检索结果-内蒙古大学图书馆

17th Asian Conference on Computer Vision, ACCV 2024

作者： Ma, Jing Xiang, Xiang He, Yan National Key Lab of Multi-Spectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9789819609161

Few-shot Font Generation (FFG) is a practical technology widely used in designing artistic characters, handwriting imitation, and identification, etc., which aims to generate realistic font images with a few reference samples. Typically, convolutional neural networks (CNNs) are employed to learn the representations of style and content from the font images. However, owing to the locality of convolutional operations, CNNs are not good at capturing the global structure of fonts, which leads to the generated images with blurry components and distorted space layouts. To address this problem, we consider cascading self-attention modules to exploit long-range dependencies for font generation and propose a transformer-based approach called FGTr. Following the style-content disentanglement paradigm, FGTr contains two different transformer encoders to extract the style and content sequences. A multi-layer transformer decoder is adopted to merge the two sequences and generate target images. In order to smoothen the transition of patch edges, we utilize a Local Self-Attention Mask (LSAM) to restrict the attention scope of each patch to a fixed-size sliding window, which plugs into the Transformer with no extra parameters. We also propose an Auxiliary Generation Module (AGM) in favor of generating glyphs closer to the real. Extensive experiments demonstrate the effectiveness and superiority of our method compared with state-of-the-art CNN-based models. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

GPS: graph contrastive learning via multi-scale augmented views from adversarial pooling

引用

science China(information sciences) 2025年第1期68卷 145-158页

作者： Wei JU Yiyang GU Zhengyang MAO Ziyue QIAO Yifang QIN Xiao LUO Hui XIONG Ming ZHANG School of Computer Science National Key Laboratory for Multimedia Information ProcessingPeking University Artificial Intelligence Thrust The Hong Kong University of Science and Technology Department of Computer Science University of California

Self-supervised graph representation learning has recently shown considerable promise in a range of fields, including bioinformatics and social networks. A large number of graph contrastive learning approaches have shown promising performance for representation learning on graphs, which train models by maximizing agreement between original graphs and their augmented views(i.e., positive views). Unfortunately, these methods usually involve pre-defined augmentation strategies based on the knowledge of human experts. Moreover, these strategies may fail to generate challenging positive views to provide sufficient supervision signals. In this paper, we present a novel approach named graph pooling contrast(GPS) to address these *** by the fact that graph pooling can adaptively coarsen the graph with the removal of redundancy, we rethink graph pooling and leverage it to automatically generate multi-scale positive views with varying emphasis on providing challenging positives and preserving semantics, i.e., strongly-augmented view and weakly-augmented view. Then, we incorporate both views into a joint contrastive learning framework with similarity learning and consistency learning, where our pooling module is adversarially trained with respect to the encoder for adversarial robustness. Experiments on twelve datasets on both graph classification and transfer learning tasks verify the superiority of the proposed method over its counterparts.

关键词： graph representation learning graph neural networks graph contrastive learning graph augmentations graph pooling

来源：评论

学校读者我要写书评

暂无评论

IIIM-SAM: Zero-Shot Texture Anomaly Detection Without External Prompts

引用

IEEE Transactions on Automation science and Engineering 2025年 22卷 14610-14622页

作者： Zhang, Zhe Zhou, Yuhang Yue, Jiahe Zhang, Runchu Ma, Jie Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Wuhan430074 China

Anomaly detection is a crucial aspect in ensuring the reliability of industrial products in smart manufacturing. Despite employing unsupervised anomaly detection methods to mitigate the challenges associated with obtaining defect data, there remains the challenge of adapting anomaly detectors to drift within normal data distributions, especially when there are significant intra-class variations in normal samples. Consequently, zero-shot anomaly detection techniques, which do not require training data and thus avoid interference from training data, have emerged as a new research direction. Meanwhile, the zero-shot segmentation capability demonstrated by the Segment Anything Mode (SAM) visual foundation model has further fueled our research enthusiasm. In this paper, we focus on texture images and propose a no-external prompt SAM-based method for zero-shot texture anomaly detection, called Image Internal information Mining SAM (IIIM-SAM). We utilize the Image Internal information Mining Prompter to mine relationships between internal regions of the image, identifying specific background and potential defect points. The two types of prompt points are fed into the SAM model in different stages, imparting the SAM with incorporating category information segmentation capability. Unlike current methods, our zero-shot texture anomaly detection method requires no external prompts or expert knowledge, and also avoids the uncertainty introduced by text prompts necessary for CLIP-based approaches. Our experimental results demonstrate the superiority of our zero-shot texture anomaly detection method compared to other approaches. Specifically, in the texture subset of MVTecAD/KolektorSDD2, our IIIM-SAM achieves 99.2%/93.6% image-level AUROC and 98.6%/92.3% pixel-level AUROC. © 2004-2012 IEEE.

关键词： Smart manufacturing

来源：评论

学校读者我要写书评

暂无评论

Learning Visual-Semantic Hierarchical Attribute Space for Interpretable Open-Set Recognition

Learning Visual-Semantic Hierarchical Attribute Space for In...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Xu, Zhuo Xiang, Xiang School of Artificial Intelligence and Automation Huazhong University of Science and Technology National Key Lab of Multi-Spectral Information Intelligent Processing Technology Wuhan China Peng Cheng Lab China

ISBN: (纸本)9798331510831

In the field of open-set recognition, conventional models often focus on addressing challenges within a single hierarchical category, and these methods frequently lack inter-pretability. In this paper, we propose a novel solution that utilizes attributes and hierarchical relationships to achieve interpretable open-set recognition. Our method is centered around the visual-semantic attribute space. By leveraging hierarchy division, we can decompose the attributes into more granular components, thereby yielding additional performance improvements. When confronted with an unfamiliar object, our method not only classifies it as an unknown category but also provides insights into the broader category and its associated attributes. This capability enhances interpretability by offering valuable information regarding the potential category and characteristics of the object. Experimental results demonstrate great performance improvements compared to existing methods. © 2025 IEEE.

关键词： Hierarchical systems

来源：评论

学校读者我要写书评

暂无评论

From First-Order to Second-Order Rationality: Advancing Game Convergence with Dynamic Weighted Fictitious Play 21st

From First-Order to Second-Order Rationality: Advancing Gam...

引用

21st Pacific Rim International Conference on Artificial Intelligence, PRICAI 2024

作者： Ju, Qi Hei, Falin Liu, Yuxuan Fang, Zhemei Luo, Yunfeng Huazhong University of Science and Technology Wuhan China National Key Laboratory of Science and Technology on Multispectral Information Processing Wuhan China

ISBN: (纸本)9789819601271

Constructing effective algorithms to converge to Nash Equilibrium (NE) is a important problem in algorithmic game theory. Prior research generally posits that the upper bound on the convergence rate for games is OT-1/2. This paper introduces a novel perspective, positing that the key to accelerating convergence in game theory is "rationality". Based on this concept, we propose a Dynamic Weighted Fictitious Play (DW-FP) algorithm. We demonstrate that this algorithm can converge to a NE and exhibits a convergence rate of O(T-1) in experimental evaluations. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Consensus algorithm

来源：评论

学校读者我要写书评

暂无评论

A novel active-passive protection strategy endows carbonyl iron with excellent intelligent anti-corrosion and microwave absorption dual functional characteristics

引用

Nano Research 2025年第1期18卷 487-500页

作者： Wei Tian Quanyuan Feng Linbo Zhang Yinfan Liu Xian Jian Longjiang Deng Institute of Microelectronics School of Information Science and TechnologySouthwest Jiaotong UniversityChengdu 611756China National Engineering Researching Centre of Electromagnetic Radiation Control Materials Key Laboratory of Multi-Spectral Absorbing Materials and Structures of Ministry of EducationState Key Laboratory of Electronic Thin Films and Integrated DevicesSchool of Electronic Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengdu 611731China School of Materials and Energy University of Electronic Science and Technology of ChinaChengdu 611731China The Yangtze Delta Region Institute(Huzhou)&School of Electronic Science and Engineering University of Electronic Science and Technology of ChinaHuzhou 313001China

Carbonyl iron absorbers(CI)face significant challenges in practical applications,such as corrosion,interface bonding failure,detachment,and high maintenance ***,we have developed intelligent self-healing technology based on proactive/passive mechanisms via in situ synthesis of self-healing factors(polydopamine/benzotriazole(PDA/BTA))and physical barrier layers(SiO_(2)/1,1,1,3,3,3-hexamethyl disilazane,SiO_(2)/HMDS)to enhance corrosion resistance,while also being compatible with efficient microwave absorption *** unique multiscale structure gives full play to the utilization of the roles of each functional layer,including the intelligent self-healing features of PDA/BTA,physical shielding and spatial confinement characteristics of SiO_(2)/HMDS,and magnetic-dielectric synergistic mechanism resulted from the good impedance matching characteristics,the conduction loss,the interfacial polarization loss and natural *** asfabricated composites achieved an exceptional minimum reflection loss value of-55.4 dB at 10.7 GHz and the effective absorption band of 7.6 ***,it still exhibits obvious self-healing and corrosion resistance characteristics after 360 h corrosion treatment,ascribed to the self-healing mechanism of PDA/BTA and the blocking intervention effect of SiO_(2)/*** work is considered to pave the way for the synthesis of high-performance magnetic absorbers,especially in enhancing their intelligent self-healing ability in corrosive environments.

关键词： microwave absorption intelligent self-healing technology carbonyl iron multiscale structure magneticdielectric synergistic mechanism

来源：评论

学校读者我要写书评

暂无评论

Pixel-Level multidirectional Image Sharpness Linear Assessment for Optical Image Stabilizer Performance Monitoring

引用

IEEE Sensors Journal 2025年第9期25卷 15204-15215页

作者： Zhou, Yuhang Zhang, Zhe Yang, Bokang Ma, Jie Huazhong University of Science and Technology National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Wuhan430074 China Huazhong University of Science and Technology China-EU Institute for Clean and Renewable Energy Wuhan430074 China

Linear quantification of blur intensity in different directions of an image and blur-type classification are crucial for the detection of anomalies and optimization calibration of widely used optical image stabilizer (OIS). However, previous image quality assessment methods mainly focused on isotropic blur, emphasizing the correlation with subjective ratings, making it difficult to provide multidirectional linear sharpness assessment. Moreover, they invariably offer a single evaluation score regardless of the kind of fuzziness. In this article, we propose a pixel-level multidirectional image sharpness (PMIS) linear assessment method that, to our knowledge, is the first to provide the capability to linearly quantify blur across multiple directions and distinguish blur types in an end-to-end manner while assessing the degree of image blur. We introduce a novel method for extracting edge information to characterize image blur, significantly enhancing correlation with the human visual system (HVS) in blur perception by filtering out high-frequency edge noise. Uniform edge block selection and data postprocessing are introduced to adapt to HVS characteristics and enhance robustness. Using blur results from four different directions and simply setting thresholds, we are able to achieve an 84.5% classification accuracy in distinguishing between defocus blur, motion blur, and clear images. In addition, we creatively make a motion blur image quality (MBIQ) database, accurately representing motion blur through the concrete physical quantity of rotational speed. Experimental results confirm that PMIS achieves significant improvements over the previous methods especially on databases with anisotropic motion blur. © 2025 IEEE.

关键词： information filtering

来源：评论

学校读者我要写书评

暂无评论

Self-distilled Dual-Network with Pixel Screening Loss for Blind Image Deblurring 27th

Self-distilled Dual-Network with Pixel Screening Loss for ...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Li, Tianyi Tian, Ming Gao, Changxin Sang, Nong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (纸本)9783031781247

In the field of image processing, blind image deblurring aims to restore sharp details in images blurred by an unknown convolution kernel. Recent advancements have shown that deep networks can act as effective image generative priors (DIP) for restoring clear images without requiring external datasets. However, the inherent non-uniqueness of solutions in blind image deblurring often leads DIP-based methods to converge on local optima, resulting in over- or under-deblurred images. To overcome this limitation, we propose a novel deblurring framework featuring dual image generators. These generators mutually constrain each other during training, guiding the model towards the optimal solution. Building on our network structure, we employ a self-ensemble and self-distillation strategy to guide network training, further enhancing performance. Additionally, we introduce a novel loss function based on a pixel screening method, which focuses on the important pixels. This loss enables the network to model the blur kernel more accurately and facilitates the restoration of image details. Our experiments demonstrate that our deblurring approach outperforms most existing methods both qualitatively and quantitatively. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Complementary Dual-Branch Network for Space-Time Video Super-Resolution 27th

Complementary Dual-Branch Network for Space-Time Video Supe...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Tian, Ming Li, Tianyi Luo, RongSheng Gao, Changxin Sang, Nong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

ISBN: (纸本)9783031781247

Space-time video super-resolution aims to simultaneously increase the space-time resolution of low-resolution and low frame-rate videos. Existing deep learning-based methods have made notable strides, predominantly achieving space-time video super-resolution through the relatively simple integration of modules for video super-resolution and video frame interpolation sub-tasks. However, these methods typically do not fully exploit the inherent relationships between the two sub-tasks. To address this limitation, we propose a Complementary Dual-Branch Network designed to better explore the interdependence of the two sub-tasks. Specifically, our dual-branch architecture facilitates mutual enhancement between video super-resolution and video frame interpolation sub-tasks within each branch and provides mutual guidance between the two branches. Additionally, we introduce a simple yet effective strategy for the rough estimation of optical flow, incorporating Flow-Guided Deformable Alignment into space-time video super-resolution to achieve precise motion estimation. In addition, we use an RNN-based Backward and Forward Recurrent module to ensure that all frames can utilize the information of the whole sequence. It is more efficient and memory saving compared to the currently popular bidirectional LSTM module. Experimental results on several datasets show that our method achieves superior accuracy and requires fewer parameters compared to state-of-the-art methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Learning Visual-Semantic Hierarchical Attribute Space for Interpretable Open-Set Recognition

Learning Visual-Semantic Hierarchical Attribute Space for In...

引用

IEEE Workshop on Applications of Computer Vision (WACV)

作者： Zhuo Xu Xiang Xiang National Key Lab of Multi-Spectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

关键词： Computer vision Computational modeling

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：