检索结果-内蒙古大学图书馆

Global video object segmentation with spatial constraint module

Computational Visual Media 2023年第2期9卷 385-400页

作者： Yadang Chen Duolin Wang Zhiguo Chen Zhi-Xin Yang Enhua Wu Engineering Research Center of Digital Forensics Ministry of EducationSchool of Computer and SoftwareNanjing University of Information Science and TechnologyNanjing 210044China State Key Laboratory of Internet of Things for Smart City Department of Electromechanical EngineeringUniversity of MacaoMacao 999078China State Key Laboratory of Computer Science Institute of SoftwareUniversity of Chinese Academy of SciencesBeijing 100190China Faculty of Science and Technology University of MacaoMacao 999078China

We present a lightweight and efficient semisupervised video object segmentation network based on the space-time memory *** some extent,our method solves the two difficulties encountered in traditional video object segmentation:one is that the single frame calculation time is too long,and the other is that the current frame’s segmentation should use more information from past *** algorithm uses a global context(GC)module to achieve highperformance,real-time *** GC module can effectively integrate multi-frame image information without increased memory and can process each frame in real ***,the prediction mask of the previous frame is helpful for the segmentation of the current frame,so we input it into a spatial constraint module(SCM),which constrains the areas of segments in the current *** SCM effectively alleviates mismatching of similar targets yet consumes few additional *** added a refinement module to the decoder to improve boundary *** model achieves state-of-the-art results on various datasets,scoring 80.1%on YouTube-VOS 2018 and a J&F score of 78.0%on DAVIS 2017,while taking 0.05 s per frame on the DAVIS 2016 validation dataset.

关键词： video object segmentation semantic segmentation global context(GC)module spatial constraint

来源：评论

学校读者我要写书评

暂无评论

Audio2AB:Audio-driven collaborative generation of virtual character animation

引用

虚拟现实与智能硬件（中英文） 2024年第1期6卷 56-70页

作者： Lichao NIU Wenjun XIE Dong WANG Zhongrui CAO Xiaoping LIU School of Computer Science and Information Engineering Hefei University of TechnologyHeifei 230009China School of Software Hefei University of TechnologyHeifei 230009China Anhui Province Key Laboratory of Industry Safety and Emergency Technology Hefei University of TechnologyHefei 230601China

Background Considerable research has been conducted in the areas of audio-driven virtual character gestures and facial animation with some degree of ***,few methods exist for generating full-body animations,and the portability of virtual character gestures and facial animations has not received sufficient *** Therefore,we propose a deep-learning-based audio-to-animation-and-blendshape(Audio2AB)network that generates gesture animations and ARK it's 52 facial expression parameter blendshape weights based on audio,audio-corresponding text,emotion labels,and semantic relevance labels to generate parametric data for full-body *** parameterization method can be used to drive full-body animations of virtual characters and improve their *** the experiment,we first downsampled the gesture and facial data to achieve the same temporal resolution for the input,output,and facial *** Audio2AB network then encoded the audio,audio-corresponding text,emotion labels,and semantic relevance labels,and then fused the text,emotion labels,and semantic relevance labels into the audio to obtain better audio ***,we established links between the body,gestures,and facial decoders and generated the corresponding animation sequences through our proposed GAN-GF loss *** By using audio,audio-corresponding text,and emotional and semantic relevance labels as input,the trained Audio2AB network could generate gesture animation data containing blendshape ***,different 3D virtual character animations could be created through *** The experimental results showed that the proposed method could generate significant gestures and facial animations.

关键词： Audio-driven Virtual character Full-body animation Audio2AB Blendshape GAN-GF

来源：评论

学校读者我要写书评

暂无评论

Combining KNN with AutoEncoder for Outlier Detection

引用

Journal of computer Science & technology 2024年第5期39卷 1153-1166页

作者： Shu-Zheng Liu Shuai Ma Han-Qing Chen Li-Zhen Cui Jie Ding State Key Laboratory of Software Development Environment Beihang UniversityBeijing 100191China School of Software Shandong UniversityJinan 250100China Joint SDU-NTU Centre for Artificial Intelligence Research Shandong UniversityJinan 250100China School of Computer Science Jiangsu University of Science and TechnologyZhenjiang 212003China

K-nearest neighbor(KNN)is one of the most fundamental methods for unsupervised outlier detection because of its various advantages,e.g.,ease of use and relatively high ***,most data analytic tasks need to deal with high-dimensional data,and the KNN-based methods often fail due to“the curse of dimensionality”.AutoEncoder-based methods have recently been introduced to use reconstruction errors for outlier detection on high-dimensional data,but the direct use of AutoEncoder typically does not preserve the data proximity relationships well for outlier *** this study,we propose to combine KNN with AutoEncoder for outlier ***,we propose the Nearest Neighbor AutoEncoder(NNAE)by persevering the original data proximity in a much lower dimension that is more suitable for performing ***,we propose the K-nearest reconstruction neighbors(K NRNs)by incorporating the reconstruction errors of NNAE with the K-distances of KNN to detect ***,we develop a method to automatically choose better parameters for optimizing the structure of ***,using five real-world datasets,we experimentally show that our proposed approach NNAE+K NRN is much better than existing methods,i.e.,KNN,Isolation Forest,a traditional AutoEncoder using reconstruction errors(AutoEncoder-RE),and Robust AutoEncoder.

关键词： outlier detection AutoEncoder K-nearest neighbor(KNN) unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Desensitization Method of Image Data in the Internet of Vehicles Based on Instance Segmentation 2

Desensitization Method of Image Data in the Internet of Vehi...

引用

2nd International Conference on Algorithms, Microchips, and Network Applications, AMNA 2023

作者： Li, Shuang Zhou, Yue Zhang, Xin Zhang, Meng School of Computer Science Fudan University 200433 China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai Development Center of Computer Software Technology 201112 China

ISBN: (纸本)9781510664791

With the continuous development of intelligent connected vehicle industry, cameras and other vehicle-mounted devices are widely used, so the amount of data collection is increasing. There is a large amount of sensitive information hidden in the image data generated by connected vehicles. Once the data leakage event occurs, it may cause very serious consequences. In order to improve the security of connected vehicle data and reduce the threat of sensitive information leakage in image data, this paper provides a desensitization process of connected vehicle image data, and desensitizes sensitive information based on instance segmentation technology. In this paper, a real road image dataset is collected, and realizes desensitization of the modified dataset based on proposed framework. © 2023 SPIE.

关键词： Vehicles

来源：评论

学校读者我要写书评

暂无评论

A Reduced State-Space Generation Method for Concurrent Systems Based on CPN-PR Model

引用

IEEE Transactions on computer-Aided Design of Integrated Circuits and Systems 2025年第6期44卷 2328-2342页

作者： Zhong, Wenjie Sun, Tao Zhou, Jian-Tao Wang, Zhuowei Song, Xiaoyu Inner Mongolia University College of Computer Science the Engineering Research Center of Ecological Big Data Ministry of Education the Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software the Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot010000 China Guangdong University of Technology School of Computer Science and Technology Guangzhou510006 China Portland State University Department of Electrical and Computer Engineering PortlandOR97207 United States

Colored Petri nets (CPNs) provide descriptions of the concurrent behaviors for software and hardware. Model checking based on CPNs is an effective method to simulate and verify the concurrent behavior in system design. However, the model-checking method traverses the full state space, which suffers from the state-space explosion problem. A reduced state-space generation method related to the property of concurrent systems is proposed. Specifically, we extend CPNs to define a property-related model (CPN-PR) and give a property-related analysis method whose results can be used to generate the CPN-PR model. A reduced state-space generation method is developed based on enabled binding element filtering rules. The stutter trace equivalence between the state spaces of CPN and CPN-PR has been proven by showing that the reduced state space may not change the model-checking result. A comparison experiment is conducted to demonstrate the effectiveness of our method. © 1982-2012 IEEE.

关键词： Model checking

来源：评论

学校读者我要写书评

暂无评论

RSCache: A Tail Latency Friendly Cache Based on NVMe SSDs 22

RSCache: A Tail Latency Friendly Cache Based on NVMe SSDs

引用

22nd IEEE International Symposium on Parallel and Distributed Processing with Applications, ISPA 2024

作者： Lu, Jincheng Cai, Miao Ye, Baoliu Hohai University College of Computer Science and Software Engineering Nanjing China Nanjing University of Aeronautics and Astronautics College of Computer Science and Technology Nanjing China Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

ISBN: (纸本)9798331509712

High fan-out requests are prevalent in systems employing multi-tier architectures. These requests are divided into several sub-requests for parallel processing. However, a high fan-out request must await all sub-requests to be completed before returning, but the processing times of sub-requests are unpredictable due to their differences in characteristics, such as data volume and data popularity. Meanwhile, existing SSD-based caches struggle to adjust request processing speeds to ensure timely handling. As a result, some sub-requests are delayed, affecting the overall latency and causing long tail latency *** paper proposes RSCache, a tail latency-friendly cache based on NVMe SSDs. RSCache combines the NVMe Weighted Round-robin (WRR) arbitration mechanism with a priority-based scheduling mechanism to enable differentiated request processing. We propose a fan-out size-based priority assignment strategy along with a latency-aware sub-request sorting method. They collaborate to prioritize sub-requests according to their impacts on tail latency and schedule them to NVMe priority queues with various processing speeds, effectively reducing the processing time variations among sub-requests. In addition, we balance the load across queues to avoid congestion with a novel feedback mechanism. We implement the prototype of RSCache based on SPDK. Our experiments demonstrate that RSCache reduces tail latency by up to 40% and improves throughput by two times compared to state-of-the-art SSD-based cache designs. © 2024 IEEE.

关键词： Parallel architectures

来源：评论

学校读者我要写书评

暂无评论

Keyword extraction method based on complex network

引用

International Journal of Information and Communication technology 2024年第4期25卷 323-335页

作者： Yang, Zhen Gong, Huajian Ma, Weiyun Yin, Chunlin Li, Jie Liu, Siyang Zhu, Hua Zhao, Na Electric Power Research Institute of Yunnan Power Grid Kunming650217 China School of Computer Science and Technology Xidian University Xian710000 China Key Laboratory in Software Engineering of Yunnan Province School of Software Yunnan University Kunming650091 China

Keyword extraction has a wide range of applications in the field of natural language processing. Many research results on keyword extraction at present. Among them, keyword extraction methods are based on complex networks do not require a lot of data training in advance and are simple to implement. This paper analyses and realises the application of complex network theory in the Chinese news keyword extraction task. We collected and analysed 2,061 news texts from Sina website as experimental data, and found that the number of keywords extracted affected the performance of keyword extraction method. We also compared the performance of our algorithm with other keyword extraction algorithms. The experiments verify the accuracy and effectiveness of complex networks in keyword extraction of Chinese news texts. Based on PyQt and TextRank, a news text keyword analysis platform is constructed to realise the visualisation of text network and the extraction of Chinese news keywords Copyright © 2024 Inderscience Enterprises Ltd.

关键词： complex network keyword extraction text network TextRank

来源：评论

学校读者我要写书评

暂无评论

A prompt-based approach to adversarial example generation and robustness enhancement

引用

Frontiers of computer Science 2024年第4期18卷 85-96页

作者： Yuting YANG Pei HUANG Juan CAO Jintao LI Yun LIN Feifei MA Key Lab of Intelligent Information Processing of Chinese Academy of Sciences(CAS) Institute of Computing TechnologyCASBeijing 100190China School of Computer Science and Technology University of Chinese Academy of SciencesBeijing 100049China Department of Computer Science Stanford UniversityCA 94305USA School of Computing National University of SingaporeSingapore 119077Singapore Laboratory of Parallel Software and Computational Science Institute of SoftwareChinese Academy of SciencesBeijing 100190China

Recent years have seen the wide application of natural language processing(NLP)models in crucial areas such as finance,medical treatment,and news media,raising concerns about the model robustness and *** find that prompt paradigm can probe special robust defects of pre-trained language *** prompt texts are first constructed for inputs and a pre-trained language model can generate adversarial examples for victim models via *** results show that prompt paradigm can efficiently generate more diverse adversarial examples besides synonym ***,we propose a novel robust training approach based on prompt paradigm which incorporates prompt texts as the alternatives to adversarial examples and enhances robustness under a lightweight minimax-style optimization *** on three real-world tasks and two deep neural models show that our approach can significantly improve the robustness of models to resist adversarial attacks.

关键词： robustness adversarial example prompt learning pre-trained language model

来源：评论

学校读者我要写书评

暂无评论

Continual Adaptation for Unsupervised Time Series Anomaly Detection 9

Continual Adaptation for Unsupervised Time Series Anomaly De...

引用

9th International Conference on Intelligent Computing and Signal Processing, ICSP 2024

作者： Yu, Ting Ding, Bo Wang, Xu College of Computer National University of Defense Technology State Key Laboratory of Complex & Critical Software Environment Changsha China

ISBN: (纸本)9798350376548

The application of time series anomaly detection has been widespread across various industrial scenarios. Although current algorithms for time series anomaly detection have shown promising results, they primarily focus on the characteristics of the data distribution within the current training set. This often leads to a lack of adaptability to changes in data distribution while retaining the ability to accommodate new data and preserve existing knowledge. Given the dynamic nature of real-world industrial production systems, the issue of continuous updating of time series anomaly detection algorithms warrants significant attention. However, existing time series anomaly detection algorithms predominantly rely on unsupervised methods, thereby resulting in sparse availability of relevant update strategies. Recognizing this challenge, this paper proposes an unsupervised anomaly detection algorithm update mechanism that incorporates continual learning methods. This approach aims to address the issue in time series anomaly detection algorithms stemming from the absence of label guidance, which leads to a lack of continuous updating capability in models. The method employs a strategy of retaining key information about the past data's feature distribution to ensure memory of past information, thus fulfilling the need for updating and adapting to new data features with minimal storage overhead. Compared to other potential improvement algorithms for continual updating, our approach achieves comparable performance with significantly reduced overhead. In particular, it addresses the issue in the current domain of unsupervised time series anomaly detection, where the lack of labeled data results in a deficiency of continuous updating methods. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Integrating Extractive and Abstractive Models for Code Comment Generation 23

Integrating Extractive and Abstractive Models for Code Comme...

引用

23rd IEEE International Conference on software Quality, Reliability, and Security, QRS 2023

作者： Sun, Weisong Hu, Yuling Xu, Yingfei Chen, Yuchen Fang, Chunrong Nanjing University State Key Laboratory for Novel Software Technology Nanjing China Shanghai Key Laboratory of Computer Software Evaluating and Testing Shanghai China

ISBN: (纸本)9798350319583

Code comments play an essential role in aiding developers understand and maintain source code. Current code comment generation techniques can be classified into categories: extractive methods and abstractive methods. Extractive methods use text retrieval techniques to extract important code tokens to constitute comments. Such comments contain important factual details articulated explicitly in code tokens, but are poor in naturalness. Abstractive methods usually regard code comment generation as a neural machine translation task. By leveraging powerful deep learning-based language models, abstractive methods can generate comments that resemble human writing. However, compared with natural language, programming language code is more complex. Comments generated by abstractive methods often leave out important factual details. In this paper, we propose a novel method for code comment generation by integrating extractive and abstractive models. Our extractive model is built on the Latent Semantic Analysis (LSA) model, effectively extracting important factual details in code snippets. Meanwhile, our abstractive model is built on a deep learning-based encoder-decoder model, enabling it to generate concise and human-written-like comments. We evaluate the effectiveness of our method, called ICS, by conducting extensive experiments on the CodeSearchNet dataset involving six programming languages. The results demonstrate that ICS outperforms state-of-the-art techniques in three widely used metrics: BLEU, METEOR, and ROUGE-L. Moreover, the outcomes of the human evaluation indicate that the comments generated by ICS exhibit superior naturalness and informativeness, and closely align with the provided code snippets. © 2023 IEEE.

关键词： Deep 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：