检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Yuan, Meng Zhuang, Fuzhen Zhang, Zhao Wang, Deqing Dong, Jin Institute of Artificial Intelligence Beihang University Beijing China Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Engineering Beihang University Beijing China Beijing Academy of Blockchain and Edge Computing Beijing China Zhongguancun Laboratory Beijing China

Since Knowledge Graphs (KGs) contain rich semantic information, recently there has been an influx of KG-enhanced recommendation methods. Most of existing methods are entirely designed based on euclidean space without considering curvature. However, recent studies have revealed that a tremendous graph-structured data exhibits highly non-euclidean properties. Motivated by these observations, in this work, we propose a knowledge-based multiple adaptive spaces fusion method for recommendation, namely MCKG. Unlike existing methods that solely adopt a specific manifold, we introduce the unified space that is compatible with hyperbolic, euclidean and spherical spaces. Furthermore, we fuse the multiple unified spaces in an attention manner to obtain the high-quality embeddings for better knowledge propagation. In addition, we propose a geometry-aware optimization strategy which enables the pull and push processes benefited from both hyperbolic and spherical spaces. Specifically, in hyperbolic space, we set smaller margins in the area near to the origin, which is conducive to distinguishing between highly similar positive items and negative ones. At the same time, we set larger margins in the area far from the origin to ensure the model has sufficient error tolerance. The similar manner also applies to spherical spaces. Extensive experiments on three real-world datasets demonstrate that the MCKG has a significant improvement over state-of-the-art recommendation methods. Further ablation experiments verify the importance of multi-space fusion and geometry-aware optimization strategy, justifying the rationality and effectiveness of MCKG. © 2023, CC BY.

关键词： Spheres

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Crowd Counting via Density Agency

arXiv

引用

arXiv 2022年

作者： Lin, Hui Ma, Zhiheng Hong, Xiaopeng Wang, Yaowei Su, Zhou School of Cyber Science and Engineering Xi’an Jiaotong University China Shenzhen Institute of Advanced Technology Chinese Academy of Science China School of Computer Science and Technology Harbin Institute of Technology China Peng Cheng Laboratory China Xi’an Jiaotong University China

In this paper, we propose a new agency-guided semi-supervised counting approach. First, we build a learnable auxiliary structure, namely the density agency to bring the recognized foreground regional features close to corresponding density sub-classes (agents) and push away background ones. Second, we propose a density-guided contrastive learning loss to consolidate the backbone feature extractor. Third, we build a regression head by using a transformer structure to refine the foreground features further. Finally, an efficient noise depression loss is provided to minimize the negative influence of annotation noises. Extensive experiments on four challenging crowd counting datasets demonstrate that our method achieves superior performance to the state-of-the-art semi-supervised counting methods by a large margin. Code is available. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Lessons Learned from Optimizing the Sunway Storage System for Higher Application I/O Performance

引用

Journal of computer science & technology 2020年第1期35卷 47-60页

作者： Qi Chen Kang Chen Zuo-Ning Chen Fellow CCF Wei Xue Xu Ji Bin Yang Department of Computer Science and Technology Beijing National Research Center for Information Science and Technology(BNRist)Tsinghua UniversityBeijing 100084China Chinese Academy of Engineering Beijing 100088China National Supercomputing Center in Wuxi Wuxi 214100China School of Software Shandong UniversityJinan 250101China

It is hard for applications to make full utilization of the peak bandwidth of the storage system in highperformance computers because of I/O interferences,storage resource misallocations and complex long I/O *** performed several studies to bridge this gap in the Sunway storage system,which serves the supercomputer Sunway *** locate these issues and connections between them,an end-to-end performance monitoring and diagnosis tool was developed to understand I/O behaviors of applications and the *** the help of the tool,we were about to find out the root causes of such performance barriers at the I/O forwarding layer and the parallel file system *** application-aware I/O forwarding allocation framework was used to address the I/O interferences and resource misallocations at the I/O forwarding layer.A performance-aware data placement mechanism was proposed to mitigate the impact of I/O interferences and performance variations of storage devices in the ***,applications obtained much better I/O *** the process,we also proposed a lightweight storage stack to shorten the I/O path of applications with N-N I/O *** paper summarizes these studies and presents the lessons learned from the process.

关键词： high performance computing I/O interference parallel file system performance optimization resource misallocation

来源：评论

学校读者我要写书评

暂无评论

FedMDC: Enabling Communication-Efficient Federated Learning over Packet Lossy Networks via Multiple Description Coding

FedMDC: Enabling Communication-Efficient Federated Learning ...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Yixuan Guan Xuefeng Liu Tao Ren Jianwei Niu State Key Laboratory of Virtual Reality Technology and Systems School of Computer Science and Engineering Beihang University Beijing China Zhongguancun Laboratory Beijing China State Key Laboratory of Intelligent Game Institute of Software Chinese Academy of Sciences Beijing China Zhengzhou University Research Institute of Industrial Technology School of Information Engineering Zhengzhou University Zhengzhou China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Federated learning (FL) generally suffers significant communication overhead from high-traffic gradient synchronization. The majority of existing studies on this problem aim at compressing gradients under the premise of reliable transmission. While transmission reliability can be ensured via TCP by default, the notably increased latency and retransmitted packets are prohibitive for most clients in FL. To tackle this issue, we propose FedMDC, a retransmission-free compression framework for FL over packet lossy networks. Given clients’ limited resources, FedMDC adopts multiple description coding to encode gradients into redundant descriptions for erasure resilience simply through multiplying an overcomplete matrix; and then quantizes these descriptions for compression. To further reduce quantization distortion and computational overhead, a reduced decoding algorithm is developed by decoding the aggregation of all clients’ encodings in conjunction with a customized dither quantization design. Besides, FedMDC explicitly supports adaptive bitrates subject to clients’ heterogeneous communication budgets, which maximize resource utilization to facilitate distortion reduction and accelerate model convergence. Theoretical analysis and experimental results both demonstrate the effectiveness of our scheme.

关键词： Quantization (signal) Federated learning Distortion Propagation losses Encoding Decoding Reliability Synchronization Resource management Resilience

来源：评论

学校读者我要写书评

暂无评论

Research Progress of Parallel Control and Management

引用

IEEE/CAA Journal of Automatica Sinica 2020年第2期7卷 355-367页

作者： Gang Xiong Xisong Dong Hao Lu Dayong Shen State Key Laboratory of Management and Control for Complex Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Computer Science and Technology Beijing Institute of TechnologyBeijing 100081China College of Systems Engineering National University of Defense TechnologyChangsha 410073China

Based on ACP(artificial systems,computational experiments,and parallel execution)methodology,parallel control and management has become a popularly systematic and complete solution for the control and management of complex *** paper focuses on summarizing comprehensive review of the research literature of parallel control and management achieved in the recent years including the theoretical framework,core technologies,and the application *** future research,application directions,and suggestions are also discussed.

关键词： ACP methodology artificial systems computational experiments parallel control parallel management parallel systems

来源：评论

学校读者我要写书评

暂无评论

Frequency-Guided Diffusion Model with Perturbation Training for Skeleton-Based Video Anomaly Detection

arXiv

引用

arXiv 2024年

作者： Tan, Xiaofeng Wang, Hongsong Geng, Xin Wang, Liang School of Computer Science and Engineering Southeast University Nanjing211189 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education China China School of Artificial Intelligence University of Chinese Academy of Sciences China

Video anomaly detection (VAD) is a vital yet complex open-set task in computer vision, commonly tackled through reconstruction-based methods. However, these methods struggle with two key limitations: (1) insufficient robustness in open-set scenarios, where unseen normal motions are frequently misclassified as anomalies, and (2) an overemphasis on, but restricted capacity for, local motion reconstruction, which are inherently difficult to capture accurately due to their diversity. To overcome these challenges, we introduce a novel frequency-guided diffusion model with perturbation training. First, we enhance robustness by training a generator to produce perturbed samples, which are similar to normal samples and target the weakness of the reconstruction model. This training paradigm expands the reconstruction domain of the model, improving its generalization to unseen normal motions. Second, to address the overemphasis on motion details, we employ the 2D Discrete Cosine Transform (DCT) to separate high-frequency (local) and low-frequency (global) motion components. By guiding the diffusion model with observed high-frequency information, we prioritize the reconstruction of low-frequency components, enabling more accurate and robust anomaly detection. Extensive experiments on five widely used VAD datasets demonstrate that our approach surpasses state-of-the-art methods, underscoring its effectiveness in open-set scenarios and diverse motion contexts. Our project website is https://***/projects/FG-Diff/***. © 2024, CC BY.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events

EventTrojan: Manipulating Non-Intrusive Speech Quality Asses...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ying Ren Kailai Shen Zhe Ye Diqun Yan Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Juphoon System Software Co. Ltd Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech’s mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods.

关键词： Measurement Resistance Adaptation models Multimedia systems Current measurement Artificial neural networks Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

RSGPT: A Remote Sensing Vision Language Model and Benchmark

arXiv

引用

arXiv 2023年

作者： Hu, Yuan Yuan, Jianlong Wen, Congcong Lu, Xiaonan Li, Xiang The DAMO Academy Alibaba Group Beijing China The Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi United Arab Emirates The University of Chinese Academy of Sciences Beijing China The King Abdullah University of Science and Technology Jeddah Saudi Arabia

The emergence of large-scale Large Language Models (LLMs), with GPT-4 as a prominent example, has significantly propelled the rapid advancement of Artificial General Intelligence (AGI) and sparked the revolution of Artificial Intelligence 2.0. In the realm of remote sensing, there is a growing interest in developing large vision language models (VLMs) specifically tailored for data analysis in this domain. However, current research predominantly revolves around visual recognition tasks, lacking comprehensive, large-scale image-text datasets that are aligned and suitable for training large VLMs, which poses significant challenges to effectively training such models for remote sensing applications. In computer vision, recent research has demonstrated that fine-tuning large vision language models on small-scale, high-quality datasets can yield impressive performance in visual and language understanding. These results are comparable to state-of-the-art VLMs trained from scratch on massive amounts of data, such as GPT-4. Inspired by this captivating idea, in this work, we build a high-quality Remote Sensing Image Captioning dataset (RSICap) that facilitates the development of large VLMs in the remote sensing field. Unlike previous remote sensing datasets that either employ model-generated captions or short descriptions, RSICap comprises 2,585 human-annotated captions with rich and high-quality information. This dataset offers detailed descriptions for each image, encompassing scene descriptions (e.g., residential area, airport, or farmland) as well as object information (e.g., color, shape, quantity, absolute position, etc). To facilitate the evaluation of VLMs in the field of remote sensing, we also provide a benchmark evaluation dataset called RSIEval. This dataset consists of human-annotated captions and visual question-answer pairs, allowing for a comprehensive assessment of VLMs in the context of remote sensing. We are actively engaged in expanding the scale of thes

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

UniAutoML: A Human-Centered Framework for Unified Discriminative and Generative AutoML with Large Language Models

arXiv

引用

arXiv 2024年

作者： Guo, Jiayi Chen, Zan Ji, Yingrui Zhang, Liyun Luo, Daqin Li, Zhigang Shen, Yiqin Glasgow College University of Electronic Science and Technology of China Chengdu China School of Engineering University of Glasgow Glasgow United Kingdom Toursun Synbio Shanghai China Aerospace Information Research Institute Chinese Academy of Sciences Beijing China School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences Beijing China School of Information and Software Engineering University of Electronic Science and Technology of China Chengdu China Research Institute Ubtech Robotics Corp Shenzhen China Qiyuan Lab. Beijing China Department of Computer Science Johns Hopkins University MD United States

Automated Machine Learning (AutoML) can streamline the complexities of machine learning pipelines. However, existing AutoML frameworks focus on discriminative tasks leaving generative tasks unexplored. Moreover, existing AutoML frameworks often lack interpretability and user engagement during the model development and training process, due to the absence of human-centered designs. To address these challenges, we propose UniAutoML, a human-centered AutoML framework that leverages Large Language Models (LLMs) to unify the automation of both discriminative (e.g., Transformers and CNNs for classification or regression) and generative tasks (e.g., fine-tuning diffusion models or LLMs). UniAutoML enables natural language interactions between users and the framework to provide real-time feedback and progress updates, thus enhancing the interpretability, transparency, and user control, where users can seamlessly modify or refine the model training in response to evolving needs. To ensure the safety and reliability of LLM-generated content, UniAutoML incorporates a safety guard-line that filter inputs and censor outputs. We evaluated UniAutoML’s performance and usability through experiments conducted on eight diverse datasets and user studies involving 25 participants. Our results demonstrate that UniAutoML not only achieves higher performance but also improves user control and trust in the AutoML process, which makes ML more accessible and intuitive for a broader audience. The code for UniAutoML is available at: https://***/richarf22/UniAutoML. © 2024, CC BY.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Enhancing Mobile Robot Speed Control: PID Controller Optimization with Bio-Inspired Algorithms

Enhancing Mobile Robot Speed Control: PID Controller Optimiz...

引用

Expert Clouds and Applications (ICOECA), International Conference on

作者： Sangeeta Singh Uma HR Bhargav H K Sujata Arya Praveen Singh Natrayan L Department of Electrical Engineering JSS Academy of Technical Education Noida Uttar Pradesh India Department of Computer Science and Engineering BGS Institute of Technology Adichunchanagiri University Mandya Karnataka India Department of Computer Science and Engineering Basaveshwar Engineering College Bagalkot Karnataka India Faculty of Law Symbiosis Law School (SLS) Symbiosis International (Deemed University) (SIU) Viman Nagar Pune Maharashtra India Department of Management Studies Graphic Era Deemed to be University Dehradun Uttarakhand India Department of Mechanical Engineering Saveetha School of Engineering SIMATS Chennai Tamil Nadu India

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

This research study presents an investigation into the optimization of PID controllers using bio-inspired algorithms for controlling the speed of mobile robots. The study begins by identifying a mathematical model that accurately represents the dynamics of the DC motor used in robots. Three different tuning methods, namely Ziegler-Nichols (ZN), Flower Pollination Algorithm (FPA), and Fish Swarm Optimization (FSO) are then utilized to design the PID controllers. The primary objective is to enhance the speed control performance of mobile robots. To evaluate the effectiveness of the optimization methods, the set speed is given to each of the three controllers, and their performance is compared. The results demonstrate that the optimization techniques outperform the conventional ZN method in achieving the desired speed control. Among the two bio-inspired algorithms, FPA yields exceptional outcomes in terms of time characteristics. The comparison of time characteristics serves as a benchmark for evaluating the performance of the controllers. It reveals that bio-inspired optimization methods, especially FPA, significantly improve the speed control of mobile robots. The time characteristics, such as rise time, settling time, overshoot, peak time, and peak value, illustrate the superior performance achieved through the optimization process.

关键词： Accuracy Uncertainty Heuristic algorithms Velocity control Optimization methods Robot sensing systems Stability analysis

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：