检索结果-内蒙古大学图书馆

DeepSolo++: Let Transformer Decoder with Explicit Points Solo for Multilingual Text Spotting

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ye, Maoyuan Zhang, Jing Zhao, Shanshan Liu, Juhua Liu, Tongliang Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computer Science Faculty of Engineering The University of Sydney Australia JD Explore Academy *** China College of Computing & Data Science Nanyang Technological University Singapore

End-to-end text spotting aims to integrate scene text detection and recognition into a unified framework. Dealing with the relationship between the two sub-tasks plays a pivotal role in designing effective spotters. Although Transformer-based methods eliminate the heuristic post-processing, they still suffer from the synergy issue between the sub-tasks and low training efficiency. Besides, they overlook the exploring on multilingual text spotting which requires an extra script identification task. In this paper, we present DeepSolo++, a simple DETR-like baseline that lets a single Decoder with Explicit Points Solo for text detection, recognition, and script identification simultaneously. Technically, for each text instance, we represent the character sequence as ordered points and model them with learnable explicit point queries. After passing a single decoder, the point queries have encoded requisite text semantics and locations, thus can be further decoded to the center line, boundary, script, and confidence of text via very simple prediction heads in parallel. Furthermore, we show the surprisingly good extensibility of our method, in terms of character class, language type, and task. On the one hand, our method not only performs well in English scenes but also masters the transcription with complex font structure and a thousand-level character classes, such as Chinese. On the other hand, our DeepSolo++ achieves better performance on the additionally introduced script identification task with a simpler training pipeline compared with previous methods. Extensive experiments on public benchmarks demonstrate that our simple approach achieves better training efficiency compared with Transformer-based models and outperforms the previous state-of-the-art. For example, on ICDAR 2019 ReCTS for Chinese text, our method boosts the 1-NED metric to a new record of 78.3%. On ICDAR 2019 MLT, DeepSolo++ achieves absolute 5.5% H-mean and 8.0% AP improvements on joint detection an

关键词： Semantics

Robust and Unsupervised KPI Anomaly Detection Based on Highly Sensitive Conditional Variational Auto-Encoders

学校读者我要写书评

暂无评论

Robust and Unsupervised KPI Anomaly Detection Based on Highl...

IEEE International Conference on Big Data and Cloud computing (BdCloud)

作者： Shili Yan Bing Tang Qing Yang Yijia He Xiaoyuan Zhang Hunan Key Laboratory for Service Computing and Novel Software Technology School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China School of Information and Communication Engineering Guangzhou Maritime University Guangzhou China Beijing Jiaotong University Beijing China

To ensure the stability and reliability of service quality, large Internet companies need to closely monitor various KPIs (key Performance Indicators, such as network throughput, CPU usages) and trigger timely troubleshooting or mitigation when any anomaly occurs. However, the diversity and complexity of anomalies bring great challenges to this work, especially when there is no manual label and low delay is required. In this paper, we propose HS-VAE (Highly Sensitive Variational Auto-Encoders), an unsupervised, robust algorithm based on CVAE (Conditional Variational Auto-Encoders) with high sensitivity to anomalies for KPIs, which contains mainly 3 parts: a simple but important data filter before training, improved conditional VAE with two dropout layers and adjusted anomaly detection method based on reconstruction probability. Our experiments using real-world data show that, HS-VAE's best F1-score ranges from 0.91 to 0.98. In addition, HS- VAE is excellent in sensitivity to anomaly and works well even with low latency requirements.

关键词： Training Sensitivity key performance indicator Training data Manuals Throughput Reliability

Hi-SAM: Marrying Segment Anything Model for Hierarchical Text Segmentation

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ye, Maoyuan Zhang, Jing Liu, Juhua Liu, Chenyu Yin, Baocai Liu, Cong Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China IFLYTEK Research IFLYTEK CO. LTD. China College of Computing & Data Science Nanyang Technological University #32 Block N4 #02a-014 50 Nanyang Avenue 639798 Singapore

The Segment Anything Model (SAM), a profound vision foundation model pretrained on a large-scale dataset, breaks the boundaries of general segmentation and sparks various downstream applications. This paper introduces Hi-SAM, a unified model leveraging SAM for hierarchical text segmentation. Hi-SAM excels in segmentation across four hierarchies, including pixel-level text, word, text-line, and paragraph, while realizing layout analysis as well. Specifically, we first turn SAM into a high-quality pixel-level text segmentation (TS) model through a parameter-efficient fine-tuning approach. We use this TS model to iteratively generate the pixel-level text labels in a semi-automatical manner, unifying labels across the four text hierarchies in the HierText dataset. Subsequently, with these complete labels, we launch the end-to-end trainable Hi-SAM based on the TS architecture with a customized hierarchical mask decoder. During inference, Hi-SAM offers both automatic mask generation (AMG) mode and promptable segmentation (PS) mode. In the AMG mode, Hi-SAM segments pixel-level text foreground masks initially, then samples foreground points for hierarchical text mask generation and achieves layout analysis in passing. As for the PS mode, Hi-SAM provides word, text-line, and paragraph masks with a single point click. Experimental results show the state-of-the-art performance of our TS model: 84.86% fgIOU on Total-Text and 88.96% fgIOU on TextSeg for pixel-level text segmentation. Moreover, compared to the previous specialist for joint hierarchical detection and layout analysis on HierText, Hi-SAM achieves significant improvements: 4.73% PQ and 5.39% F1 on the text-line level, 5.49% PQ and 7.39% F1 on the paragraph level layout analysis, requiring 20× fewer training epochs. The code is available at Hi-SAM. Copyright © 2024, The Authors. All rights reserved.

关键词： Masks

Noncontact Doppler Radar-based Heart Rate Detection on the SVD and ANC

学校读者我要写书评

暂无评论

Noncontact Doppler Radar-based Heart Rate Detection on the S...

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Shi, Qiuxia Hu, Bin Tian, Fuze Zhao, Qinglin Gansu Provincial Key Laboratory of Wearable Computing School of Information Science and Engineering Lanzhou University China School of Computer and Communication Lanzhou University of Technology China Key Laboratory of Special Functional Materials and Structural Design Lanzhou University Ministry of Education Lanzhou China CAS Center for Excellence in Brain Science and Intelligence Technology Shanghai Institutes for Biological Sciences Chinese Academy of Sciences China Joint Research Center for Cognitive Neurosensor Technology of Lanzhou University Institute of Semiconductors Chinese Academy of Sciences China Engineering Research Center of Open Source Software and Real-Time System Lanzhou University Ministry of Education China

ISBN: (纸本)9781665468190

In the Doppler biological radar-based applications of noncontact measurement of vital signs, effectively extracting heartbeat information from weak thoracic mechanical motion is an important problem to be solved. This study is aimed at extracting heartbeat signal via the technology combined with Short Time Fourier Transform (STFT), Singular Value Decomposition (SVD) and Adaptive Noise Canceller (ANC) from radar recording. The simulated data and the data collected by Doppler radar biosensor realized in laboratory are employed to validate the proposed method. The results show that the proposed method has the ability of detection for the heart rate and heart rate variability indexes in rest state, it has certain advantages in time-consuming and detection accuracy. Therefore, the current method provides another way to process vital sign signals recorded by Doppler radar. © 2022 IEEE.

关键词： Singular value decomposition

Hidden Follower Detection via Refined Gaze and Walking State Estimation

学校读者我要写书评

暂无评论

Hidden Follower Detection via Refined Gaze and Walking State...

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yaxi Chen Ruimin Hu Danni Xu Zheng Wang Linbo Luo Dengshi Li National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan China School of Computing the National University of Singapore Singapore School of Cyber Engineering Xidian University Xi’an China School of Artificial Intelligence Jianghan University Wuhan China

Hidden following is following behavior with special intentions, and detecting hidden following behavior can prevent many criminal activities in advance. The previous method uses gaze and spacing behaviors to distinguish hidden followers from normal pedestrians. However, they express gaze behaviors in a coarse-grained way with binary values, making it difficult to accurately depict the gaze state of pedestrians. To this end, we propose the Refined Hidden Follower Detection (RHFD) model by choosing a suitable mapping function based on the principle that the closer the gaze direction is to someone, the more likely it is to gaze at someone, which converts the gaze direction into a continuous estimated gaze state representing the complex and variable gaze behavior of pedestrians. Simultaneously, we introduce variations in the magnitude and direction of pedestrian velocity to refine the representation of pedestrian walking states. Experimental results on the surveillance dataset show that RHFD outperforms state-of-the-art methods.

关键词：

DarkSAM: fooling segment anything model to segment nothing 24

学校读者我要写书评

暂无评论

DarkSAM: fooling segment anything model to segment nothing

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Ziqi Zhou Yufei Song Minghui Li Shengshan Hu Xianlong Wang Leo Yu Zhang Dezhong Yao Hai Jin National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Cluster and Grid Computing Lab and School of Computer Science and Technology Huazhong University of Science and Technology School of Cyber Science and Engineering Huazhong University of Science and Technology School of Software Engineering Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System and Services Computing Technology and System Lab and Hubei Engineering Research Center on Big Data Security and Hubei Key Laboratory of Distributed System Security and School of Cyber Science and Engineering Huazhong University of Science and Technology School of Information and Communication Technology Griffith University

ISBN: (纸本)9798331314385

Segment Anything Model (SAM) has recently gained much attention for its outstanding generalization to unseen data and tasks. Despite its promising prospect, the vulnerabilities of SAM, especially to universal adversarial perturbation (UAP) have not been thoroughly investigated yet. In this paper, we propose DarkSAM, the first prompt-free universal attack framework against SAM, including a semantic decoupling-based spatial attack and a texture distortion-based frequency attack. We first divide the output of SAM into foreground and background. Then, we design a shadow target strategy to obtain the semantic blueprint of the image as the attack target. DarkSAM is dedicated to fooling SAM by extracting and destroying crucial object features from images in both spatial and frequency domains. In the spatial domain, we disrupt the semantics of both the foreground and background in the image to confuse SAM. In the frequency domain, we further enhance the attack effectiveness by distorting the high-frequency components (i.e., texture information) of the image. Consequently, with a single UAP, DarkSAM renders SAM incapable of segmenting objects across diverse images with varying prompts. Experimental results on four datasets for SAM and its two variant models demonstrate the powerful attack capability and transferability of DarkSAM. Our codes are available at: https://***/CGCL-codes/DarkSAM.

关键词：

Socially Beneficial Metaverse: Framework, Technologies, Applications, and Challenges

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xu, Xiaolong Zhou, Xuanhong Bilal, Muhammad Zeadally, Sherali Crowcroft, Jon Qi, Lianyong Xue, Shengjun Nanjing University of Information Science and Technology Nanjing China School of Software Nanjing University of Information Science and Technology Nanjing China School of Computing and Communications Lancaster University Lancaster United Kingdom College of Communication and Information University of Kentucky Lexington United States Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom State Key Laboratory for Novel Software Technology Nanjing University China School of Computer Science and Technology Silicon Lake College Suzhou China

In recent years, the maturation of emerging technologies such as Virtual Reality, Digital Twin,s and Blockchain has accelerated the realization of the metaverse. As a virtual world independent of the real world, the metaverse will provide users with a variety of virtual activities which bring great convenience to society. In addition, the metaverse can facilitate digital twins, which offers transformative possibilities for the industry. Thus, the metaverse has attracted the attention of the industry, and a huge amount of capital is about to be invested. However, the development of the metaverse is still in its infancy and little research has been undertaken so far. We describe the development of the metaverse. Next, we introduce the architecture of the socially beneficial metaverse (SB-Metaverse) and we focus on the technologies that support the operation of SB-Metaverse. In addition, we also present the applications of SB-Metaverse. Finally, we discuss several challenges faced by SB-Metaverse which must be addressed in the *** Codes 68U01, 68M11, 68U35 © 2023, CC BY.

关键词： Blockchain

Reversible Data Hiding With Secret Encrypted Image Sharing and Adaptive Coding

学校读者我要写书评

暂无评论

IEEE Internet of Things Journal 2025年

作者： Fang, Guangtian Wang, Feng Zhao, Chenbin Qin, Chuan Chang, Ching-Chun Chang, Chin-Chen Fujian University of Technology College of Computer Science and Mathematics Fuzhou350118 China Fujian University of Technology College of Computer Science and Mathematics Key Laboratory of Big Data Mining and Applications Fuzhou350118 China Monash University Faculty of IT Department of Software Systems and Cybersecurity VIC3800 Australia Ministry of Education School of Cyber Science and Engineering Key Laboratory of Aerospace Information Security and Trusted Computing Wuhan430072 China University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Feng Chia University Information and Communication Security Research Center Taichuang 40724 Taiwan Feng Chia University Department of Information Engineering and Computer Science Taichung40724 Taiwan

To ensure the security of image information and facilitate efficient management in the cloud, the utilization of reversible data hiding in encrypted images (RDHEI) has emerged as pivotal. However, most existing RDHEI schemes suffer from lower security and limited embedding capacity. To tackle these challenges, we propose a reversible data hiding with secret encrypted image sharing and adaptive coding scheme. Specifically, in the encryption phase, we introduce an improved secret sharing (SS) encryption method based on the chinese remainder theorem for polynomials (CRTP). This method not only improves the security of encrypted images but also vacates a larger room for embedding. In the embedding phase, we introduce an adaptive coding embedding approach using XOR preservation (XORP) and huffman coding, which provides high embedding capacity. Experimental results and security analysis demonstrate that our proposed encryption method achieves optimal values in security indicators for encrypted images, such as information entropy, histograms, NPCR and UACI. The proposed embedding method is superior to some state-of-the-art schemes in terms of embedding capacity. Furthermore, in datasets BOSSBase and BOWS2, the average embedding rates of the proposed embedding approach can reach 2.1745 bpp and 2.0656 bpp, respectively. © 2025 IEEE.

关键词： adaptive coding chinese remainder theorem for polynomials encrypted images Reversible data hiding secret sharing

Securely Fine-tuning Pre-trained Encoders Against Adversarial Examples

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zhou, Ziqi Li, Minghui Liu, Wei Hu, Shengshan Zhang, Yechao Wan, Wei Xue, Lulu Zhang, Leo Yu Yao, Dezhong Jin, Hai National Engineering Research Center for Big Data Technology and System China Services Computing Technology and System Lab. China Cluster and Grid Computing Lab. China Hubei Engineering Research Center on Big Data Security China Hubei Key Laboratory of Distributed System Security China School of Computer Science and Technology Huazhong University of Science and Technology China School of Software Engineering Huazhong University of Science and Technology China School of Cyber Science and Engineering Huazhong University of Science and Technology China School of Information and Communication Technology Griffith University Australia

With the evolution of self-supervised learning, the pre-training paradigm has emerged as a predominant solution within the deep learning landscape. Model providers furnish pre-trained encoders designed to function as versatile feature extractors, enabling downstream users to harness the benefits of expansive models with minimal effort through fine-tuning. Nevertheless, recent works have exposed a vulnerability in pre-trained encoders, highlighting their susceptibility to downstream-agnostic adversarial examples (DAEs) meticulously crafted by attackers. The lingering question pertains to the feasibility of fortifying the robustness of downstream models against DAEs, particularly in scenarios where the pre-trained encoders are publicly accessible to the attackers. In this paper, we initially delve into existing defensive mechanisms against adversarial examples within the pre-training paradigm. Our findings reveal that the failure of current defenses stems from the domain shift between pre-training data and downstream tasks, as well as the sensitivity of encoder parameters. In response to these challenges, we propose Genetic Evolution-Nurtured Adversarial Fine-tuning (Gen-AF), a two-stage adversarial fine-tuning approach aimed at enhancing the robustness of downstream models. Gen-AF employs a genetic-directed dual-track adversarial fine-tuning strategy in its first stage to effectively inherit the pre-trained encoder. This involves optimizing the pre-trained encoder and classifier separately while incorporating genetic regularization to preserve the model’s topology. In the second stage, Gen-AF assesses the robust sensitivity of each layer and creates a dictionary, based on which the top-k robust redundant layers are selected with the remaining layers held fixed. Upon this foundation, we conduct evolutionary adaptability fine-tuning to further enhance the model’s generalizability. Our extensive experiments, conducted across ten self-supervised training methods and six

关键词： Topology