检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Kehan Li Zhennan Wang Zesen Cheng Runyi Yu Yian Zhao Guoli Song Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Peng Cheng Laboratory Shenzhen China Dalian University of Technology Department of Automation and BNRist Tsinghua University Beijing China

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions in the image is non-trivial since over/ under-clustering overwhelms the conceptualization procedure under various semantic distributions of different images. In this work, we investigate the pixel-level semantic aggregation in self-supervised ViT pre-trained models as image Segmentation and propose the Adaptive Conceptualization approach for USS, termed ACSeg. Concretely, we explicitly encode concepts into learnable prototypes and design the Adaptive Concept Generator (ACG), which adaptively maps these prototypes to informative concepts for each image. Meanwhile, considering the scene complexity of different images, we propose the modularity loss to optimize ACG independent of the concept number based on estimating the intensity of pixel pairs belonging to the same concept. Finally, we turn the USS task into classifying the discovered concepts in an unsupervised manner. Extensive experiments with state-of-the-art results demonstrate the effectiveness of the proposed ACSeg.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Reduce Fingerprint Construction for Positioning IoT Devices Based on Generative Adversarial Nets 1

Reduce Fingerprint Construction for Positioning IoT Devices ...

引用

1st International Conference on Pervasive Artificial Intelligence, ICPAI 2020

作者： Tarekegn, Getaneh Berie Juang, Rong-Terng Lin, Hsin-Piao Munaye, Yirga Yayeh Belay Adege, Abebe National Taipei University of Technology Department of International Graduate Program in Electrical Engineering and Computer Science Taipei Taiwan Feng Chia University Department of Electronic Engineering Taichung Taiwan National Taipei University of Technology Department of Electronic Engineering Taipei Taiwan Debre Markos University Department of Information Technology Debre Markos Ethiopia

ISBN: (纸本)9781665404839

Fingerprint-based positioning is popular and applicable for Internet of Things (IoT) applications to offer seamless, intelligent and adaptive location-aware services for IoT devices. However, it takes time and cost to build the radio-map. This paper proposed deep convolutional Generative adversarial nets (DCGANs) to minimize the site survey time and cost, and to mitigate signal fluctuations. The radio-map was designed for receiving radio signals from detectable wireless local area network (WLAN) and cellular networks in scalable environments. The proposed fingerprinting-based positioning is a sequential combination of the hybrid support vector machine and long short-term memory algorithms. The experimental results indicate that the proposed method achieves a promising and reasonable positioning performance for IoT devices in scalable wireless environments. © 2020 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Sagittal Lower Limb Joint Angular Phase-Plane Analysis at Long, Short and No-Countermovement

Sagittal Lower Limb Joint Angular Phase-Plane Analysis at Lo...

引用

Bioengineering (ENBENG), Portuguese Meeting in

作者： Carlos Rodrigues Miguel Correia João Abrantes Marco Rodrigues Jurandir Nadal C-BER - Centre for Biomedical Engineering Research INESC TEC - Institute for Systems and Computer Engineering Technology and Science Porto Portugal MovLab - Laboratory of Technologies for Interactions and Interfaces CICANT - Centre for Research in Applied Communication Culture and New Technologies Lisbon Portugal Department of Electronic and Systems Federal University of Pernambuco Recife Brazil Biomedical Engineering Program Federal University of Rio de Janeiro Rio de Janeiro Brazil

This study presents non-invasive subject specific analysis using innovative tools from dynamic systems theory and image processing for sagittal plane anatomical marker tracking and digital filtering for detection of normalized phase differences of lower limb joint angular displacement and angular velocity coordination during long and short countermovement (CM) and muscle stretch-shortening cycle. Applied metrics captured at low-dimensional level (one variable - the phase) differences of CM neuromuscular control of lower limb joint coordination with greater dissimilarity between long and short CM, whereas no CM condition shares higher phase coordination at the hip, knee, ankle.

关键词：

来源：评论

学校读者我要写书评

暂无评论

3D Liver and Tumor Segmentation in CT Scans with Robust Self-Paced Learning 7

3D Liver and Tumor Segmentation in CT Scans with Robust Self...

引用

7th International Conference on Information Science and Control engineering, ICISCE 2020

作者： Nartey, Obed Tettey Yang, Guowu Asare, Sarpong Kwadwo Wu, Jinzhao Agyapong, Dorothy Araba Yakoba Frempong, Lady Nadia University of Electronic Science and Technology of China Big Data Research Center School of Computer Science and Engineering Chengdu611731 China University of Electronic Science and Technology of China School of Electronic Science and Engineering Chengdu611731 China Guangxi University for Nationalities School of Mathematics and Physics Nanning530006 China Kwame Nkrumah University of Science and Technology Biomedical Engineering Program Kumasi Ghana

ISBN: (纸本)9781728164069

Liver segmentation is a challenging problem where fully supervised deep learning models require large amounts of voxel-wise labels, which are usually laborious, expensive, and time consuming to obtain. However, massive non-annotated 3D CT volumes are usually easily accessible. Most deep learning based works to address semi-supervised CT medical image segmentation problems have mostly been graph-based or adversarial-based. In sharp contrast, this work investigates the potential of a semi-supervised learning method;novel self-training framework utilizing self-paced learning strategy to generate and select pseudo-labels from easy-to-transfer(well represented classes) to hard-to-transfer(less represented classes) samples. The proposed scheme introduces an effective pseudo-label generation and selection algorithm to generate highly confident pseudo-labels, jointly learn and optimize a model which can be solved by alternatively generating pseudo labels on unlabeled target data and re-training the model with the generated labels. Further, we also propose a novel class balancing framework to avoid the gradual eminence of easy-to-transfer discriminative features on pseudo-label generation utilizing class-wise normalization of confidence scores. Comprehensive experiments conducted on publicly available datasets show that the proposed method outperformed other state-of-the-art semi-supervised and some fully supervised methods on the segmentation results of tumors and achieved very competitive performance for liver segmentation. © 2020 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Double-SP Method to Enhance Privacy and Security of Smart City Applications

Double-SP Method to Enhance Privacy and Security of Smart Ci...

引用

International Conference on Computing for Sustainable Global Development (INDIACom)

作者： Nour Mahmoud Bahbouh Abdulelah Alhussain Hassan Hakami Yaser Mohammed Aljohani Adnan Ahmed Abi Sen Ahmad Alkhodre Aeshah Alsughayyir Department of Information and Communication Sciences Granada University Granada Spain Saudi Electronic University Al-Madinah Saudi Arabia YasRef Program Yanbu Saudi Arabia Computing and Information Technology Islamic University Al-Madinah Saudi Arabia Faculty of Computer and Information Systems Islamic University Al-Madinah Saudi Arabia College of Computer Science and Engineering Taibah University Al-Madinah Saudi Arabia

Smart cities promise a lot of well-being to their users in all areas of life through millions of applications and services. Smart services rely heavily on collecting data and the preferences of users. But on the dark side, the users' information is posed to threat and penetration during transmission or stored far in the clouds. Depending on encryption only is not sufficient if the attacker has strong resources or if the attacker is the service provider (SP) itself. In addition, changing data before sending is not a practical solution in many systems because of the adverse impact on the quality of a main service. This research presented a new idea to address the issue of protection. The proposed method enhanced the privacy and security of users' data without affecting the accuracy of service. The core of the suggested solution relies on a knowledge base of services that are managed by experts. Also, the solution depends on fog nodes to measure the level of security and privacy of users' queries without delay. Moreover, the fog nodes manage contact with SPs. Finally, the proposed method divided the SP into two, one for user queries and the other for user data. The simulation and analytical discussion on a practical case in smart cities demonstrated the superiority of the proposed approach over previous methods in the level of protection by maintaining the quality of services, and the resistance to attacks.

关键词： Resistance Privacy Data privacy Machine learning algorithms Smart cities Knowledge based systems Quality of service

来源：评论

学校读者我要写书评

暂无评论

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

Chat-UniVi: Unified Visual Representation Empowers Large Lan...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Ryuichi Takanobu Wancai Zhang Xiaochun Cao Li Yuan School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Nari Technology Co. Ltd. China School of Cyber Science and Tech. Shenzhen Campus of Sun Yat-sen University Shenzhen China

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multi-modal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified Vision-language model capable of comprehending and engaging in conver-sations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to ef-ficiently utilize a limited number of visual tokens to simul-taneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level seman-tic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Exten-sive experimental results demonstrate that Chat- UniVi con-sistently outperforms even existing methods exclusively de-signed for either images or videos. Code is available at https://***/PKu-Yuan Group/Chat-UniVi.

关键词： Bridges Visualization computer vision Codes Large language models Computational modeling Oral communication

来源：评论

学校读者我要写书评

暂无评论

Mechanically reprogrammable Pancharatnam-Berry metasurface for microwaves

引用

Advanced Photonics 2022年第1期4卷 69-79页

作者： Quan Xu Xiaoqiang Su Xueqian Zhang Lijuan Dong Lifeng Liu Yunlong Shi Qiu Wang Ming Kang Andrea Alù Shuang Zhang Jiaguang Han Weili Zhang Tianjin University Center for Terahertz Waves and College of Precision Instrument and Optoelectronics EngineeringKey Laboratory of Optoelectronic Information Technology(Ministry of Education of China)TianjinChina Shanxi Datong University Institute of Solid State Physics and College of Physics and Electronic ScienceShanxi Province Key Laboratory of Microstructure Electromagnetic Functional MaterialsDatongChina Wuhan University of Technology School of Information EngineeringWuhanChina Tianjin Normal University College of Physics and Materials ScienceTianjinChina City University of New York Advanced Science Research CenterPhotonics InitiativeNew YorkUnited States City University of New York Graduate CenterPhysics ProgramNew YorkUnited States University of Hong Kong Faculty of ScienceDepartment of PhysicsHong KongChina University of Hong Kong Department of Electrical and Electronic EngineeringHong KongChina Guilin University of Electronic Technology Guangxi Key Laboratory of Optoelectronic Information ProcessingSchool of Optoelectronic EngineeringGuilinChina Oklahoma State University School of Electrical and Computer EngineeringStillwaterOklahomaUnited States

Metasurfaces have enabled the realization of several optical functionalities over an ultrathin platform,fostering the exciting field of flat *** metasurfaces are achieved by arranging a layout of static meta-atoms to imprint a desired operation on the impinging wavefront,but their functionality cannot be *** and programmability of metasurfaces are the next important step to broaden their impact,adding customized on-demand functionality in which each meta-atom can be individually *** demonstrate a mechanical metasurface platform with controllable rotation at the meta-atom level,which can implement continuous Pancharatnam–Berry phase control of circularly polarized *** the proof-of-concept experiments,we demonstrate metalensing,focused vortex beam generation,and holographic imaging in the same metasurface template,exhibiting versatility and superior *** dynamic control of electromagnetic waves using a single,low-cost metasurface paves an avenue towards practical applications,driving the field of reprogrammable intelligent metasurfaces for a variety of applications.

关键词： reprogrammable metasurfaces Pancharatnam-Berry phase mechanical metasurfaces microwaves

来源：评论

学校读者我要写书评

暂无评论

Suboptimal Safety-Critical Control for Continuous Systems Using Prediction-Correction Online Optimization

arXiv

引用

arXiv 2022年

作者： Wang, Shengbo Wen, Shiping Yang, Yin Cao, Yuting Shi, Kaibo Huang, Tingwen The School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China Australian AI Institute Faculty of Engineering and Information Technology University of Technology SydneyNSW2007 Australia College of Science and Engineering Hamad Bin Khalifa University Doha5855 Qatar School of Information Science and Engineering Chengdu University Chengdu611040 China Science Program Texas A & M University at Qatar Doha23874 Qatar

This paper presents an innovative efficient safety-critical control scheme for nonlinear systems by combining techniques of control barrier function (CBF) and online time-varying optimization. The idea lies in that when directly calling the complete optimization solvers used in the CBF method, such as CBF-based quadratic programming (CBF-QP), is computationally inefficient for complex tasks, the suboptimal solutions obtained from online learning techniques can be an alternatively reliable choice for ensuring both efficiency and control performance. By using the barrier-based interior point method, the original optimization problem with CBF constraints is reduced to an unconstrained one with approximate optimality. Then, Newton- and gradient-based continuous dynamics are introduced to generate alternative cheap solutions while ensuring safety. By further considering the lag effect of online tracking, a prediction term is added to the dynamics. In this way, the online cheap solutions are proven to exponentially converge to the time-varying suboptimal solutions of the interior point method. Furthermore, the safety criteria are established, and the robustness of the designed algorithms is analyzed theoretically. Finally, the effectiveness is illustrated by conducting two experiments on obstacle avoidance and anti-swing tasks. © 2022, CC BY-NC-ND.

关键词： Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Chat-UniVi: Unified Visual Representation Empowers Large Language Models with Image and Video Understanding

arXiv

引用

arXiv 2023年

作者： Jin, Peng Takanobu, Ryuichi Zhang, Wancai Cao, Xiaochun Yuan, Li School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China -Preferred Program Peking University Shenzhen Graduate School Shenzhen China Nari Technology Co. Ltd. China School of Cyber Science and Tech. Sun Yat-sen University Shenzhen Campus Shenzhen China

Large language models have demonstrated impressive universal capabilities across a wide range of open-ended tasks and have extended their utility to encompass multimodal conversations. However, existing methods encounter challenges in effectively handling both image and video understanding, particularly with limited visual tokens. In this work, we introduce Chat-UniVi, a Unified Vision-language model capable of comprehending and engaging in conversations involving images and videos through a unified visual representation. Specifically, we employ a set of dynamic visual tokens to uniformly represent images and videos. This representation framework empowers the model to efficiently utilize a limited number of visual tokens to simultaneously capture the spatial details necessary for images and the comprehensive temporal relationship required for videos. Moreover, we leverage a multi-scale representation, enabling the model to perceive both high-level semantic concepts and low-level visual details. Notably, Chat-UniVi is trained on a mixed dataset containing both images and videos, allowing direct application to tasks involving both mediums without requiring any modifications. Extensive experimental results demonstrate that Chat-UniVi consistently outperforms even existing methods exclusively designed for either images or videos. Code is available at https://***/PKU-YuanGroup/Chat-UniVi. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using a Deep Learning Approach

Enhancing Diagnostic Accuracy for Knee Osteoarthritis Using ...

引用

International Symposium on Applied Science 2024, ISAS 2024

作者： Raza, Aquib Ching, Congo Tak Shing Liu, Peng-Ta Phan, Thien-Luan Tran, Ngoc-Luan Nguyen, Ha Anh T. Rameez, Mohammad Li, Hung-Chung Linh, Dao Nguyen Phuong Van Hieu, Nguyen Tran, Trung Nghia National Taiwan University Taipei City10673 Taiwan Research Center for Information Technology Academia Sinica Taipei City11529 Taiwan Graduate Institute of Biomedical Engineering National Chung Hsing University Taichung402 Taiwan Department of Electrical Engineering National Chi Nan University Nantou County Taiwan Advanced Plant and Food Crop Biotechnology Center National Chung Hsing University Taichung402 Taiwan International Doctoral Program in Agriculture National Chung Hsing University Taichung402 Taiwan Fall Prevention Center Department of Physical Medicine & Rehabilitation Changhua Christian Hospital Changhua500 Taiwan Department of Physics and Electronic Engineering University of Science Vietnam National University - Ho Chi Minh City Ho Chi Minh City70000 Viet Nam Department of Computer Science University of York York HeslingtonYO10 5DD United Kingdom Undergraduate Program of Intellectual Creativity Engineering National Chung Hsing University Taichung402 Taiwan Ho Chi Minh City72409 Viet Nam HCMUT Vietnam National University Ho Chi Minh City Thu Duc Ho Chi Minh City71308 Viet Nam

This research introduces a deep learning framework that combines convolutional neural networks with autoencoders to improve the diagnostic accuracy of knee osteoarthritis. The study utilized a publicly available dataset from the Mendeley Data repository, where knee joint images were preprocessed using Contrast Limited Adaptive Histogram Equalization to enhance contrast and ensure consistent image sizing. Initially, an autoencoder was employed in an unsupervised manner to learn compressed representations of the data. These representations were then used to train a CNN to classify knee images into 'healthy' and 'osteoarthritic' categories. The model was trained using an 80:20 split for training and testing data, incorporating early stopping and data augmentation techniques to prevent overfitting and enhance generalization. Performance metrics such as accuracy, precision, recall, and the area under the Receiver Operating Characteristic curve (ROCAUC) were used to evaluate the model, resulting in a high test accuracy of 98.95%. The high precision and recall rates further confirmed the model's robustness in diagnosing KOA. To enhance interpretability, Gradient-weighted Class Activation Mapping (Grad-CAM) was applied to identify critical regions in the images that influenced the model's decisions. Additionally, t-Distributed Stochastic Neighbor Embedding (t-SNE) was used to visualize the high-dimensional encoded features in a two-dimensional space, providing deeper insights into how the model differentiates between classes. The promising results of this deep learning approach suggest its potential for broader applications in medical imaging diagnostics. By providing healthcare professionals with a tool that enhances diagnostic accuracy and operational efficiency, this framework lays the foundation for developing scalable, AI-driven diagnostic systems for various complex medical conditions. © 2025 Institute of Physics Publishing. All rights reserved.

关键词： Joints (anatomy)

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：