检索结果-内蒙古大学图书馆

Symmetry-Enhanced Attention Network for Acute Ischemic Infarct Segmentation with Non–Contrast CT Images

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Liang, Kongming Han, Kai Li, Xiuli Cheng, Xiaoqing Li, Yiming Wang, Yizhou Yu, Yizhou Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Deepwise AI Lab Beijing China Department of Medical Imaging Jinling Hospital Nanjing University School of Medicine Jiangsu Nanjing China Department of Computer Science and Technology Peking University Beijing China The University of Hong Kong Pokfulam Hong Kong

Quantitative estimation of the acute ischemic infarct is crucial to improve neurological outcomes of the patients with stroke symptoms. Since the density of lesions is subtle and can be confounded by normal physiologic changes, anatomical asymmetry provides useful information to differentiate the ischemic and healthy brain tissue. In this paper, we propose a symmetry enhanced attention network (SEAN) for acute ischemic infarct segmentation. Our proposed network automatically transforms an input CT image into the standard space where the brain tissue is bilaterally symmetric. The transformed image is further processed by a U-shape network integrated with the proposed symmetry enhanced attention for pixel-wise lab.lling. The symmetry enhanced attention can efficiently capture context information from the opposite side of the image by estimating long-range dependencies. Experimental results show that the proposed SEAN outperforms some symmetry-based state-of-the-art methods in terms of both dice coefficient and infarct localization. Copyright © 2021, The Authors. All rights reserved.

关键词： Computerized tomography

Semi-heterogeneous three-way joint embedding network for sketch-based image retrieval

学校读者我要写书评

暂无评论

arXiv 2019年

作者： Lei, Jianjun Song, Yuxin Peng, Bo Ma, Zhanyu Shao, Ling Song, Yi-Zhe School of Electrical and Information Engineering Tianjin University Tianjin300072 China Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing100876 China Inception Institute of Artificial Intelligence Abu Dhabi United Arab Emirates SketchX Lab Centre for Vision Speech and Signal Processing University of Surrey Surrey GuildfordGU2 7XH United Kingdom

Sketch-based image retrieval (SBIR) is a challenging task due to the large cross-domain gap between sketches and natural images. How to align abstract sketches and natural images into a common high-level semantic space remains a key problem in SBIR. In this paper, we propose a novel semi-heterogeneous three-way joint embedding network (Semi3-Net), which integrates three branches (a sketch branch, a natural image branch, and an edgemap branch) to learn more discriminative cross-domain feature representations for the SBIR task. The key insight lies with how we cultivate the mutual and subtle relationships amongst the sketches, natural images, and edgemaps. A semi-heterogeneous feature mapping is designed to extract bottom features from each domain, where the sketch and edgemap branches are shared while the natural image branch is heterogeneous to the other branches. In addition, a joint semantic embedding is introduced to embed the features from different domains into a common high-level semantic space, where all of the three branches are shared. To further capture informative features common to both natural images and the corresponding edgemaps, a co-attention model is introduced to conduct common channel-wise feature recalibration between different domains. A hybrid-loss mechanism is designed to align the three branches, where an alignment loss and a sketch-edgemap contrastive loss are presented to encourage the network to learn invariant cross-domain representations. Experimental results on two widely used category-level datasets (Sketchy and TU-Berlin Extension) demonstrate that the proposed method outperforms state-of-the-art methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Semantics

Survey on Deep Face Restoration: From Non-blind to Blind and Beyond

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Li, Wenjie Wang, Mei Zhang, Kai Li, Juncheng Li, Xiaoming Zhang, Yuhang Gao, Guangwei Deng, Weihong Lin, Chia-Wen The Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China The Computer Vision Lab ETH Zürich Zürich Switzerland The School of Communication and Information Engineering Shanghai University Shanghai China The Nanyang Technological University Singapore The Intelligent Visual Information Perception Laboratory Institute of Advanced Technology Nanjing University of Posts and Telecommunications Nanjing China The Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan

Face restoration (FR) is a specialized field within image restoration that aims to recover low-quality (LQ) face images into high-quality (HQ) face images. Recent advances in deep learning technology have led to significant progress in FR methods. In this paper, we begin by examining the prevalent factors responsible for real-world LQ images and introduce degradation techniques used to synthesize LQ images. We also discuss notable benchmarks commonly utilized in the field. Next, we categorize FR methods based on different tasks and explain their evolution over time. Furthermore, we explore the various facial priors commonly utilized in the restoration process and discuss strategies to enhance their effectiveness. In the experimental section, we thoroughly evaluate the performance of state-of-the-art FR methods across various tasks using a unified benchmark. We analyze their performance from different perspectives. Finally, we discuss the challenges faced in the field of FR and propose potential directions for future advancements. The open-source repository corresponding to this work can be found at https://***/24wenjie-li/Awesome-Face-Restoration. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

Multi-lingual Handwriting Recovery Framework based on Convolutional Denoising Autoencoder with Attention model

学校读者我要写书评

暂无评论

TechRxiv

TechRxiv 2022年

作者： Rabhi, Besma Elbaati, Abdelkarim Boubaker, Houcine Pal, Umapada Alimi, Adel M. University of Sfax National Engineering School of Sfax REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Sfax3038 Tunisia University of Monastir Higher Institute of Applied Sciences and Technology of Mahdia REGIM-Lab.: REsearch Groups in Intelligent Machines LR11ES48 Mahdia5121 Tunisia Computer Vision and Pattern Recognition Unit Indian Statistical Institute 203 B. T. Road Kolkata700108 India Department of Electrical and Electronic Engineering Science Faculty of Engineering and the Built Environment University of Johannesburg Johannesburg South Africa

For several decades, the offline handwriting recognition problem has escaped a satisfactory solution. In the field of online recognition, researchers have had more successful performance, but the ability to extract dynamic information from static images has not been well explored yet. In this paper, we introduce a novel multi-lingual word handwriting recovery framework based on a convolutional denoising autoencoder with an attention model for pen up / down, velocity and temporal order recovery. The proposed framework consists of extracting robust features from a handwriting image using a stacked denoising autoencoder and an encoder Bidirectional Gated Recurrent Unit (BGRU) model. Then, the obtained vectors are decoded to produce an online script with dynamic characteristics using a BGRU with temporal attention. Evaluation is done on a Latin and Arabic Online and offline handwriting character / word databases and the proposed framework achieves high competitive results. To the best of our knowledge, this is the first work of its kind. © 2022, CC BY.

关键词： Recovery

Graph Convolution Based Cross-Network Multi-Scale Feature Fusion for Deep Vessel Segmentation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhao, Gangming Liang, Kongming Pan, Chengwei Zhang, Fandong Wu, Xianpeng Hu, Xinyang Yu, Yizhou The Department of Computer Science The University of Hong Kong Hong Kong Pattern Recognition and Intelligent System Laboratory School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China Institute of Artificial Intelligence Beihang University Beijing China The AI Lab Deepwise Healthcare Beijing China Department of Cardiology of the Second Affiliated Hospital School of Medicine Zhejiang University Hangzhou China Key Laboratory of Cardiovascular of Zhejiang Province Hangzhou China

Vessel segmentation is widely used to help with vascular disease diagnosis. Vessels reconstructed using existing methods are often not sufficiently accurate to meet clinical use standards. This is because 3D vessel structures are highly complicated and exhibit unique characteristics, including sparsity and anisotropy. In this paper, we propose a novel hybrid deep neural network for vessel segmentation. Our network consists of two cascaded subnetworks performing initial and refined segmentation respectively. The second subnetwork further has two tightly coupled components, a traditional CNN-based U-Net and a graph U-Net. Cross-network multi-scale feature fusion is performed between these two U-shaped networks to effectively support high-quality vessel segmentation. The entire cascaded network can be trained from end to end. The graph in the second subnetwork is constructed according to a vessel probability map as well as appearance and semantic similarities in the original CT volume. To tackle the challenges caused by the sparsity and anisotropy of vessels, a higher percentage of graph nodes are distributed in areas that potentially contain vessels while a higher percentage of edges follow the orientation of potential nearby vessels. Extensive experiments demonstrate our deep network achieves state-of-the-art 3D vessel segmentation performance on multiple public and in-house datasets. Copyright © 2023, The Authors. All rights reserved.

关键词： Anisotropy

Spontaneous speech dialogue system TOSBURG II - The user-centered multimodal interface

学校读者我要写书评

暂无评论

systemS AND COMPUTERS IN JAPAN 1995年第14期26卷 77-91页

作者： Takebayashi, Y Member Senior Research Engineer 3rd Communications System Lab. Research & Development Center Toshiba Corporation Kawasaki Japan 210 Received his B.E. degree in 1974 from Dept. Electrical Eng. Keio Univ. and his Ph.D. degree in 1980 from Tohoku Univ. He affiliated in 1980 with Toshiba Corp. He is engaged in research on speech recognition and intelligent interface. Presently Chief Researcher 3rd Comm. System Lab. in R&D Center. Visiting Researcher 1985–1987 MIT Media Lab. Head of 5th Lab. 1992–1993 Jap. Electr. Dictionary Lab. Paper Award 1992 Nat. Conv. Soc. Artif. Intel. Tech. Dev. Award 1993 Acost. Soc. Jap. He is a member of Inf. Proc. Soc. Acoust. Soc. Jap. and Soc. Artif. Intel.

This paper considers the user-centered spontaneous speech dialogue system TOSBURG-II (Task-oriented dialogue system based on speech understanding and response generation), and discusses the design from the viewpoint of media technology and a multimodal interface. The authors have developed element techniques, including spontaneous speech understanding, user-center dialogue control, multimodal response generation and speech response cancelling, all based on the noise-immune word-spotting and keywords. The concept is that ''no constraint is imposed on the user.'' By integrating these techniques, the realtime speech dialogue system for an unspecified user is developed. The speech dialogue data acquisition/ evaluation system is constructed on the real system. The system can record real speech data as well as the intermediate result of processing in the dialogue system, such as keyword spotting, Speech understanding and dialogue processing: The system can also be utilized in the construction of the speech dialogue corpus and the. evaluation/improvement of the human factor aspect, in addition to,the evaluation of the system performance. As a result of trial use and evaluation experiment for the real system for unspecified users, it is verified that spontaneous speech understanding based on the interruption function by the user and the multimodal response and keywords, is useful in improving the naturalness of the dialogue and robustness.

关键词： speech dialogue multimodal multimedia speech understanding human interface

The role of data analysis in the development of intelligent energy networks

学校读者我要写书评

暂无评论

arXiv 2017年

作者： Ma, Zhanyu Xie, Jiyang Li, Hailong Si, Zhongwei Zhang, Jianhua Guo, Jun Sun, Qie Pattern Recognition and Intelligent Systems Lab. Beijing University of Posts and Telecommunications Beijing China School of Business Mälardalen University Society and Engineering Västerås Sweden .Tianjin Key Laboratory of Refrigeration Technology School of Mechanical Engineering Tianjin University of Commerce Tianjin China Institute of Thermal Science and Technology Shandong University Ji'nan China Key Laboratory of Universal Wireless Communications Beijing University of Posts and Telecommunications MOE Beijing China State Key Lab of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing China

Data analysis plays an important role in the development of intelligent energy networks (IENs). This article reviews and discusses the application of data analysis methods for energy big data. The installation of smart energy meters has provided a huge volume of data at different time resolutions, suggesting data analysis is required for clustering, demand forecasting, energy generation optimization, energy pricing, monitoring and diagnostics. The currently adopted data analysis technologies for IENs include pattern recognition, machine learning, data mining, statistics methods, etc. However, existing methods for data analysis cannot fully meet the requirements for processing the big data produced by the IENs and, therefore, more comprehensive data analysis methods are needed to handle the increasing amount of data and to mine more valuable information. Copyright © 2017, The Authors. All rights reserved.

关键词： District heating

Comparison of Backbones for Semantic Segmentation Network

学校读者我要写书评

暂无评论

Journal of Physics: Conference Series 2020年第1期1544卷

作者： Rongyu Zhang Lixuan Du Qi Xiao Jiaming Liu International School Beijing University of Post and Telecommunication BEIJING 100876 CHINA International School of business&Fiance Sun Yat-Sen University GUANGZHOU 510275 CHINA Pattern Recognition and Intelligent System Lab Beijing University of Posts and Telecommunications BEIJING 100876 CHINA

As for the classification network that is constantly emerging with each passing day, different classification network as the backbone of the semantic segmentation network may show different performance. This paper selected the road extraction data set of CVPR DeepGlobe, and compared the performance differences of VGG-16 as the backbone of Unet, ResNet34, ResNet101 and Xception as the backbone of AD-LinkNet. When VGG-16 is used as the backbone of the semantic segmentation network, it performs better in the face of long and wide road extraction. As the backbone of the semantic segmentation network, ResNet has a higher ability to extract small roads. When Xception is used as the backbone of the semantic segmentation network, it not only retains the characteristics of ResNet34, but also can effectively deal with the complex situation of extracting target covered by occlusions.

关键词：

Application of a genetic algorithm in triangulation of a 3-D object surface

学校读者我要写书评

暂无评论

International Journal of Computers and Applications 2000年第2期22卷 73-77页

作者： Zhenyu, Chen Mbede, J.B. Yan, Zhou Dehua, Li Hanping, Hu State Commn. Res. Open Lab. Image P. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Intelligent Contr. and Robotics Lab. Dept. of Contr. Sci. and Engineering Huazhong Univ. of Sci. and Technol. 430074 Wuhan China Second Artillery Institute Huazhong Univ. of Sci. and Technol. Inst. Pattern Recog. Artif. Intell. Huazhong Univ. of Sci. and Technol. Second Artillery Institute China Wuhan University China Artificial Intelligence Department University of Edinburgh Inst. of AI and Pattern Recognition Huazhong Univ. of Sci. and Technol. China Cogn. Sci. Natl. Key Found. Res. P. Douala University Cameroon Tübingen University Germany Automatic Control Laboratory Darmstadt University Department of Service Cameroon Min. of National Education Robotics Laboratory Huazhong Univ. of Sci. and Technol. Wuhan China Assoc. Connectionnistes These-ACTH Rennes France IEEE Soc. of Robotics and Automation IEEE Society of Control Systems IASTED Assoc. Jeunes Chercheurs Robotique France Navy University of Engineering China Huazhong Univ. of Sci. and Technol. China Department of Computer Science Airforce Radar Acad. of Engineering China Inst. of P.R and AI Huazhong Univ. of Sci. and Technol.

This paper proposes a genetic-based algorithm for surface reconstruction of three-dimension (3-D) objects from a group of contours representing its section plane lines. The algorithm can optimize the triangulation of the surface of 3-D objects with a multi-objective optimization function to meet the needs of a wide range of applications. Further, a new crossover operator for triangulation and a new 3-D quadrilateral mutation operator are also introduced.

关键词： Object recognition