检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Lu, Yanzuo Zhang, Manlin Ma, Andy J. Xie, Xiaohua Lai, Jianhuang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Province Key Laboratory of Information Security Technology China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Guangzhou China

Diffusion model is a promising approach to image generation and has been employed for Pose-Guided Person Image Synthesis (PGPIS) with competitive performance. While existing methods simply align the person appearance to the target pose, they are prone to overfitting due to the lack of a high-level semantic understanding on the source person image. In this paper, we propose a novel Coarse-to-Fine Latent Diffusion (CFLD) method for PGPIS. In the absence of image-caption pairs and textual prompts, we develop a novel training paradigm purely based on images to control the generation process of a pre-trained text-to-image diffusion model. A perception-refined decoder is designed to progressively refine a set of learnable queries and extract semantic understanding of person images as a coarse-grained prompt. This allows for the decoupling of fine-grained appearance and pose information controls at different stages, and thus circumventing the potential overfitting problem. To generate more realistic texture details, a hybrid-granularity attention module is proposed to encode multi-scale fine-grained appearance features as bias terms to augment the coarse-grained prompt. Both quantitative and qualitative experimental results on the DeepFashion benchmark demonstrate the superiority of our method over the state of the arts for PGPIS. Code is available at https://***/YanzuoLu/CFLD. Copyright © 2024, The Authors. All rights reserved.

关键词： Textures

来源：评论

学校读者我要写书评

暂无评论

EDA: Enhanced Domain-Adversarial Training for Anatomical Landmark Detection 22

EDA: Enhanced Domain-Adversarial Training for Anatomical Lan...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Yang, Fan Zhou, S. Kevin School of Biomedical Engineering Division of Life Sciences and Medicine University of Science and Technology of China Anhui Hefei230026 China Suzhou Institute for Advanced Research University of Science and Technology of China Jiangsu Suzhou215123 China Key Laboratory of Precision and Intelligent Chemistry Ustc Anhui Hefei230026 China Institute of Computing Technology Cas Beijing100190 China

ISBN: (纸本)9798331520526

Manually annotating anatomical landmarks in medical images requires experienced clinicians and is a labor-intensive process. However, recent AI-assisted methods for landmark detection often rely on the training and test data originating from the same domain. This work introduces a novel unsupervised domain adaptation (UDA) framework aimed at anatomical landmark detection from a medical image, designed to bridge the gap between a source domain with labels and an unlabeled target domain. Specifically, we have developed a new Domain-Adversarial Network that incorporates skip connections to transfer and fuse high-resolution feature maps. Additionally, we proposed Dynamic Gaussian Learning, which allows the model to escape from local error regions. We carry out experiments on landmark detection for both head and chest, and the results demonstrate that our method achieves state-of-the-art performances in each experiment. © 2025 IEEE.

关键词： Anatomical Landmark Detection Unsupervised Domain Adaptation

来源：评论

学校读者我要写书评

暂无评论

Neural Manifold Learning Based on 40 nm Dual-Mode PCM Compute-in-Memory Chip with Hardware Adaptive Drift Compensation

Neural Manifold Learning Based on 40 nm Dual-Mode PCM Comput...

引用

2024 IEEE International Electron Devices Meeting, IEDM 2024

作者： Yan, Longhao Li, Yuqi Li, Xi Pan, Zelun Wang, Zeyu Wang, Xile Wang, Bowen Zhan, Zhe Tang, Xiyuan Tao, Yaoyu Ge, Woo-Ping Song, Zhitang Huang, Ru Yang, Yuchao Beijing Advanced Innovation Center for Integrated Circuits School of Integrate Circuits Peking University Beijing China Beijing China Center for Brain Inspired Chips Institute for Artificial Intelligence Peking University Beijing China Guangdong Provincial Key Laboratory of In-Memory Computing Chips School of Electronic and Computer Engineering Peking University Shenzhen China State Key Laboratory of Functional Materials for Informatics Shanghai Institute of Microsystem and Information Technology Chinese Academy of Sciences China

ISBN: (纸本)9798350365429

Neural manifold learning (NML), as a significant research topic in the field of neuroscience, plays a vital role in the realization of intelligent brain-computer interface (BCI) at the edge. However, traditional edge computing platforms fall short in meeting the demands for the huge computing power needed to process massive neural data. Here, we design a 288Kb dual-mode phase change memory (PCM) compute-in-memory chip in 40nm technology and utilize its two cores for two fundamental kernels in NML, vector matrix multiplication (VMM) and true random number generation, and develop a PCM-based NML system for the first time. In particular, in order to mitigate the performance degradation caused by PCM conductance drift, we propose a novel adaptive-PCM-drift-compensation scheme that significantly improves the accuracy of VMM results. Compared with CPU platforms running the same tasks, the resulting chip improves the computing energy efficiency and throughput by 476× and 264×, respectively. © 2024 IEEE.

关键词： Random number generation

来源：评论

学校读者我要写书评

暂无评论

Long‐time target tracking algorithm based on re‐detection multi‐feature fusion

引用

IET Cyber-Systems and Robotics 2022年第1期4卷 38-50页

作者： Junsuo Qu Chenxue Tang Yuan Zhang Kai Zhou Abolfazl Razi School of Automation Xi'an Key Laboratory of Advanced Control and Intelligent ProcessXi'an University of Posts and TelecommunicationsXi'anShaanxiChina School of Communication and Information Engineering Xi'an University of Posts and TelecommunicationsXi'anShaanxiChina School of Informatics Computing and Cyber SystemsNorthern Arizona UniversityFlagstaffAZUSA

This paper considers the problem of long-term target tracking in complex scenes when tracking failures are unavoidable due to illumination change,target deformation,scale change,motion blur,and other *** specifically,a target tracking algorithm,called re-detection multi-feature fusion,is proposed based on the fusion of scale-adaptive kernel correlation filtering and *** target tracking algorithm trains three kernel correlation filters based on the histogram of oriented gradients,colour name,and local binary pattern features and then obtains the fusion weight of response graphs corresponding to different features based on average peak correlation energy criterion and uses weighted average to complete the position estimation of the tracked *** order to deal with the problem that the target is occluded and disappears in the tracking process,a random fern classifier is trained to perform re-detection when the target is *** comparing the OTB-50 target tracking dataset,the experimental results show that the proposed tracker can track the target well in the occlusion attribute video sequence in the OTB-100 test dataset and has a certain improvement in tracking accuracy and success rate compared with the traditional correlation filter tracker.

关键词： machine learning pedestrian identification robustness visual surveillance visual tracking

来源：评论

学校读者我要写书评

暂无评论

Preparation of active coke combining coal with biomass and its denitrification performance

引用

Journal of Iron and Steel Research International 2021年第10期28卷 1203-1211页

作者： Xiao-hu Zhou Sheng-fu Zhang Yu-yang Wei Farooq Sher Yang Li Wen-zhou Yu Liang-ying Wen College of Materials Science and Engineering Chongqing UniversityChongqing400044China Chongqing Key Laboratory of Vanadium-Titanium Metallurgy and Advanced Materials Chongqing UniversityChongqing400044China School of Mechanical Aerospace and Automotive EngineeringFaculty of EngineeringEnvironment and ComputingCoventry UniversityCoventryCV15FBUK

To improve the selective catalytic reduction of NO with NH3 over active coke(AC),coal–biomass ACs were prepared from the mixture of poplar and 1/3 coking coal for increasing the active *** resultant ACs were characterized by N2 adsorption and X-ray photoelectron ***,the denitrification performance was tested at laboratory *** addition,density functional theory was used to analyze active sites on the surface of *** result revealed that,with an increase in poplar content,the decrease in micropores volume appeared in the reduction of denitrification ***,C−O group including hydroxyl and ether increased with the increase in poplar content,which was found to be most likely responsible for the promoted catalytic activity of AC toward NO reduction mainly because of enhancing NH3 *** comprehensive effect of two factors made the denitrification ability of AC increased first and then decreased.

关键词： Active coke Denitrification Pore structure Functional group Density functional theory

来源：评论

学校读者我要写书评

暂无评论

Path planning of UAV base station based on deep reinforcement learning

引用

Procedia Computer Science 2022年 202卷 89-104页

作者： Siming Yang Zheng Shan Jiang Cao Yuan Gao Yang Guo Ping Wang Xiaonan Wang Jing Wang Tingting Zhang Jiayu Guo State Key Laboratory of Mathematical Engineering and Advanced Computing Zhengzhou Henan 450001 China Academy of Military Science of the PLA Beijing 100091 China Network Technology Research Center of the PLA Beijing 100090 China

UAV base station platform has become the current research hotspot of assisting ground base station for wireless *** present, the most important issue is how to make path planning to provide the stable communication guarantee for multiple mobile users. In this article, we model the air-to-ground channel to describe the path loss between the UAV platform and the user and build a simulation environment for training based on the OpenAI-GYM architecture. In addition, this paper proposes a reinforcement learning algorithm based on intrinsic rewards, which uses the mean square error of the state prediction results to quantify the novelty of the state. Algorithms enable agents to efficiently carry out strategy iterations. Experiments results showed that our algorithm has a higher score and takes less time.

关键词： UAV path planning Wireless communication coverage Deep learning Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availability of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly available image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are available at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Loss Network for Localization of Image Manipulation 19th

A Hybrid Loss Network for Localization of Image Manipulation

引用

19th International Workshop on Digital Forensics and Watermarking, IWDW 2020

作者： Yin, Qilin Wang, Jinwei Luo, Xiangyang Nanjing University of Information Science and Technology and Engineering Research Center of Digital Forensics Ministry of Education Nanjing210044 China State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450001 China Shanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China

ISBN: (纸本)9783030694487

With the development of information security, localization of image manipulations havs become a hot topic. In this paper, a hybrid loss network is proposed for the manipulated image forensics. First, the patch prediction module extracts corresponding features representing the discrepancy of the tampered region boundaries. Then, these features are constrained by the Pixel Normalization, thereby improving the classification performance for the tampered patches. Finally, multi-scale patch prediction masks and semantic information are fused to segment out the tampered regions. The experiments demonstrate the proposed model can achieve high performance. © 2021, Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

Improved attribute reductions based on combined measures from dependency-roughness-entropy fusion and classification-class-level integration

引用

Applied Intelligence 2025年第9期55卷 1-27页

作者： Yuan, Yixiao Zhang, Xianyong Wang, Qian Mo, Zhiwen School of Mathematical Sciences Sichuan Normal University Chengdu China Research Center of Sichuan Normal University National-Local Joint Engineering Laboratory of System Credibility Automatic Verification Chengdu China Visual Computing and Virtual Reality Key Laboratory of Sichuan Province Sichuan Normal University Chengdu China

Attribute reductions facilitate data analyses and knowledge discovery, and they rely on uncertainty measures. The current dependency degree (DD) and condition entropy (CE) effectively motivate attribute reductions and corresponding heuristic algorithms (called DD-AR and CE-AR). However, algebraic DD and informational CE emphasize only a single view, and their algebra-information fusion implies advancement space for uncertainty measurements and attribute reductions. For measurement reinforcement, the roughness/accuracy degree (RD/AD) is further introduced to constitute three-factor measures DD, CE, RD/AD with two levels, the direct classification-level fusion and preferential class-level fusion produce two fusion measures (called DFM and PFM) with hierarchical integrations, so DFM and PFM motivate attribute reductions and corresponding heuristic algorithms (called DFM-AR and PFM-AR) with learning improvements. At first, hierarchical sizes of RDs/ADs are revealed by max-min and mean statistics of class-level values. Then, DFM directly emerges by fused multiplication of classification-level three-factor measures, while PFM hierarchically emerges by fused multiplication of class-level three-factor measures and by subsequent integrated summation; DFM and PFM acquire essential expressions, size relationships, granulation monotonicity, and construction algorithms. Furthermore, DFM and PFM generate attribute reductions, and DFM-AR and PFM-AR are designed by attribute significance to improve DD-AR and CE-AR. Finally, relevant fusion measures and reduction algorithms are validated through table examples and data experiments, so the two new algorithms generally outperform current baselines DD-AR, CE-AR and other latest algorithms (such as AR-JSI, UDI-IG) to achieve better classification performances.

关键词： Attribute reduction Uncertainty measurement Information fusion Granular computing Rough set Three-way decision

来源：评论

学校读者我要写书评

暂无评论

A Channel-Augmented Multi-Domain Graph Convolutional Network for Fatigue Driving Detection 4

A Channel-Augmented Multi-Domain Graph Convolutional Network...

引用

4th International Conference on Industrial Automation, Robotics and Control engineering, IARCE 2024

作者： Sun, Mingyi Cui, Weigang Li, Yang Beihang University Department of Automation Science and Electrical Engineering Beijing China School of Engineering Medicine Beihang University Beijing China The Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University State Key Laboratory of Virtual Reality Technology and Systems Department of Automation Science and Electrical Engineering Beijing China

ISBN: (纸本)9798350380323

Electroencephalography (EEG) has emerged as a crucial cornerstone within the realm of brain-computer interface (BCI) applications, with its significance notably pronounced in the field of fatigue detection. However, the inherent limitations of EEG acquisition equipment during real driving scenarios have contributed to the constrained robustness of existing models. Moreover, most of recent methods failed to extract robust multi-domain features, leading to a suboptimal performance. To address these challenges, we propose a novel channel-augmented multi-domain graph convolutional network (CA-MDGCNet). Specifically, the initial EEG signals are enriched by incorporating supplementary virtual EEG channels, distinguished as learnable parameters within the network architecture. Then, differential entropy features are extracted from the augmented EEG signals. Following this, a multi-domain graph convolutional network is designed to encode high-level EEG features by means of convolutions in diverse paths, which is beneficial to integrating the characteristics extracted from multiple domains. Finally, the classification block derives the detection outcome from the refined feature maps. To substantiate the potency of the proposed method, the validation was conducted on the publicly accessible SEED-VIG. The proposed CA-MDGCNet not only demonstrates more promising performance compared to state-of-the-art approaches but also underscores the potential viability of our method for the realm of fatigue driving detection. © 2024 IEEE.

关键词： electroencephalogram fatigue detection graph convolutional network multi-domain feature extraction

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：