检索结果-内蒙古大学图书馆

Scene text recognition via dual character counting-aware visual and semantic modeling network

Science China(Information Sciences) 2024年第3期67卷 313-314页

作者： Ke XIAO Anna ZHU Brian Kenji IWANA Cheng-Lin LIU School of Computer Science and Artificial Intelligence Wuhan University of Technology Human Interface Laboratory Kyushu University State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences

Scene text recognition(STR) is drawing increasing attention nowadays due to its wide application in real life. Character counting information, as auxiliary information, has been shown to be effective in boosting text ... 详细信息

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Few shot font generation via transferring similarity guided global style and quantization local style

Few shot font generation via transferring similarity guided ...

引用

International Conference on computer Vision (ICCV)

作者： Wei Pan Anna Zhu Xinyu Zhou Brian Kenji Iwana Shilin Li School of Computer Science and Artificial Intelligence Wuhan University of Technology Human Interface Laboratory Kyushu University

Automatic few-shot font generation (AFFG), aiming at generating new fonts with only a few glyph references, reduces the labor cost of manually designing fonts. However, the traditional AFFG paradigm of style-content disentanglement cannot capture the diverse local details of different fonts. So, many component-based approaches are proposed to tackle this problem. The issue with component-based approaches is that they usually require special pre-defined glyph components, e.g., strokes and radicals, which is infeasible for AFFG of different languages. In this paper, we present a novel font generation approach by aggregating styles from character similarity-guided global features and stylized component-level representations. We calculate the similarity scores of the target character and the referenced samples by measuring the distance along the corresponding channels from the content features, and assigning them as the weights for aggregating the global style features. To better capture the local styles, a cross-attention-based style transfer module is adopted to transfer the styles of reference glyphs to the components, where the components are self-learned discrete latent codes through vector quantization without manual definition. With these designs, our AFFG method could obtain a complete set of component-level style representations, and also control the global glyph characteristics. The experimental results reflect the effectiveness and generalization of the proposed method on different linguistic scripts, and also show its superiority when compared with other state-of-the-art methods. The source code can be found at https://***/awei669/VQ-Font.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Few shot font generation via transferring similarity guided global style and quantization local style

arXiv

引用

arXiv 2023年

作者： Pan, Wei Zhu, Anna Zhou, Xinyu Iwana, Brian Kenji Li, Shilin School of Computer Science and Artificial Intelligence Wuhan University of Technology China Human Interface Laboratory Kyushu University Japan

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Obstacle Detection and Avoidance based on 3D Stereoscopic Technique for Autonomous Drone 13

Obstacle Detection and Avoidance based on 3D Stereoscopic Te...

引用

13th International Conference on Information Technology and Electrical Engineering, ICITEE 2021

作者： Nabandit, Thanawut Saiyod, Saiyan Nonsakhoo, Woottichai Sirisawat, Piyanat Khon Kaen University Hardware-Human Interface and communication laboratory Department of Computer Science Khon Kaen Thailand

ISBN: (纸本)9781665443067

Autonomous drones are drones that can fly on their own without the need for human supervision. Once the drone is assigned a flight mission, it will automatically fly to its destination. The ability to quickly maneuver obstacles is essential to complete the task assigned to it. Obstacle analysis processes need to be efficient and require fewer computing resources due to the hardware and power constraints of drones. This work presents a simple but effective way to detect obstacles using a 3D Stereoscopic camera and a less complicated image processing method, which can run on a small single-board computer. On-site flight tests show that the proposed method can be used efficiently. It can detect obstacles at a distance of 2 meters, 5 frames per second, 79.55% of detection accuracy, and maneuver effectively. © 2021 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Survey and Experimental Comparison of Machine Learning Models for Motorcycle Detection 5

Survey and Experimental Comparison of Machine Learning Model...

引用

5th International Conference on Information Technology, InCIT 2020

作者： Jarunakarint, Vattiya Uttama, Surapong Rueangsirarak, Worasak Mobile Device and Human Interface Laboratory School of Information Technology Mae Fah Luang University Chiang Rai Thailand Mobile Device and Human Interface Laboratory Center of Excellence in Ai Emerging Technology School of Information Technology Mae Fah Luang University Chiang Rai Thailand Mobile Device and Human Interface Laboratory Computer and Communication Engineering for Capacity Building Research Unit School of Information Technology Mae Fah Luang University Chiang Rai Thailand

ISBN: (纸本)9781728166940

Road accidents are largely related to motorcycles and many cases resulted in severe injuries and fatalities. Automatic detection of motorcycles is considered a useful measure for monitoring evaluating predicting and eventually planning to prevent further motorcycle-related accidents. Many researchers proposed techniques to detect and track vehicles but only few focused on detecting motorcycles. In this paper we reviewed and conducted experiments on 20 different machine learning models with different sizes and views (front rear top) of traffic images to evaluate motorcycle detection's accuracy and time. By setting 60% threshold of accuracy on images of 480270 pixels the best detection model is rfcn-resnet101-coco which provided average accuracy detection time and efficiency at 65.85% 1.91 frames/second and 34.55 respectively. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Biomolecular condensates and disease pathogenesis

引用

Science China(Life Sciences) 2024年第9期67卷 1792-1832页

作者： Ke Ruan Ge Bai Yanshan Fang Dan Li Tingting Li Xingguo Liu Boxun Lu Qing Lu Zhou Songyang Shuguo Sun Zheng Wang Xin Zhang Wen Zhou Hong Zhang The First Affiliated Hospital&School of Life Sciences Ministry of Education Key Laboratory for Membrane-less Organelles&Cellular DynamicsHefei National Research Center for Interdisciplinary Sciences at the MicroscaleCenter for Advanced Interdisciplinary Science and Biomedicine of IHMDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefei 230027China Nanhu Brain-computer Interface Institute Hangzhou 311100China Department of Neurology of Second Affiliated Hospital and School of Brain Science and Brain Medicine Zhejiang University School of MedicineHangzhou 310058China Interdisciplinary Research Center on Biology and Chemistry Shanghai Institute of Organic ChemistryChinese Academy of SciencesShanghai 201210China University of Chinese Academy of Sciences Beijing 100049China Bio-X Institutes Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders(Ministry of Education)Shanghai Jiao Tong UniversityShanghai 200030China Department of Biomedical Informatics School of Basic Medical SciencesPeking University Health Science CenterBeijing 100191China CAS Key Laboratory of Regenerative Biology Joint School of Life SciencesGuangzhou Institutes of Biomedicine and HealthChinese Academy of SciencesGuangzhou 510530China Joint School of Life Sciences Guangzhou Medical UniversityGuangzhou 510000China Neurology Department at Huashan Hospital State Key Laboratory of Medical Neurobiology and MOE Frontiers Center for Brain ScienceInstitutes of Brain ScienceSchool of Life SciencesFudan UniversityShanghai 200433 China Key Laboratory for the Genetics of Developmental and Neuropsychiatric Disorders Ministry of EducationBio-X InstitutesShanghai Jiao Tong UniversityShanghai 200030China State Key Laboratory of Biocontrol MOE Key Laboratory of Gene Function and Regulation and Guangzhou Key Laboratory of Healthy Aging ResearchSchool of Life SciencesSun Yat-sen Memorial HospitalSun Yat-sen UniversityGuangzhou 510275China Department of Human Anatomy Hist

Biomolecular condensates or membraneless organelles(MLOs)formed by liquid-liquid phase separation(LLPS)divide intracellular spaces into discrete compartments for specific *** of LLPS or aberrant phase transition that disturbs the formation or material states of MLOs is closely correlated with neurodegeneration,tumorigenesis,and many other pathological ***,we summarize the recent progress in development of methods to monitor phase separation and we discuss the biogenesis and function of MLOs formed through phase *** then present emerging proof-of-concept examples regarding the disruption of phase separation homeostasis in a diverse array of clinical conditions including neurodegenerative disorders,hearing loss,cancers,and immunological ***,we describe the emerging discovery of chemical modulators of phase separation.

关键词： liquid-liquid phase separation biomolecular condensate membraneless organelle

来源：评论

学校读者我要写书评

暂无评论

Corrigendum to “FETNet: Feature Erasing and Transferring Network for Scene Text Removal”: Pattern Recognition Volume 140 (2023) 109531

引用

Pattern Recognition 2023年 141卷

作者： Guangtao Lyu Kun Liu Anna Zhu Seiichi Uchida Brian Kenji Iwana School of Computer Science and Artificial Intelligence Wuhan University of Technology Wuhan China Human Interface Laboratory Kyushu University Fukuoka Japan

来源：评论

学校读者我要写书评

暂无评论

Scene text magnifier 15

Scene text magnifier

引用

15th IAPR International Conference on Document Analysis and Recognition, ICDAR 2019

作者： Nakamura, Toshiki Nakamura Zhu, Anna Uchida, Seiichi Human Interface Laboratory Kyushu University Fukuoka Japan School of Computer Wuhan University of Technology Wuhan China

ISBN: (纸本)9781728128610

Scene text magnifier aims to magnify text in natural scene images without recognition. It could help the special groups, who have myopia or dyslexia to better understand the scene. In this paper, we design the scene text magnifier through interacted four CNN-based networks: character erasing, character extraction, character magnify, and image synthesis. The architecture of the networks are extended based on the hourglass encoderdecoders. It inputs the original scene text image and outputs the text magnified image while keeps the background unchange. Intermediately, we can get the side-output results of text erasing and text extraction. The four sub-networks are first trained independently and fine-tuned in end-to-end mode. The training samples for each stage are processed through a flow with original image and text annotation in ICDAR2013 and Flickr dataset as input, and corresponding text erased image, magnified text annotation, and text magnified scene image as output. To evaluate the performance of text magnifier, the Structural Similarity is used to measure the regional changes in each character region. The experimental results demonstrate our method can magnify scene text effectively without effecting the background. © 2019 IEEE.

关键词： Extraction

来源：评论

学校读者我要写书评

暂无评论

Investigating an effective character-level embedding in Korean sentence classification 33

Investigating an effective character-level embedding in Kore...

引用

33rd Pacific Asia Conference on Language, Information and Computation, PACLIC 2019

作者： Cho, Won Ik Kim, Seok Min Kim, Nam Soo Human Interface Laboratory Department of Electrical and Computer Engineering and INMC Seoul National University 1 Gwanak-ro Gwanak-gu Seoul08826 Korea Republic of

Different from the writing systems of many Romance and Germanic languages, some languages or language families show complex conjunct forms in character composition. For such cases where the conjuncts consist of the components representing consonant(s) and vowel, various character encoding schemes can be adopted beyond merely making up a one-hot vector. However, there has been little work done on intra-language comparison regarding performances using each representation. In this study, utilizing the Korean language which is character-rich and agglutinative, we investigate an encoding scheme that is the most effective among Jamo1-level one-hot, character-level one-hot, character-level dense, and character-level multi-hot. Classification performance with each scheme is evaluated on two corpora: one on binary sentiment analysis of movie reviews, and the other on multiclass identification of intention types. The result displays that the character-level features show higher performance in general, although the Jamo-level features may show compatibility with the attention-based models if guaranteed adequate parameter set size. Copyright © 2019 Won Ik Cho, Seok Min Kim and Nam Soo Kim.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Survey and Experimental Comparison of Machine Learning Models for Motorcycle Detection

Survey and Experimental Comparison of Machine Learning Model...

引用

International Conference on Information Technology (INCIT)

作者： Vattiya Jarunakarint Surapong Uttama Worasak Rueangsirarak Mobile Device and Human Interface Laboratory School of Information Technology Mae Fah Luang University Chiang Rai Thailand Mobile Device and Human Interface Laboratory Center of Excellence in AI & Emerging Technology School of Information Technology Mae Fah Luang University Chiang Rai Thailand Mobile Device and Human Interface Laboratory Computer and Communication Engineering for Capacity Building Research Unit School of Information Technology Mae Fah Luang University Chiang Rai Thailand

ISBN: (数字)9781728166940

ISBN: (纸本)9781728193212

Road accidents are largely related to motorcycles and many cases resulted in severe injuries and fatalities. Automatic detection of motorcycles is considered a useful measure for monitoring evaluating predicting and eventually planning to prevent further motorcycle-related accidents. Many researchers proposed techniques to detect and track vehicles but only few focused on detecting motorcycles. In this paper we reviewed and conducted experiments on 20 different machine learning models with different sizes and views (front rear top) of traffic images to evaluate motorcycle detection's accuracy and time. By setting 60% threshold of accuracy on images of 480×270 pixels the best detection model is rfcn_resnet101_coco which provided average accuracy detection time and efficiency at 65.85% 1.91 frames/second and 34.55 respectively.

关键词： Integrated circuits Roads Indium tin oxide Automobiles Radio frequency Optical imaging Machine learning

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：