检索结果-内蒙古大学图书馆

2022 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2022

作者： Dai, Zhigang Cai, Bolun Chen, Junying South China University of Technology Key Lab. of Big Data & Intell. Robot MoE School of Software Engineering Guangzhou China Tencent Wechat Ai Guangzhou China

ISBN: (数字)9781665452588

ISBN: (纸本)9781665452588

Momentum Contrast (MoCo) achieves great success for unsupervised visual representation learning. However, there are a lot of supervised and semi-supervised datasets, which are already lab.led. To fully utilize the lab.l annotations, we propose Unified Momentum Contrast (UniMoCo), which extends MoCo to support arbitrary ratios of lab.led data and unlab.led data training. Compared with MoCo, UniMoCo has two modifications as follows: (1) Different from a single positive pair in MoCo, we maintain multiple positive pairs on-the-fly by comparing the query lab.l to a lab.l queue. (2) We propose a Unified Contrastive (UniCon) loss to support an arbitrary number of positives and negatives in a unified pair-wise optimization perspective. Our UniCon is more reasonable and powerful than the supervised contrastive loss in theory and practice. In our experiments, we pre-train multiple UniMoCo models with different ratios of ImageNet lab.ls and evaluate the performance on various downstream tasks. Experiment results show that UniMoCo generalizes well for unsupervised, semi-supervised and fully-supervised visual representation learning. Besides, we surprisingly find that UniMoCo performs best with 60% ImageNet lab.ls for COCO and VOC transfer learning. The code is availab.e: https://***/dddzg/unimoco. © 2022 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Ppt4j: Patch Presence Test for Java Binaries 24

Ppt4j: Patch Presence Test for Java Binaries

引用

44th ACM/IEEE International Conference on software engineering, ICSE 2024

作者： Pan, Zhiyuan Hu, Xing Xia, Xin Zhan, Xian Lo, David Yang, Xiaohu Zhejiang University The State Key Laboratory of Blockchain and Data Security Hangzhou China Huawei Software Engineering Application Technology Lab Hangzhou China The Hong Kong Polytechnic University Hong Kong School of Computing and Information Systems Singapore Management University Singapore

ISBN: (纸本)9798400702174

The number of vulnerabilities reported in open source software has increased substantially in recent years. Security patches provide the necessary measures to protect software from attacks and vulnerabilities. In practice, it is difficult to identify whether patches have been integrated into software, especially if we only have binary files. Therefore, the ability to test whether a patch is applied to the target binary, a.k.a. patch presence test, is crucial for practitioners. However, it is challenging to obtain accurate semantic information from patches, which could lead to incorrect results. In this paper, we propose a new patch presence test framework named Ppt4j (Patch Presence Test forJava Binaries). Ppt4j is designed for open-source Java libraries. It takes Java binaries (i.e. bytecode files) as input, extracts semantic information from patches, and uses feature-based techniques to identify patch lines in the binaries. To evaluate the effectiveness of our proposed approach Ppt4j, we construct a dataset with binaries that include 110 vulnerabilities. The results show that Ppt4j achieves an F1 score of 98.5% with reasonable efficiency, improving the baseline by 14.2%. Furthermore, we conduct an in-the-wild evaluation of Ppt4j on JetBrains IntelliJ IDEA. The results suggest that a third-party library included in the software is not patched for two CVEs, and we have reported this potential security problem to the vendor. © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Head360: Learning a Parametric 3D Full-Head for Free-View Synthesis in 360◦

arXiv

引用

arXiv 2024年

作者： He, Yuxiao Zhuang, Yiyu Wang, Yanwen Yao, Yao Zhu, Siyu Li, Xiaoyu Zhang, Qi Cao, Xun Zhu, Hao State Key Laboratory for Novel Software Technology Nanjing University China Fudan University Shanghai China Tencent AI Lab. Shenzhen China

Creating a 360◦ parametric model of a human head is a very challenging task. While recent advancements have demonstrated the efficacy of leveraging synthetic data for building such parametric head models, their performance remains inadequate in crucial areas such as expression-driven animation, hairstyle editing, and text-based modifications. In this paper, we build a dataset of artist-designed high-fidelity human heads and propose to create a novel parametric 360-degree renderable parametric head model from it. Our scheme decouples the facial motion/shape and facial appearance, which are represented by a classic parametric 3D mesh model and an attached neural texture, respectively. We further propose a training method for decompositing hairstyle and facial appearance, allowing free-swapping of the hairstyle. A novel inversion fitting method is presented based on single image input with high generalization and fidelity. To the best of our knowledge, our model is the first parametric 3D full-head that achieves 360◦ free-view synthesis, image-based fitting, appearance editing, and animation within a single model. Experiments show that facial motions and appearances are well disentangled in the parametric space, leading to SOTA performance in rendering and animating quality. The code and SynHead100 dataset are released in https://***/projects/Head360. Copyright © 2024, The Authors. All rights reserved.

关键词： Animation

来源：评论

学校读者我要写书评

暂无评论

Photovoltaic Power prediction based on long and short-term memory neural networks 5

Photovoltaic Power prediction based on long and short-term m...

引用

5th International Conference on Electronic Communication and Artificial Intelligence, ICECAI 2024

作者： Ma, Dongjin Gao, Yingcai Zhang, Lei Dai, Qin China Energy Science and Technology Research Institute Co. Ltd. State Key Lab. of Low-carbon Smart Coal-fired Power Generation and Ultra-clean Emission Nanjing China Shenyang Institute of Engineering Shenyang China

ISBN: (纸本)9798350386943

With the growing global interest in renewable energy, photovoltaic (PV) power generation has become an important form of energy. However, the prediction of PV power is still a challenge due to the uncertainty of factors such as weather. In this paper, we propose a PV power prediction model based on Long Short-Term Memory (LSTM) neural network, which aims to improve the prediction accuracy by learning the patterns and trends of historical data. © 2024 IEEE.

关键词： artificial intelligence long and short-term memory neural networks photovoltaic power generation renewable energy sources

来源：评论

学校读者我要写书评

暂无评论

Measurement-based Path Loss Prediction and Analysis in Water Scenarios

Measurement-based Path Loss Prediction and Analysis in Water...

引用

2024 IEEE International Conference on Computational Electromagnetics, ICCEM 2024

作者： Li, Hanpeng Chen, Xiaomin Li, Hangang Ma, Jian Ye, Xuchao Song, Lixin Zhang, Taotao Zhong, Weizhi Zhu, Qiuming Nanjing University of Aeronautics and Astronautics College of Electronic and Information Engineering Nanjing211106 China Aviation Key Laboratory of Science and Technology On Aero Electromechanical System Integration Nanjing211106 China State Key Lab. of Complex Electromagnetic Environment Effects On Electronics and Information System Luoyang471003 China

ISBN: (纸本)9798350383317

Unmanned aerial vehicles (UAVs) have enabled the unmanned management of water areas. Path loss (PL) serves as a critical factor that affects the UAV communication quality. In this work, a PL model for UAV channel in water scenarios is proposed, aiming to explore the multidimensional relationship between transceiver distance, carrier frequency, UAV height, and PL by constructing an Artificial Neural Network (ANN). Moreover, channel measurements are conducted in a river area, and the obtained data are analyzed using the proposed ANN model as well as the close-in (CI) model. The analysis results demonstrates that the PL increases initially and then declines as the UAV height increases. The proposed ANN model has higher prediction accuracy than the classic empirical model, and can achieve precise prediction of the PL in water scenarios. © 2024 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Supercomputer Supported Online Deep Learning Techniques for High Throughput EEG Prediction

Supercomputer Supported Online Deep Learning Techniques for ...

引用

2021 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2021

作者： Li, Xiang Zhang, Yazhou Li, Jing China Nanjing University Software Engineering College Zhengzhou University of Light Industry State Key Lab. for Novel Software Technology China Jiuquan Satellite Launch Center China

ISBN: (纸本)9781665401265

Electroencephalogram (EEG) is a precise reflection of the brain activities and has been widely studied in clinical medicine, neuroscience, brain interface, etc. Intelligent prediction of the EEG's evolution accurately plays important roles in several application areas, such as epilepsy seizure forecasting and neonatal brain monitoring. Nevertheless, when the prediction service is deployed as a business service on the Cloud and open for public usage, there are several problems that need to be resolved: (i) how to design a computation platform to process the high-throughput multi-source EEG data, which arrives sequentially and increases rapidly when the services are rapidly promoted, namely tackling the 'high-throughput computing' problem;(ii) how to develop a deep learning model to capture the complex EEG distribution as well as the anomaly patterns that could evolve dynamically, namely tackling the 'concept drift' problem for non-stationary EEG signals. To tackle these challenges, we propose an Evolutive Convolutional Neural Network (ECNN) and the corresponding supercomputer supported distributed computation system. The ECNN model can dynamically reweighting the sub-structure of the model from data streams in an online learning fashion, by which the capacity scalab.lity and sustainability are introduced into the model. As far as we know, it is the first work that introduce supercomputer supported online deep learning techniques into EEG prediction research. © 2021 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Formally Verified C Code Generation from Hybrid Communicating Sequential Processes

Formally Verified C Code Generation from Hybrid Communicatin...

引用

IEEE/ACM International Conference on Cyber-Physical Systems (ICCPS)

作者： Shuling Wang Zekun Ji Xiong Xu Bohua Zhan Qiang Gao Naijun Zhan State Key Lab. of Computer Science Institute of Software Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798350369274

ISBN: (纸本)9798350369281

Hybrid Communicating Sequential Processes (HCSP) is a formal model for hybrid systems, including primitives for evolution along an ordinary differential equation (ODE), communication, and parallel composition. Code generation is needed to convert HCSP models into code that can be executed in practice, and the correctness of this conversion is essential to ensure that the generated code accurately reflects the formal model. In this paper, we propose a code generation algorithm from HCSP to C with POSIX library for concurrency. The main difficulties include how to bridge the gap between the synchronized communication model in HCSP and the use of mutexes for synchronization in C, and how to discretize evolution along ODEs and support interrupt of ODE evolution by communication. To prove the correctness of code generation, we define a formal semantics for POSIX C, and build transition system models for both HCSP and C programs. We then define an approximate bisimulation relation between traces of transition systems, and show that under certain robustness conditions for HCSP, the generated C program is approximately bisimilar to the original model. Finally, we evaluate the code generation algorithm on a detailed model for automatic cruise control, showing its utility on real-world examples.

关键词： Industries Codes Semantics Ordinary differential equations Mathematical models Robustness Hybrid power systems

来源：评论

学校读者我要写书评

暂无评论

A 3.5~7.5 GHz GaAs HEMT Cryogenic Low-NoiseAmplifier Achieving 5 Kelvin Noise Temperature for Qubits Measurement

A 3.5~7.5 GHz GaAs HEMT Cryogenic Low-NoiseAmplifier Achievi...

引用

2023 IEEE/MTT-S International Microwave Symposium, IMS 2023

作者： Peng, Yatao Zhong, Youpeng Guo, Zechen Liu, Song Yu, Dapeng University of Macau State Key Lab. of Analog and Mixed-Signal VLSI IME/ECE of FST China Shenzhen International Quantum Academy China SUSTech Shenzhen Institute for Quantum Science and Engineering China

ISBN: (纸本)9798350347647

The measurement of the fast-increasing number of qubits necessitates the use of a large number of specialized cryogenic low-noise amplifiers (LNAs).). This work presents a broadband LNA designed with discrete GaAs HEMT components which operate well at ~3.6 K temperature. The dual-frequency optimum noise matching network and output matching elements of the first stage were employed to optimize the equivalent noise temperature (NT) and the input return loss in a wideband. Measurement results at 3.6 K ambient temperature show that the LNA achieved an equivalent NT of 30 dB in the 3.5 GHz to 7.5 GHz band with a minimum of 5 Kelvin at ~6.5 GHz. The best visibility of ~0.891 is achieved when using the LNA to observe a superconducting transmon qubit without using a JPA. © 2023 IEEE.

关键词： Low noise amplifiers

来源：评论

学校读者我要写书评

暂无评论

On Efficient Packet Batching and Resource Allocation for GPU based NFV Acceleration 31

On Efficient Packet Batching and Resource Allocation for GPU...

引用

31st IEEE/ACM International Symposium on Quality of Service, IWQoS 2023

作者： Zeng, Deze Zhu, Andong Gu, Lin Chen, Quan Guo, Minyi School of Computer Science China University of Geosciences Hubei Wuhan China Nanjing University State Key Lab. for Novel Software Technology Nanjing China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China Shanghai Jiao Tong University Department of Computer Science and Engineering Shanghai China

ISBN: (纸本)9798350399738

Network Function Virtualization (NFV) has already become an essential technology for improving the scalab.lity and flexibility of modern computer networks. The performance gap has become the main issue that impedes the development of NFV. GPUs, with massive parallel processors, are advocated to accelerate the Virtualized Network Functions (VNFs). However, the special architecture and workflow of GPUs introduce new challenges, especially on the batched processing, and resource allocation. In this paper, we propose GPU-based NFV Acceleration framework (GNFA) with an efficient packet batching and resource allocation solution. Considering the increased latency caused by the accumulation of the GPU kernel invoking overhead, we first invent a latency reduction mechanism called SM Performance Compensation (SPC). A Partition and Adjustment based Batching and Resource Allocation (PABARA) algorithm that jointly considers batch size tuning and GPU thread allocation is also proposed. We have practically implemented GNFA and extensively evaluated its performance on some well-known VNFs. The experiment results show that GNFA can effectively promote the GPU resource utilization and improve the NFV performance in terms of per-packet latency. © 2023 IEEE.

关键词： Graphics processing unit

来源：评论

学校读者我要写书评

暂无评论

New Algorithms for Distributed Fair k-Center Clustering: Almost Accurate as Sequential Algorithms 23

New Algorithms for Distributed Fair k-Center Clustering: Alm...

引用

23rd International Conference on Autonomous Agents and Multiagent Systems, AAMAS 2024

作者： Wu, Xiaoliang Feng, Qilong Huang, Ziyun Xu, Jinhui Wang, Jianxin School of Computer Science and Engineering Central South University Xiangjiang Laboratory Changsha China Department of Computer Science and Software Engineering Penn State Erie The Behrend College Erie United States Department of Computer Science and Engineering State University of New York at Buffalo Buffalo United States Hunan Provincial Key Lab on Bioinformatics Central South University Xiangjiang Laboratory Changsha China

Fair clustering problems have been paid lots of attention recently. In this paper, we study the k-Center problem under the group fairness and data summarization fairness constraints, denoted as Group Fair k-Center (GFkC) and Data Summarization Fair k-Center (DSFkC), respectively, in the massively parallel computational (MPC) distributed model. The previous best results for the above two problems in the MPC model are a 9-approximation with violation 7 (WWW 2022) and a (17 + ∊)-approximation without fairness violation (ICML 2020), respectively. In this paper, we obtain a (3 + ∊)- approximation with violation 1 for the GFkC problem in the MPC model, which is almost as accurate as the best known approximation ratio 3 with violation 1 for the sequential algorithm of the GFkC problem. Moreover, for the DSFkC problem in the MPC model, we obtain a (4 + ∊)-approximation without fairness violation, which is very close to the best known approximation ratio 3 for the sequential algorithm of the DSFkC problem. Empirical experiments show that our distributed algorithms perform better than existing state-of-the-art distributed methods for the above two problems. © 2024 International Foundation for Autonomous Agents and Multiagent Systems.

关键词： Machine learning

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：