检索结果-内蒙古大学图书馆

arXiv 2024年

作者： He, Haibin Ye, Maoyuan Zhang, Jing Liu, Juhua Du, Bo Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Wuhan University China College of Computing & Data Science Nanyang Technological University Singapore

Beyond the text detection and recognition tasks in image text spotting, video text spotting presents an augmented challenge with the inclusion of tracking. While advanced end-to-end trainable methods have shown commendable performance, the pursuit of multi-task optimization may pose the risk of producing sub-optimal outcomes for individual tasks. In this paper, we identify a main bottleneck in the state-of-the-art video text spotter: the limited recognition capability. In response to this issue, we propose to efficiently turn an off-the-shelf query-based image text spotter into a specialist on video and present a simple baseline termed GoMatching, which focuses the training efforts on tracking while maintaining strong recognition performance. To adapt the image text spotter to video datasets, we add a rescoring head to rescore each detected instance's confidence via efficient tuning, leading to a better tracking candidate pool. Additionally, we design a long-short term matching module, termed LST-Matcher, to enhance the spotter's tracking capability by integrating both long- and short-term matching results via Transformer. Based on the above simple designs, GoMatching delivers new records on ICDAR15-video, DSText, BOVText, and our proposed novel test with arbitrary-shaped text termed ArTVideo, which demonstrates GoMatching's capability to accommodate general, dense, small, arbitrary-shaped, Chinese and English text scenarios while saving considerable training budgets. Copyright © 2024, The Authors. All rights reserved.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Crack Detection Methods in Ancient Buildings 24

Machine Learning-Based Crack Detection Methods in Ancient Bu...

引用

2024 Guangdong-Hong Kong-Macao Greater Bay Area International Conference on Digital Economy and Artificial Intelligence, DEAI 2024

作者： Fang, Tianke Hui, Zhenxing Rey, William P. Yang, Aihua Liu, Bin He, Yuanrong School of Information Technology Mapua University Manila1200 Philippines School of Computing and Information Engineering Xiamen University of Technology Xiamen Fujian361024 China Big Data Institute of Digital Natural Disaster Monitoring in Fujian Xiamen University of Technology Xiamen Fujian361024 China School of Information Media Zhangzhou Vocational College of Science and Technology Zhangzhou Fujian363200 China College of Software Engineering Xiamen University of Technology Xiamen Fujian361024 China

ISBN: (纸本)9798400717147

This research paper introduces an innovative machine learning-based methodology for detecting cracks in ancient buildings, a vital aspect of architectural heritage conservation. Recognizing the limitations of conventional techniques in addressing the complex nature of historical structures, this study explores the integration of deep learning algorithms with enhanced image processing methods tailored for aged and varied materials typical of ancient architecture. The paper includes a comprehensive process involving meticulous data collection from diverse ancient structures, employing specialized preprocessing methods to handle the unique challenges of old surfaces. The development of a custom machine learning model, designed to adapt to the intricacies of historical construction, is thoroughly detailed. Experimental results demonstrate the model's superior performance in accurately identifying structural cracks compared to traditional methods. This research not only significantly contributes to the preservation of historical buildings but also exemplifies the versatile application of machine learning in the field of architectural conservation. The findings hold promise for revolutionizing the approach to maintaining and restoring our architectural heritage, ensuring longevity and integrity. © 2024 ACM.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Energy-Efficient Dynamic Asynchronous Federated Learning in Mobile Edge Computing Networks

Energy-Efficient Dynamic Asynchronous Federated Learning in ...

引用

IEEE International Conference on Communications (ICC)

作者： Guozeng Xu Xiuhua Li Hui Li Qilin Fan Xiaofei Wang Victor C. M. Leung School of Big Data & Software Engineering Chongqing University Chongqing China TKLAN College of Intelligence & Computing Tianjin University Tianjin China College of Computer Science & Software Engineering Shenzhen University Shenzhen China Department of Electrical & Computer Engineering The University of British Columbia Vancouver Canada

To break data silos and address the challenge of green communication, federated learning (FL) is widely used at network edges to train deep learning models in mobile edge computing (MEC) networks. However, many existing FL algorithms do not fully consider the dynamic environment, resulting in slower convergence of the model and larger training energy consumption. In this paper, we design a dynamic asynchronous federated learning (DAFL) model to improve the efficiency of FL in MEC networks. Specifically, we dynamically choose a certain number of mobile devices (MDs) by their arrival order to participate in the global aggregation at each epoch. Meanwhile, we analyze the energy consumption model of local update and upload update, and formulate the problem as a dynamic sequential decision problem to minimize the energy consumption, which is NP-hard. To address it, we propose an energy-efficient algorithm based on deep reinforcement learning named DDAFL, to intelligently determine the number of MDs participating in global aggregation according to the state of MEC networks at each epoch. Compared with baseline schemes, the proposed algorithm can significantly reduce energy consumption and accelerate model convergence.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spatial-Temporal Graph-Based AU Relationship Learning for Facial Action Unit Detection

Spatial-Temporal Graph-Based AU Relationship Learning for Fa...

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zihan Wang Siyang Song Cheng Luo Yuzhi Zhou Shiling Wu Weicheng Xie Linlin Shen Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University School of Computing and Mathematical Sciences University of Leicester

This paper presents our Facial Action Units (AUs) detection submission to the fifth Affective Behavior Analysis in-the-wild Competition (ABAW). Our approach consists of three main modules: (i) a pre-trained facial representation encoder which produce a strong facial representation from each input face image in the input sequence; (ii) an AU-specific feature generator that specifically learns a set of AU features from each facial representation; and (iii) a spatio-temporal graph learning module that constructs a spatio-temporal graph representation. This graph representation describes AUs contained in all frames and predicts the occurrence of each AU based on both the modeled spatial information within the corresponding face and the learned temporal dynamics among frames. The experimental results show that our approach outperformed the baseline and the spatio-temporal graph representation learning allows our model to generate the best results among all ablated systems. Our model ranks at the 4th place in the AU recognition track at the 5th ABAW Competition. Our code is publicly available at https://***/wzh125/ABAW-5.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

arXiv

引用

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

PUSHGNN: A Low-communication Runtime System for GNN Acceleration on Multi-GPUs

PUSHGNN: A Low-communication Runtime System for GNN Accelera...

引用

IEEE International Conference on big data

作者： Guoqing Xiao Li Xia Yuedan Chen Wangdong Yang College of Computer Science and Electronic Engineering Hunan University Changsha China National Supercomputing Center in Changsha Changsha China Big Data Institute Central South University Changsha China

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

The need for multi-GPU platforms in graph neural networks (GNNs) has been driven by the growing size of input graphs. However, although the existing multi-gpu GNN framework has been optimized from the perspective of optimizing computing and communication operations, communication competition still exists. To this end, we introduce PUSHGNN, a runtime system designed to reduce communication overhead across GPUs, boosting GNN performance. Therefore, we designed a push-based pipeline communication model and made custom tuning to significantly reduce pipeline contention. Comparative assessments demonstrate that PUSHGNN consistently outperforms leading full-graph GNN systems on average 1.97× and 7.57× faster than MGG and MGG-UVM, respectively.

关键词： Runtime Computational modeling Pipelines big data Boosting Graph neural networks Tuning Optimization Load modeling

来源：评论

学校读者我要写书评

暂无评论

StyleAU: StyleGAN based Facial Action Unit Manipulation for Expression Editing

StyleAU: StyleGAN based Facial Action Unit Manipulation for ...

引用

IEEE International Joint Conference on Biometrics (IJCB)

作者： Yanliang Guo Xianxu Hou Feng Liu Linlin Shen Lei Wang Zhen Wang Peng Liu Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University School of AI and Advanced Computing Xi’an Jiaotong-Liverpool University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Qualcomm Technologies Inc

Facial expression editing has a wide range of applications, such as emotion detection, human-computer interaction, and social entertainment. However, existing expression editing methods either fail to allow for fine-grained editing, resulting in unnatural and unrealistic facial expressions, or generate artifacts and blurs, leading to poor image quality. In this paper, we propose a novel framework called StyleAU, which is based on StyleGAN and facial action units, to address these problems. Our framework leverages the pre-trained StyleGAN prior knowledge to enable action unit editing of the face in the StyleGAN latent space, allowing precise expression editing. In addition, we use an encoder to extract multi-scale content features to achieve high-fidelity image reconstruction. Our approach qualitatively and quantitatively outperforms competing methods for action unit manipulation and expression editing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Like an Ophthalmologist: Dynamic Selection Driven Multi-View Learning for Diabetic Retinopathy Grading 39

Like an Ophthalmologist: Dynamic Selection Driven Multi-View...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Luo, Xiaoling Xu, Qihao Wu, Huisi Liu, Chengliang Lai, Zhihui Shen, Linlin Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Key Laboratory of Visual Object Detection and Recognition Harbin Institute of Technology Shenzhen China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

ISBN: (纸本)157735897X

Diabetic retinopathy (DR), with its large patient population, has become a formidable threat to human visual health. In the clinical diagnosis of DR, multi-view fundus images are considered to be more suitable for DR diagnosis because of the wide coverage of the field of view. Therefore, different from the previous single-view DR grading methods, we design a dynamic selection-driven multi-view DR grading method to fit clinical scenarios better. Since lesion information plays a key role in DR diagnosis, previous methods usually boost the model performance by enhancing the lesion feature. However, during the actual diagnosis, ophthalmologists not only focus on the crucial parts, but also exclude irrelevant features to ensure the accuracy of judgment. To this end, we introduce the idea of dynamic selection and design a series of selection mechanisms from fine granularity to coarse granularity. In this work, we first introduce an Ophthalmic Image Reader (OIR) agent to provide the model with pixel-level prompts of suspected lesion areas. Moreover, we design a Multi-View Token Selection Module (MVTSM) that prunes redundant feature tokens and dynamically selects key information. In the final decision stage, we dynamically fuse multi-view features through the novel Multi-View Mixture of Experts Module (MVMoEM), to enhance key views and reduce the impact of conflicting views. Extensive experiments on a large multi-view fundus image dataset with 34,452 images prove that our method performs favorably against state-of-the-art models. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Ophthalmology

来源：评论

学校读者我要写书评

暂无评论

NESpMV: NEON-Enhanced SpMV Algorithm for NUMA Architectures

NESpMV: NEON-Enhanced SpMV Algorithm for NUMA Architectures

引用

Smart World Congress (SWC), IEEE

作者： Guoqing Xiao Zhijie Li Yuedan Chen Yimiao Zeng Wangdong Yang College of Computer Science and Electronic Engineering Hunan University Changsha China National Supercomputing Center in Changsha Changsha China Big Data Institute Central South University Changsha China

ISBN: (数字)9798331520861

ISBN: (纸本)9798331520878

Iterative methods are used to solve large-scale, sparse linear equations to approximate the exact solutions in various real-world applications, such as CG, GMRES, SOR, Jacobi and so on. Sparse matrix-vector multiplication (SpMV), the primary computational step, usually must be performed thousands of times in the iterative solution. However, the complexity of the underlying hardware architectures and the sparse characteristics of sparse matrices lead to unbalanced computational loads and memory access bottlenecks, which makes it challenging to accelerate the performance of SpMV. ARMv8-A is a high-performance computing processor architecture launched by ARM. It provides the Non-Uniform Memory Access (NUMA) architecture, multiple cores, and SIMD instructions to improve parallel float-precision computing capabilities. This paper introduces a novel compression sparse row (NeCSR) format that leverages the NEON technique, which is an ARM Advanced SIMD (Single Instruction, Multiple data) extension. NEON facilitates parallel processing of data, allowing for efficient handling of operations on multiple data points simultaneously. By applying NEON in the context of sparse matrix storage, the NeCSR format enhances data locality and computational performance by grouping data with similar characteristics into the same processing units. For example, 4 float data, named a vector pair, can be stored simultaneously in the 128 -bit vector register. This paper calculates the vector pair with the smallest unit in subsequent calculations instead of simply performing computations on nonzero elements. Correspondingly, this paper designs a NUMAaware distribution strategy to address the issue of cross-node memory access during the computation process and ensure that threads on each node only access local memory on the current node. We select 13 data sets from SuitSparse and test the performance of NESpMV on the Kunpeng 920 processor. The experimental results show that NESpMV gains a performa

关键词： Jacobian matrices Neon Single instruction multiple data Instruction sets Memory architecture Vectors Mathematical models Registers Sparse matrices Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Prioritizing Test Cases Through Dual-Uncertainty Evaluating for Road Disease Detection System

Prioritizing Test Cases Through Dual-Uncertainty Evaluating ...

引用

Asia-Pacific Conference on software engineering

作者： Chenxu Niu Huijun Liu Ao Li Tianhao Xiao Zhimin Ruan Ling Xu Yongxin Ge College of Computer Science Chongqing University Chongqing China School of Big Data & Software Engineering Chongqing University Chongqing China China Merchants Chongqing Communications Technology Research&Design Institute Co. Ltd. Chongqing China

ISBN: (数字)9798331534011

ISBN: (纸本)9798331534028

Road damage detection system based on deep learning models has been extensively researched, capable of intelligently detecting damages in roads. However, to ensure reliability, a large number of images usually need to be collected and annotated to test the model. Collecting images is often a straightforward work, but annotating them is both time-consuming and costly. To minimize annotation costs during the testing phase, we can evaluate images using Test Prioritization method to select more meaningful samples for system testing. Yet, most mainstream work currently only evaluates cases based on classification result, neglecting the impact of localization. At the same time, these methods do not provide higher evaluation results to complex images that may detect errors or images where targets cannot be detected at all. To address these issues, we propose a new Test Prioritization tool, Dual-u, to evaluate road damage cases. It consists of two components: (1) Localization Uncertainty Evaluation, which evaluates the localization of damages while considering the value of the image, ensuring that complex images and images where targets cannot be detected also have higher priority; (2) Classification Uncertainty Evaluation, which evaluates the classification of damages. To evaluate Dual-u, we conduct extensive experiments using two object detection model architectures on multiple road disease datasets, and the results demonstrate that Dual-u outperforms existing methods in evaluating cases. Moreover, Dual-u can also be used to improve the accuracy and robustness of road disease detection models.

关键词： Location awareness Deep learning System testing Uncertainty Costs Roads Object detection Robustness Diseases software engineering

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：