specifically, we introduce the pointer mechanism and propose a new targeted guessing model, namely POINTERGUESS. By hierarchically redefining password reuse from both personal and population-wide perspectives, we can accurately and comprehensively characterize users' password reuse behaviors. Moreover, we propose MS-POINTERGUESS, which can employ the victim's multiple leaked *** employing 13 large-scale real-world password datasets, we demonstrate that POINTERGUESS is effective: (1) When the victim's password at site A (namely pwA) is known, within 100 guesses, the average success rate of POINTERGUESS in guessing her password at site B (namely pwB, pwA ≠ pwB) is 25.21% (for common users) and 12.34% (for security-savvy users), respectively, which is 21.23%~71.54% (38.37% on average) higher than its foremost counterparts; (2) When not excluding identical password pairs (i.e., pwA can equal pwB), within 100 guesses, the average success rate of POINTERGUESS is 48.30% (for common users) and 28.42% (for security-savvy users), respectively, which is 6.31%~15.92% higher than its foremost counterparts; (3) Within 100 guesses, the MS-POINTERGUESS further improves the cracking success rate by 31.21% compared to POINTERGUESS.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

Multi-Grained Feature Pruning for Video-Based Human Pose Est...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Zhigang Fan, Shaojing Liu, Zhenguang Wu, Zheqi Wu, Sifan Jiao, Yingying College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatio-temporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset. © 2025 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

TASK ARITHMETIC IN TRUST REGION: A TRAINING-FREE MODEL MERGING APPROACH TO NAVIGATE KNOWLEDGE CONFLICTS

arXiv

引用

arXiv 2025年

作者： Sun, Wenju Li, Qingyong Wang, Wen Geng, Yangli-Ao Li, Boyang Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Beijing100044 China College of Computing and Data Science Nanyang Technological University 639798 Singapore

Multi-task model merging offers an efficient solution for integrating knowledge from multiple fine-tuned models, mitigating the significant computational and storage demands associated with multi-task training. As a key technique in this field, Task Arithmetic (TA) defines task vectors by subtracting the pre-trained model (θpre) from the fine-tuned task models in parameter space, then adjusting the weight between these task vectors and θpre to balance task-generalized and task-specific knowledge. Despite the promising performance of TA, conflicts can arise among the task vectors, particularly when different tasks require distinct model adaptations. In this paper, we formally define this issue as knowledge conflicts, characterized by the performance degradation of one task after merging with a model fine-tuned for another task. Through in-depth analysis, we show that these conflicts stem primarily from the components of task vectors that align with the gradient of task-specific losses at θpre. To address this, we propose Task Arithmetic in Trust Region (TATR), which defines the trust region as dimensions in the model parameter space that cause only small changes (corresponding to the task vector components with gradient orthogonal direction) in the task-specific losses. Restricting parameter merging within this trust region, TATR can effectively alleviate knowledge conflicts. Moreover, TATR serves as both an independent approach and a plug-and-play module compatible with a wide range of TA-based methods. Extensive empirical evaluations on eight distinct datasets robustly demonstrate that TATR improves the multi-task performance of several TA-based model merging methods by an observable margin. Copyright © 2025, The Authors. All rights reserved.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

RS‐YOLOX: A High Precision Detector for Object Detection in Satellite Remote Sensing Images

arXiv

引用

arXiv 2025年

作者： Yang, Lei Yuan, Guowu Zhou, Hao Liu, Hongyu Chen, Jian Wu, Hao School of Information Science and Engineering Yunnan University Kunming650504 China Yunnan Key Laboratory of Intelligent Systems and Computing Kunming650504 China

Automatic object detection by satellite remote sensing images is of great significance for resource exploration and natural disaster assessment. To solve existing problems in remote sensing image detection, this article proposes an improved YOLOX model for satellite remote sensing image automatic detection. This model is named RS‐YOLOX. To strengthen the feature learning ability of the network, we used Efficient Channel Attention (ECA) in the backbone network of YOLOX and combined the Adaptively Spatial Feature Fusion (ASFF) with the neck network of YOLOX. To balance the numbers of positive and negative samples in training, we used the Varifocal Loss function. Finally, to obtain a high‐performance remote sensing object detector, we combined the trained model with an open‐source framework called Slicing Aided Hyper Inference (SAHI). This work evaluated models on three aerial remote sensing datasets (DOTA‐v1.5, TGRS‐HRRSD, and RSOD). Our comparative experiments demonstrate that our model has the highest accuracy in detecting objects in remote sensing image datasets. © 2025, CC BY-NC-ND.

关键词： Optical remote sensing

来源：评论

学校读者我要写书评

暂无评论

Using Depth-Enhanced Spatial Transformation for Student Gaze Target Estimation in Dual-View Classroom Images

Using Depth-Enhanced Spatial Transformation for Student Gaze...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Miao, Haonan Zhao, Peizheng Sun, Yuqi Nan, Fang Zhang, Xiaolong Wu, Yaqiang Tian, Feng School of Computer Science and Technology Xi'an Jiaotong University Xi'an710049 China Ministry of Education Key Laboratory of Intelligent Networks and Network Security Xi'an Jiaotong University Xi'an710049 China School of Advanced Technology Xi'an Jiaotong-Liverpool University Suzhou215123 China Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Xi'an Jiaotong University Xi'an710049 China

ISBN: (纸本)9798350368741

Dual-view gaze target estimation in classroom environments has not been thoroughly explored. Existing methods lack consideration of depth information, primarily focusing on 2D image information and neglecting the latent 3D spatial context, which could lead to suboptimal transformation and cause the gaze cone to intersect with an incorrect object. This paper introduces a novel dual-view gaze target estimation method tailored for classroom settings, leveraging depth-enhanced spatial transformations. By formulating a depth-enhanced 2D space, our method uses depth-enhanced spatial transformation to accurately project students' gaze cones to the teacher-oriented image. Additionally, we collected a dataset named DVSGE, specifically for student gaze target estimation in dual-view classroom images. Experimental results demonstrate significant performance improvements of 9.8% in AUC and 19.9% in L2-Distance for our method, surpassing existing methods. © 2025 IEEE.

关键词： classroom depth-enhanced 2D space dual-view gaze target estimation spatial transformation

来源：评论

学校读者我要写书评

暂无评论

Show Me Your Code! Kill Code Poisoning: A Lightweight Method Based on Code Naturalness

arXiv

引用

arXiv 2025年

作者： Sun, Weisong Chen, Yuchen Yuan, Mengzhe Fang, Chunrong Chen, Zhenpeng Wang, Chong Liu, Yang Xu, Baowen Chen, Zhenyu College of Computing and Data Science Nanyang Technological University Singapore State Key Laboratory for Novel Software Technology Nanjing University Nanjing China

Neural code models (NCMs) have demonstrated extraordinary capabilities in code intelligence tasks. Meanwhile, the security of NCMs and NCMs-based systems has garnered increasing attention. In particular, NCMs are often trained on large-scale data from potentially untrustworthy sources, providing attackers with the opportunity to manipulate them by inserting crafted samples into the data. This type of attack is called a code poisoning attack (also known as a backdoor attack). It allows attackers to implant backdoors in NCMs and thus control model behavior, which poses a significant security threat. However, there is still a lack of effective techniques for detecting various complex code poisoning attacks. In this paper, we propose an innovative and lightweight technique for code poisoning detection named KILLBADCODE. KILLBADCODE is designed based on our insight that code poisoning disrupts the naturalness of code. Specifically, KILLBADCODE first builds a code language model (CodeLM) on a lightweight n-gram language model. Then, given poisoned data, KILLBADCODE utilizes CodeLM to identify those tokens in (poisoned) code snippets that will make the code snippets more natural after being deleted as trigger tokens. Considering that the removal of some normal tokens in a single sample might also enhance code naturalness, leading to a high false positive rate (FPR), we aggregate the cumulative improvement of each token across all samples. Finally, KILLBADCODE purifies the poisoned data by removing all poisoned samples containing the identified trigger tokens. We conduct extensive experiments to evaluate the effectiveness and efficiency of KILLBADCODE, involving two types of advanced code poisoning attacks (a total of five poisoning strategies) and datasets from four representative code intelligence tasks. The experimental results demonstrate that across 20 code poisoning detection scenarios, KILLBADCODE achieves an average FPR of 8.30% and an average Recall of 100%, signif

关键词： Coding errors

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：