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

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

Infrared small target detection based on coarse-To-fine feature extraction network 12

Infrared small target detection based on coarse-To-fine feat...

引用

SPIE 12th International Symposium on multispectral Image processing and Pattern Recognition, MIPPR 2023

作者： Han, Peng Zuo, Zhengrong National Key Lab of Science and Technology on Multi-spectral Information Processing Huazhong University of Science and Technology Wuhan China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China

ISBN: (数字)9781510674943

ISBN: (纸本)9781510674936

Infrared small target detection (IRSTD) is a technique that has been developed to detect small and faint targets in cluttered backgrounds. It shows extensive use in medical diagnosis and aircraft navigation. However, due to the limited feature information and low signal-To-noise ratio, accurately detecting infrared targets and avoiding false alarms is a challenging task. Our study presents a Coarse-To-Fine Feature Extraction Network (CFFENet) for accurately classifying targets and backgrounds in blurred images. This network consists of a Two-stream Region Proposal Network (2s-RPN) and a Region Refinement Attention Network (RRAN), specifically designed to tackle the problem of false alarms. Specifically, 2s-RPN adds edge features to the RPN, in order to enable the network to extract discriminative information between targets and false alarms, so as to provide reliable coarse candidate boxes. In RRAN, firstly, attention-based encoder is used to extract the attention-Aware features in candidate boxes, and predicted mask map is output through multi-layer perception (MLP). Subsequently, the refined feature map is further processed by attention encoder, and MLP is utilized to generate the ultimate detection results. The effectiveness of our approach is validated through comparative experiment, which shows its superiority over representative state-of-The-Art IRSTD methods. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

CNS/Pulsar Integrated Navigation Using Two-level Filter

引用

Chinese Journal of Electronics 2023年第2期19卷 265-269页

作者： Jin Liu Jie Ma Jinwen Tian Key Laboratory of National Defense Science and Technology for Multi-spectral Information Processing Technologies Huazhong University of Science and Technology Wuhan China

To improve the position accuracy, a CNS (Celestial navigation system)/pulsar integrated navigation system with clock drift is proposed. In the pulsar navigation subsystem, the epoch-difference method is adopted to eliminate clock drift, but it induces colored noise. The two-level filter, which is composed of an UKF (Unscented Kalman filter) and an $\mathrm{H}_{\infty}$ filter in series connected, is proposed for fusing the data from the celestial navigation and pulsar navigation subsystems. The celestial navigation subsystem adopts the UKF because of its good performance in nonlinear estimation, while the pulsar navigation subsystem utilizes the $\mathrm{H}_{\infty}$ filter due to its robustness to colored noise. Compared with CNS and two CNS/pulsar integrated navigation methods without two-level filter, the proposed method can provide higher navigation accuracy. Simulation results show that the position estimation accuracy of the proposed method can achieve 140m in the presence of clock drift.

关键词： Navigation Simulation Estimation information filters Robustness Space exploration Kalman filters

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

Distributed Passive Sensor Trajectory Association and Fusion

Distributed Passive Sensor Trajectory Association and Fusion

引用

International Conference on Autonomous Unmanned Systems, ICAUS 2021

作者： Chang, Ruowang Wang, Bolan Xu, Shengli Cheng, Haoyu Wang, Yuehuan Huazhong University of Science and Technology Wuhan China National Key Lab of Science and Technology on Multi-spectral Information Processing Wuhan China Shanghai Electro-Mechanical Engineering Institute Shanghai201109 China Northwestern Polytechnical University Xi’an710072 China

ISBN: (纸本)9789811694912

The two key steps in the space-based optical passive tracking system are track association and fusion. The traditional distributed fusion methods are based on three-dimensional trajectory and are not suitable for the two-dimensional track association problem of passive sensors. For this reason, the probability distribution of the hinge angle difference statistic is modeled exactly in the correct and the wrong association situation. Then regarding the track association task as a two-dimensional assignment problem, we use Kuhn-Munkras algorithm to find the optimal association results of the bipartite graph. Finally, we model the target motion process and the sensor measurement process, and use UKF algorithm to fuse angular trajectories, which can accurately reconstruct the spatial position of the target. The simulation results under the STK platform show that our algorithm has favorable association and fusion performance. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Graph theory

来源：评论

学校读者我要写书评

暂无评论

Skeleton-Aware Network for Aircraft Landmark Detection 11th

Skeleton-Aware Network for Aircraft Landmark Detection

引用

11th International Conference on Image and Graphics, ICIG 2021

作者： Ye, Yuntong Chang, Yi Li, Yi Yan, Luxin National Key Laboratory of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China AI Center Pengcheng Lab Shenzhen China

ISBN: (纸本)9783030873547

The landmark detection has been widely investigated for the human pose with rapid progress in recent years. In this work, we aim at dealing with a new problem: aircraft landmark detection in the wild. We have a key observation: the aircraft is a rigid object with global structural relationships between local landmarks. This motivates us to progressively learn the global geometrical structure and local landmark localization in a coarse-to-fine guidance manner. In this paper, we propose a simple yet effective skeleton-aware landmark detection (SALD) network, including one stream for exploiting the coarse global skeleton structure and one stream for the precise local landmarks localization. The global skeleton structure models the aircraft "images" into skeleton "lines", in which the multiple skeletons of the holistic aircraft and the parts are explicitly extracted to serve as the geometrical structure constraints for landmarks. Then, the local landmark localization precisely detects the key "points" with the guidance of skeleton "lines". Consequently, the progressive strategy of "extracting lines from images, detecting points with lines" significantly eases the landmark detection task by decomposing the task into the simpler coarse-to-fine sub-tasks, thus further improving the detection performance. Extensive experimental results show the superiority of proposed method compared to state-of-the-arts. © 2021, Springer Nature Switzerland AG.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Efficient Single-Image Depth Estimation on Mobile Devices, Mobile AI & AIM 2022 Challenge: Report 17th

Efficient Single-Image Depth Estimation on Mobile Devices, ...

引用

17th European Conference on Computer Vision, ECCV 2022

作者： Ignatov, Andrey Malivenko, Grigory Timofte, Radu Treszczotko, Lukasz Chang, Xin Ksiazek, Piotr Lopuszynski, Michal Pioro, Maciej Rudnicki, Rafal Smyl, Maciej Ma, Yujie Li, Zhenyu Chen, Zehui Xu, Jialei Liu, Xianming Jiang, Junjun Shi, XueChao Xu, Difan Li, Yanan Wang, Xiaotao Lei, Lei Zhang, Ziyu Wang, Yicheng Huang, Zilong Luo, Guozhong Yu, Gang Fu, Bin Li, Jiaqi Wang, Yiran Huang, Zihao Cao, Zhiguo Conde, Marcos V. Sapozhnikov, Denis Lee, Byeong Hyun Park, Dongwon Hong, Seongmin Lee, Joonhee Lee, Seunggyu Chun, Se Young Computer Vision Lab ETH Zürich Zürich Switzerland AI Witchlabs Zollikerberg Switzerland University of Wuerzburg Wuerzburg Germany TCL Research Europe Warsaw Poland Harbin Institute of Technology Harbin China Xiaomi Inc. Beijing China Tencent GY-Lab Shenzhen China National Key Laboratory of Science and Technology on Multi-Spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Department of Electrical and Computer Engineering Seoul National University Seoul Korea Republic of

ISBN: (纸本)9783031250651

Various depth estimation models are now widely used on many mobile and IoT devices for image segmentation, bokeh effect rendering, object tracking and many other mobile tasks. Thus, it is very crucial to have efficient and accurate depth estimation models that can run fast on low-power mobile chipsets. In this Mobile AI challenge, the target was to develop deep learning-based single image depth estimation solutions that can show a real-time performance on IoT platforms and smartphones. For this, the participants used a large-scale RGB-to-depth dataset that was collected with the ZED stereo camera capable to generated depth maps for objects located at up to 50 m. The runtime of all models was evaluated on the Raspberry Pi 4 platform, where the developed solutions were able to generate VGA resolution depth maps at up to 27 FPS while achieving high fidelity results. All models developed in the challenge are also compatible with any Android or Linux-based mobile devices, their detailed description is provided in this paper. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “Low-light image enhancement with knowledge distillation” [Neurocomputing 518 (2023) 332–343]

引用

Neurocomputing 2023年 523卷 144-144页

作者： Ziwen Li Yuehuan Wang Jinpu Zhang National Key Lab of Science and Technology on Multi-spectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan 430074 China

来源：评论

学校读者我要写书评

暂无评论

Natural van der Waals canalization lens for non-destructive nanoelectronic circuit imaging and inspection

arXiv

引用

arXiv 2025年

作者： Ou, Qingdong Xue, Shuwen Ma, Weiliang Yang, Jiong Si, Guangyuan Liu, Lu Zhong, Gang Liu, Jingying Xie, Zongyuan Xiao, Ying Kalantar-Zadeh, Kourosh Qi, Xiang Li, Peining Dai, Zhigao Chen, Huanyang Bao, Qiaoliang Faculty of Innovation Engineering Macau University of Science and Technology Macao Taipa999078 China Department of Materials Science and Engineering Monash University ClaytonVIC3800 Australia Department of Physics Xiamen University Xiamen361005 China National Engineering Research Center of Electromagnetic Radiation Control Materials Key Laboratory of Multi-spectral Absorbing Materials and Structures Ministry of Education University of Electronic Science and Technology of China Chengdu610054 China School of Optoelectronic Science and Engineering Collaborative Innovation Center of Suzhou Nano Science and Technology Key Lab of Advanced Optical Manufacturing Technologies of Jiangsu Province Key Lab of Modern Optical Technologies Education Ministry of China Soochow University Suzhou215006 China Melbourne Centre for Nanofabrication Victorian Node of The Australian National Fabrication Facility ClaytonVIC3168 Australia Engineering Research Center of Nano-Geomaterials Ministry of Education Faculty of Materials Science and Chemistry China University of Geosciences Wuhan430074 China School of Chemical and Biomolecular Engineering The University of Sydney SydneyNSW Australia Hunan Key Laboratory for Micro-Nano Energy Materials and Devices School of Physics and Optoelectronic Xiangtan University Hunan411105 China Wuhan National Laboratory for Optoelectronics School of Optical and Electronic Information Huazhong University of Science and Technology Wuhan430074 China Shenzhen Research Institute China University of Geosciences Shenzhen518063 China University of Shanghai for Science and Technology Shanghai200093 China Nanjing kLIGHT Laser Technology Co. Ltd. Jiangsu Nanjing210032 China

Optical inspection has long served as a cornerstone non-destructive method in semiconductor wafer manufacturing, particularly for surface and defect analysis. However, conventional techniques such as bright-field and dark-field scattering optics face significant limitations, including insufficient resolution and the inability to penetrate and detect buried structures. Atomic force microscopy (AFM), while offering higher resolution and precise surface characterization, is constrained by slow speed, limited to surface-level imaging, and incapable of resolving subsurface features. Here, we propose an approach that integrates the strengths of dark-field scattering optics and AFM by leveraging a van der Waals (vdW) canalization lens based on natural biaxial α-MoO3 crystals. This method enables ultrahigh-resolution subwavelength imaging with the ability to visualize both surface and buried structures, achieving a spatial resolution of 15 nm and grating pitch detection down to 100 nm. The underlying mechanism relies on the unique anisotropic properties of α-MoO3, where its atomic-scale unit cells and biaxial symmetry facilitate the diffraction-free propagation of both evanescent and propagating waves via a flat-band canalization regime. Unlike metamaterial-based superlenses and hyperlenses, which suffer from high plasmonic losses, fabrication imperfections, and uniaxial constraints, α-MoO3 provides robust and aberration-free imaging in multiple directions. We successfully applied this approach to achieve high-resolution inspection of buried nanoscale electronic circuits, offering unprecedented capabilities essential for next-generation semiconductor manufacturing. © 2025, CC BY-NC-ND.

关键词： Van der Waals forces

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：