检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Hong, Fa-Ting Feng, Jia-Chang Xu, Dan Shan, Ying Zheng, Wei-Shi School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Peng Cheng Laboratory Shenzhen China Tencent PCG Shenzhen China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Department of Computer Science and Engineering HKUST Hong Kong Pazhou Lab Guangzhou China Guangdong Key Laboratory of Information Security Technology Sun Yat-sen University Guangzhou China

Weakly supervised temporal action localization (WS-TAL) is a challenging task that aims to localize action instances in the given video with video-level categorical supervision. Previous works use the appearance and motion features extracted from pre-trained feature encoder directly, e.g., feature concatenation or score-level fusion. In this work, we argue that the features extracted from the pre-trained extractors, e.g., I3D, which are trained for trimmed video action classification, but not specific for WS-TAL task, leading to inevitable redundancy and sub-optimization. Therefore, the feature re-calibration is needed for reducing the task-irrelevant information redundancy. Here, we propose a cross-modal consensus network (CO2-Net) to tackle this problem. In CO2-Net, we mainly introduce two identical proposed cross-modal consensus modules (CCM) that design a cross-modal attention mechanism to filter out the task-irrelevant information redundancy using the global information from the main modality and the cross-modal local information from the auxiliary modality. Moreover, we further explore inter-modality consistency, where we treat the attention weights derived from each CCM as the pseudo targets of the attention weights derived from another CCM to maintain the consistency between the predictions derived from two CCMs, forming a mutual learning manner. Finally, we conduct extensive experiments on two commonly used temporal action localization datasets, THUMOS14 and ActivityNet1.2, to verify our method, which we achieve the state-of-the-art results. The experimental results show that our proposed cross-modal consensus module can produce more representative features for temporal action localization. Copyright © 2021, The Authors. All rights reserved.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Explore Contextual Information for 3D Scene Graph Generation

arXiv

引用

arXiv 2022年

作者： Liu, Yuanyuan Long, Chengjiang Zhang, Zhaoxuan Liu, Bokai Zhang, Qiang Yin, Baocai Yang, Xin The Department of Electronic Information and Electrical Engineering Dalian University of Technology Dalian116024 China Meta Reality Labs BurlingameCA94010 United States The Key Lab of Advanced Design and Intelligent Computing Dalian University Ministry of Education Dalian116622 China The Beijing Key Laboratory of Multimedia and Intelligent Software Technology Beijing Institute of Artificial Intelligence Faculty of Information Technology Beijing University of Technology Beijing100124 China

3D scene graph generation (SGG) has been of high interest in computer vision. Although the accuracy of 3D SGG on coarse classification and single relation label has been gradually improved, the performance of existing works is still far from being perfect for fine-grained and multi-label situations. In this paper, we propose a framework fully exploring contextual information for the 3D SGG task, which attempts to satisfy the requirements of fine-grained entity class, multiple relation labels, and high accuracy simultaneously. Our proposed approach is composed of a Graph Feature Extraction module and a Graph Contextual Reasoning module, achieving appropriate information-redundancy feature extraction, structured organization, and hierarchical inferring. Our approach achieves superior or competitive performance over previous methods on the 3DSSG dataset, especially on the relationship prediction sub-task. Copyright © 2022, The Authors. All rights reserved.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Simulations and Experiments of Time-Varying Takagi Factorization via Zhang Neural Network

Simulations and Experiments of Time-Varying Takagi Factoriza...

引用

IEEE advanced Information Technology, Electronic and Automation Control Conference (IAEAC)

作者： Zanyu Tang Tianyu Zeng Zhenyu Li Jianrong Chen Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangdong Key Laboratory of Modern Control Technology Guangzhou China College of Information Science and Engineering Jishou University Jishou China Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education Guangzhou China School of Public Health Administration Youjiang Medical University for Nationalities Baise China

ISBN: (数字)9781728180281

ISBN: (纸本)9781728180298

The problem of Takagi factorization (TF) for complex time-varying symmetric matrix is proposed in this paper. To solve this difficult and challenging problem, a continuous-time TF (CTTF) model of derivative equation system form is proposed via Zhang neural network (ZNN) method. For the sake of digital hardware implementation, we also build up the corresponding discrete-time (DT) ZNN solution models with different precisions of the derivative equation system discretization. Specifically, an eight-instant DTTF (EIDTTF) model are proposed. We also comparatively use two other multi-instant (e.g., four-instant and six-instant, i.e., FIDTTF and SIDTTF, respectively) models by discretizing the CTTF model. The effective solution step-size intervals of the proposed DTTF models are further discussed lastly. The results of simulations and experiments substantiate the correctness, effectiveness and superiority of the proposed CTTF and DTTF models.

关键词： Symmetric matrices Conferences Neural networks Hardware Numerical models Mathematical model Information technology

来源：评论

学校读者我要写书评

暂无评论

Fast quantum algorithm for differential equations

arXiv

引用

arXiv 2023年

作者： Bagherimehrab, Mohsen Nakaji, Kouhei Wiebe, Nathan Aspuru-Guzik, Alán Chemical Physics Theory Group Department of Chemistry University of Toronto TorontoON Canada Department of Computer Science University of Toronto TorontoON Canada 1-1-1 Umezono Ibaraki Tsukuba305-8568 Japan Quantum Computing Center Keio University 3-14-1 Hiyoshi Kohoku-ku Kanagawa Yokohama223-8522 Japan Pacific Northwest National Laboratory RichlandWA United States Canadian Institute for Advanced Research TorontoON Canada Vector Institute for Artificial Intelligence TorontoON Canada Department of Chemical Engineering & Applied Chemistry University of Toronto TorontoON Canada Department of Materials Science & Engineering University of Toronto TorontoON Canada

Partial differential equations (PDEs) are ubiquitous in science and engineering. Prior quantum algorithms for solving the system of linear algebraic equations obtained from discretizing a PDE have a computational complexity that scales at least linearly with the condition number κ of the matrices involved in the computation. For many practical applications, κ scales polynomially with the size N of the matrices, rendering a polynomial-in-N complexity for these algorithms. Here we present a quantum algorithm with a complexity that is polylogarithmic in N but is independent of κ for a large class of PDEs. Our algorithm generates a quantum state that enables extracting features of the solution. Central to our methodology is using a wavelet basis as an auxiliary system of coordinates in which the condition number of associated matrices is independent of N by a simple diagonal preconditioner. We present numerical simulations showing the effect of the wavelet preconditioner for several differential equations. Our work could provide a practical way to boost the performance of quantum-simulation algorithms where standard methods are used for discretization. © 2023, CC BY.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Adaptive Stepwise Feature Selection Approach for EEG-Based Epileptic Seizure Classification

Adaptive Stepwise Feature Selection Approach for EEG-Based E...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Sunday Timothy Aboyeji Wenfang Zhou Yuan Tao Mingxing Zhu Oluwarotimi Williams Samuel Ijaz Ahmad Guoru Zhao Ji Yi Michael Chi Fai Tong Xin Wang Yi Guo Shixiong Chen CAS Key Laboratory of Human-Machine Intelligence-Synergy Systems Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China Department of Otolaryngology Luohu District People's Hospital Shenzhen China Department of Otorhinolaryngology Peking University Shenzhen Hospital Shenzhen China School of Electronics and Information Engineering Harbin Institute of Technology Shenzhen Shenzhen China School of Computing and Engineering University of Derby Derby UK Department of Ophthalmology School of Medicine Johns Hopkins University Baltimore USA Department of Otorhinolaryngology Head and Neck Surgery The Chinese University of Hong Kong Hong Kong China Department of Neurology Shenzhen People’s Hospital Shenzhen China School of Medicine The Chinese University of Hong Kong Shenzhen Shenzhen China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Recent advancements in feature selection (FS) optimization algorithms have influenced the field of epileptic seizure classification. However, integrating these optimization algorithms into machine learning (ML) models often creates time complexity, limiting their clinical deployment. To address this issue, we propose an innovative adaptive stepwise FS method tailored for epileptic seizure detection (ESD). First, a discrete wavelet transform (DWT) was applied to the preprocessed signal to get three levels of the db4 wavelet family within the frequency range pertinent to epileptic seizure classification. Linear and nonlinear features are then extracted from each level of the DWT. The selected features are initially ranked using the minimum relevance, maximum redundancy (mRMR) FS technique. After that, a stepwise FS approach was applied to the ranked features to optimize the performance of Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) classifiers. The experiment was performed on a publicly accessible CHB-MIT dataset in a patient-independent approach. The model's performance was assessed using accuracy, sensitivity, and specificity. The results show an improved performance of the ML models with the integration of stepwise algorithm into the mRMR technique. Among the classifiers, RF exhibited superior performance with accuracy, sensitivity, and specificity of 87.69%, 91.53%, and 83.86%, respectively, when 12 features were selected. Our proposed stepwise feature selection method (PSFS) performs similarly to generalize forward feature selection (GFFS), with an average accuracy of 88.37% and 88.57%, respectively across selected features with less computation. This makes PSFS a very efficient and effective FS in epileptic seizure classification.

关键词： Support vector machines Radio frequency Accuracy Redundancy Sensitivity and specificity Feature extraction Brain modeling Classification algorithms Discrete wavelet transforms Optimization

来源：评论

学校读者我要写书评

暂无评论

Redundant-Manipulator Minimal Motion via Different-Precision Discrete-Time Zhang Neural Dynamics Algorithms Especially Ten-Instant One

Redundant-Manipulator Minimal Motion via Different-Precision...

引用

Chinese Automation Congress (CAC)

作者： Zanyu Tang Jinjin Guo Jianrong Chen Yunong Zhang School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Jishou University Jishou China Guangdong Key Laboratory of Modern Control Technology Guangzhou China School of Public Health and Management Youjiang Medical University for Nationalities Baise China Ministry of Education Key Laboratory of Machine Intelligence and Advanced Computing Guangzhou China

ISBN: (纸本)9781665426480

As a significant and basic robotic sub-topic, the problem of optimal MPC (motion planning & control) of ordinarily redundant manipulator widely exists in many fields, such as industry and daily-life applications. Following previous work, the aim of this paper is at solving the problem of velocity-level minimal joint motion planning & control (VLMJMPC) in a way of discrete time. Firstly, the VLMJMPC problem is introduced and analyzed using Zhang neural dynamics (ZND) method, and the motion scheme is then given. Secondly, by using ZND and Lagrange-multiplier methods, a continuous-time (CT) model for real-time solving the problem is established. In order to realize on digital computers, we use a ten-instant Zhang time discretization (abbreviated as ZTD) general formula with the fifth-order precision to discretize the model, and a special algorithm with high precision is derived, developed and analyzed. Finally, five discrete-time ZND (DTZND) algorithms are further acquired by adopting this ten-instant ZTD formula and other ZTD formulas, and the corresponding theoretical analyses are given. Computer experiment results numerically verify the online effectiveness and correctness of the developed five DTZND algorithms.

关键词： Industries Digital computers Service robots Heuristic algorithms Computational modeling Dynamics Real-time systems

来源：评论

学校读者我要写书评

暂无评论

UOD: Universal One-shot Detection of Anatomical Landmarks

arXiv

引用

arXiv 2023年

作者： Zhu, Heqin Quan, Quan Yao, Qingsong Liu, Zaiyi 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 Institute of Computing Technology CAS Beijing100190 China Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China

One-shot medical landmark detection gains much attention and achieves great success for its label-efficient training process. However, existing one-shot learning methods are highly specialized in a single domain and suffer domain preference heavily in the situation of multi-domain unlabeled data. Moreover, one-shot learning is not robust that it faces performance drop when annotating a sub-optimal image. To tackle these issues, we resort to developing a domain-adaptive one-shot landmark detection framework for handling multi-domain medical images, named Universal One-shot Detection (UOD). UOD consists of two stages and two corresponding universal models which are designed as combinations of domain-specific modules and domain-shared modules. In the first stage, a domain-adaptive convolution model is self-supervised learned to generate pseudo landmark labels. In the second stage, we design a domain-adaptive transformer to eliminate domain preference and build the global context for multi-domain data. Even though only one annotated sample from each domain is available for training, the domain-shared modules help UOD aggregate all one-shot samples to detect more robust and accurate landmarks. We investigated both qualitatively and quantitatively the proposed UOD on three widely-used public X-ray datasets in different anatomical domains (i.e., head, hand, chest) and obtained state-of-the-art performances in each domain. The code is at https://***/heqin-zhu/UOD_universal_oneshot_detection. © 2023, CC BY-NC-SA.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

ContribChain: A Stress-Balanced Blockchain Sharding Protocol with Node Contribution Awareness

arXiv

引用

arXiv 2025年

作者： Huang, Xinpeng Jie, Wanqing Zhang, Shiwen Yang, Haofu Qiu, Wangjie Zhang, Qinnan Huang, Huawei Xiong, Zehui Tang, Shaoting Zheng, Hongwei Zheng, Zhiming Institute of Artificial Intelligence Beihang University Beijing China Beijing Advanced Innovation Center for Future Blockchain and Privacy Computing Beihang University Beijing China Zhongguancun Laboratory Beijing China School of Software Engineering Sun Yat-Sen University China Singapore University of Technology and Design Singapore Beijing China

Existing blockchain sharding protocols have focused on eliminating imbalanced workload distributions. However, even with workload balance, disparities in processing capabilities can lead to differential stress among shards, resulting in transaction backlogs in certain shards. Therefore, achieving stress balance among shards in the dynamic and heterogeneous environment presents a significant challenge of blockchain sharding. In this paper, we propose ContribChain, a blockchain sharding protocol that can automatically be aware of node contributions to achieve stress balance. We calculate node contribution values based on the historical behavior to evaluate the performance and security of nodes. Furthermore, we propose node allocation algorithm NACV and account allocation algorithm P-Louvain, which both match shard performance with workload to achieve stress balance. Finally, we conduct extensive experiments to compare our work with state-of-the-art baselines based on real Ethereum transactions. The evaluation results show that P-Louvain reduces allocation execution time by 86% and the cross-shard transaction ratio by 7.5%. Meanwhile, ContribChain improves throughput by 35.8% and reduces the cross-shard transaction ratio by 16%. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Learning to Know Where to See: A Visibility-Aware Approach for Occluded Person Re-identification

Learning to Know Where to See: A Visibility-Aware Approach f...

引用

International Conference on Computer Vision (ICCV)

作者： Jinrui Yang Jiawei Zhang Fufu Yu Xinyang Jiang Mengdan Zhang Xing Sun Yingcong Chen Wei-Shi Zheng School of Computer Science and Engineering Sun Yat-sen University China Pazhou Lab Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Youtu Lab Tencent Microsoft Research Asia The Hong Kong University of Science and Technology The Hong Kong University of Science and Technology (Guangzhou)

ISBN: (纸本)9781665428132

Person re-identification (ReID) has gained an impressive progress in recent years. However, the occlusion is still a common and challenging problem for recent ReID methods. Several mainstream methods utilize extra cues (e.g., human pose information) to distinguish human parts from obstacles to alleviate the occlusion problem. Although achieving inspiring progress, these methods severely rely on the fine-grained extra cues, and are sensitive to the estimation error in the extra cues. In this paper, we show that existing methods may degrade if the extra information is sparse or noisy. Thus we propose a simple yet effective method that is robust to sparse and noisy pose information. This is achieved by discretizing pose information to the visibility label of body parts, so as to suppress the influence of occluded regions. We show in our experiments that leveraging pose information in this way is more effective and robust. Besides, our method can be embedded into most person ReID models easily. Extensive experiments validate the effectiveness of our model on common occluded person ReID datasets.

关键词： Estimation error Computer vision Annotations Computational modeling Robustness Noise measurement

来源：评论

学校读者我要写书评

暂无评论

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Learning as a Service

APPFLx: Providing Privacy-Preserving Cross-Silo Federated Le...

引用

IEEE International Conference on e-Science and Grid computing

作者： Zilinghan Li Shilan He Pranshu Chaturvedi Trung-Hieu Hoang Minseok Ryu E. A. Huerta Volodymyr Kindratenko Jordan Fuhrman Maryellen Giger Ryan Chard Kibaek Kim Ravi Madduri Data Science and Learning Division Argonne National Laboratory Lemont IL USA Department of Computer Science University of Illinois at Urbana-Champaign Urbana IL USA National Center for Supercomputing Applications University of Illinois at Urbana-Champaign Urbana IL USA Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign Urbana IL USA School of Computing and Augmented Intelligence Arizona State University Tempe AZ USA Department of Physics University of Illinois at Urbana-Champaign Urbana IL USA Department of Computer Science The University of Chicago Chicago IL USA Mathematics and Computer Science Division Argonne National Laboratory Lemont IL USA University of Chicago Consortium for Advanced Science and Engineering Chicago IL USA

Cross-silo privacy-preserving federated learning (PPFL) is a powerful tool to collaboratively train robust and generalized machine learning (ML) models without sharing sensitive (e.g., healthcare of financial) local data. To ease and accelerate the adoption of PPFL, we introduce APPFLx, a ready-to-use platform that provides privacy-preserving cross-silo federated learning as a service. APPFLx employs Globus authentication to allow users to easily and securely invite trustworthy collaborators for PPFL, implements several synchronous and asynchronous FL algorithms, streamlines the FL experiment launch process, and enables tracking and visualizing the life cycle of FL experiments, allowing domain experts and ML practitioners to easily orchestrate and evaluate cross-silo FL under one platform. APPFLx is available online at https://***

关键词：

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：