检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Yu Zeng Yang Zhang Jiachen Liu Linlin Shen Kaijun Deng Weizhao He Jinbao Wang Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University and Shenzhen Institute of Artificial Intelligence and Robotics for Society and National Engineering Laboratory for Big Data System Computing Technology Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University and Guangdong Provincial Key Laboratory of Intelligent Information Processing

ISBN: (纸本)9798331314385

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Network Fault Prediction-Based Service Migration Approach for Unstable Mobile Edge Environment

引用

Wireless Communications and Mobile computing 2023年第1期2023卷

作者： Wang, Haiyan Tang, Weihao Luo, Jian Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

How to perform efficient service migration in a mobile edge environment has become one of the research hotspots in the field of service computing. Most service migration approaches assume that the mobile edge network on which the migration depends is stable. However, in practice, these networks often fluctuate greatly due to the fault of edge devices, resulting in unexpected service interruptions during the migration process. Besides, most of the existing solutions do not consider the migration cost and path selection in the event of edge network fault. Aiming at the above problems, we propose a service migration approach based on network fault prediction (SMNFP) for mobile edge environment. The SMNFP method first introduces the software-defined network as a global controller, which is used to monitor and collect the changing of the edge network and schedule the migration tasks. Second, a network fault prediction model based on Wide&Deep model is proposed to predict the upcoming faults in the network according to the alarm information of network equipment. Finally, the service migration problem is constructed as a Markov decision process, and a fault penalty function is introduced to avoid faulty nodes, together with the deep Q-learning method to solve the migration strategy. Simulation experiments are conducted on the public metro network fault dataset, and results show the proposed method can effectively predict network faults and complete service migration. Copyright © 2023 Haiyan Wang et al.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

Few-Shot Object Detection Based on the Transformer and High-Resolution Network

引用

Computers, Materials & Continua 2023年第2期74卷 3439-3454页

作者： Dengyong Zhang Huaijian Pu Feng Li Xiangling Ding Victor S.Sheng Hunan Provincial Key Laboratory of Intelligent Processing of Big Data on Transportation Changsha University of Science and TechnologyChangsha410114China School of Computer and Communication Engineering Changsha University of Science and TechnologyChangsha410114China School of Computer Science and Engineering Hunan University of Science and TechnologyXiangtan411004China Department of Computer Science Texas Tech UniversityLubbock79409TXUSA

Now object detection based on deep learning tries different *** uses fewer data training networks to achieve the effect of large dataset ***,the existing methods usually do not achieve the balance between network parameters and training *** makes the information provided by a small amount of picture data insufficient to optimize model parameters,resulting in unsatisfactory detection *** improve the accuracy of few shot object detection,this paper proposes a network based on the transformer and high-resolution feature extraction(THR).High-resolution feature extractionmaintains the resolution representation of the *** and spatial attention are used to make the network focus on features that are more useful to the *** addition,the recently popular transformer is used to fuse the features of the existing *** compensates for the previous network failure by making full use of existing object *** on the Pascal VOC and MS-COCO datasets prove that the THR network has achieved better results than previous mainstream few shot object detection.

关键词： Object detection few shot object detection transformer high-resolution

来源：评论

学校读者我要写书评

暂无评论

DMHFR:Decoder with Multi-Head Feature Receptors for Tract Image Segmentation

引用

Computers, Materials & Continua 2025年第3期82卷 4841-4862页

作者： Jianuo Huang Bohan Lai Weiye Qiu Caixu Xu Jie He Department of Endoscopy Center Zhongshan Hospital(Xiamen)Fudan UniversityXiamen361015China School of Computing and Data Science Xiamen University MalaysiaSepang43900Malaysia School of Computer Science and Techonology Tongji UniversityShanghai200092China Guangxi Key Laboratory of Machine Vision and Intelligent Control Wuzhou UniversityWuzhou543002China Xiamen Clinical Research Center for Cancer Therapy Xiamen361015China

The self-attention mechanism of Transformers,which captures long-range contextual information,has demonstrated significant potential in image ***,their ability to learn local,contextual relationships between pixels requires further *** methods face challenges in efficiently managing multi-scale fea-tures of different granularities from the encoder backbone,leaving room for improvement in their global representation and feature extraction *** address these challenges,we propose a novel Decoder with Multi-Head Feature Receptors(DMHFR),which receives multi-scale features from the encoder backbone and organizes them into three feature groups with different granularities:coarse,fine-grained,and full *** groups are subsequently processed by Multi-Head Feature Receptors(MHFRs)after feature capture and modeling *** include two Three-Head Feature Receptors(THFRs)and one Four-Head Feature Receptor(FHFR).Each group of features is passed through these MHFRs and then fed into axial transformers,which help the model capture long-range dependencies within the *** three MHFRs produce three distinct feature *** output from the FHFR serves as auxiliary auxiliary features in the prediction head,and the prediction output and their losses will eventually be *** results show that the Transformer using DMHFR outperforms 15 state of the arts(SOTA)methods on five public ***,it achieved significant improvements in mean DICE scores over the classic Parallel Reverse Attention Network(PraNet)method,with gains of 4.1%,2.2%,1.4%,8.9%,and 16.3%on the CVC-ClinicDB,Kvasir-SEG,CVC-T,CVC-ColonDB,and ETIS-LaribPolypDB datasets,respectively.

关键词： Medical image segmentation feature exploration feature aggregation deep learning multi-head feature receptor

来源：评论

学校读者我要写书评

暂无评论

SSR-TA: Sequence to Sequence based expert recurrent recommendation for ticket automation

arXiv

引用

arXiv 2023年

作者： Cao, Chenhan Fang, Xiaoyu Luo, Bingqing Xia, Bin Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

The ticket automation provides crucial support for the normal operation of IT software systems. An essential task of ticket automation is to assign experts to solve upcoming tickets. However, facing thousands of tickets, inappropriate assignments will make tickets transfer frequently among experts, which causes time delays and wasted resources. Effectively and efficiently finding an appropriate expert in fewer steps is vital to ticket automation. In this paper, we proposed a sequence to sequence based translation model combined with a recurrent recommendation network to recommend appropriate experts for tickets. The sequence to sequence model transforms the ticket description into the corresponding resolution for capturing the potential and useful features of representing tickets. The recurrent recommendation network recommends the appropriate expert based on the assumption that the previous expert in the recommendation sequence cannot solve the expert. To evaluate the performance, we conducted experiments to compare several baselines with SSR-TA on two real-world datasets, and the experimental results show that our proposed model outperforms the baselines. The comparative experiment results also show that SSR-TA has a better performance of expert recommendations for user-generated tickets. Copyright © 2023, The Authors. All rights reserved.

关键词： Automation

来源：评论

学校读者我要写书评

暂无评论

Economical Electricity Supplement for Mobile Collectors in Large-Scale Multitask WSNs

Economical Electricity Supplement for Mobile Collectors in L...

引用

IEEE International Conference on big data and Cloud computing (BdCloud)

作者： Xin Zhai Lijie Xu Jialei Zhang Kun Wang Jia Xu Bei Xu Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

For large-scale multitask wireless sensor networks (LSM-WSNs), the traditional data collection mode could suffer low energy-efficiency on data transmission, since the large-scale multitask scenarios could result in much higher packet collision probability, especially for harsh environments. Mobile data collection is an efficient data acquisition way to prolong network lifetime for LSM-WSNs. However, the mobile collectors could suffer electricity shortage problem, since the limited battery capacity of any mobile collector could not afford the energy consumption of its long-distance movement and massive data collection in large-scale multitask scenarios. Deploying wireless chargers to supplement the energy of mobile collectors is a feasible solution to electricity shortage problem, but will incur extra charger deployment cost. In this paper, we focus on the problem that how to optimize such charger deployment cost, which is NP-hard. By transforming it into minimum-cost submodular cover problem, we devise an efficient approximation algorithm with a provable approximation ratio. The extensive simulation results reveal that our solution always outperforms the other solutions under whatever configurations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Answer Summarization Scheme Based on Multilayer Attention Model

An Answer Summarization Scheme Based on Multilayer Attention...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Xiaolong Xu Yihao Dong Jian Song Jiangsu Key Laboratory of Big Data Security & Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

At present, deep learning technologies have been widely used in the field of natural language process, such as text summarization. In CQA, the answer summary could help users get a complete answer quickly. There are still some problems with the current answer summary scheme, such as semantic inconsistency, repetition of words, etc. In order to solve this, we propose a novel scheme Answer Summarization based on Multi-layer Attention Scheme (ASMAM). Based on the traditional Seq2Seq, we introduce self-attention and multi-head attention scheme respectively during sentence and text encoding, which could improve text representation ability of the model. In order to solve "long distance dependence" of RNN and too many parameters of LSTM, we all use GRU as the neuron at the encoder and decoder sides. Experiments over the Yahoo! Answers dataset demonstrate that the coherence and fluency of the generated summary are all superior to the benchmark model in ROUGE evaluation system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-stability analysis and energy control for 4D hyperchaotic system with hidden attractors

引用

The European Physical Journal Special Topics 2023年第6期233卷 1401-1412页

作者： Ma, Shaojuan Wang, Meibo Ma, Xiaoyan Li, Hufei School of Mathematics and Information Science North Minzu University Yinchuan China Ningxia Key Laboratory of Intelligent Information and Big Data Processing Yinchuan China

Multi-stability and control of hyperchaotic system are researched in this paper. Firstly, a new 4D hyperchaotic system containing hidden attractors is modeled. Secondly, the coexistence of different attractors is confirmed and transient hyperchaotic phenomena is found as the parameters are changed. Then, the Hamiltonian energy function of the system is calculated and the energy feedback controller is designed to control the system. Finally, numerical simulations are performed to verify the validity of the results.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SFSM: A Serverless Function Scheduling Method for FaaS Applications over Edge computing

SFSM: A Serverless Function Scheduling Method for FaaS Appli...

引用

IEEE International Conference on Web Services (ICWS)

作者： Hao Tian Cheng Chen Fei Dai Wanchun Dou State Key Laboratory for Novel Software Technology Nanjing University China College of Big Data and Intelligent Engineering Southwest Forestry University China

ISBN: (数字)9798350368550

ISBN: (纸本)9798350368567

Serverless edge computing is emerging as an enabler to provision scalable and flexible Function-as-a-Service (FaaS) applications with lightweight function instances at network edge. In serverless edge computing, the function instances with inter-dependencies are scheduled to proximate edge nodes in a distributed manner. However, the heterogeneity and unpredictability of edge networks bring significant challenge in realizing optimal scheduling decision to guarantee execution performance of applications without any prior. In view of this challenge, a Serverless Function Scheduling Method, named SFSM, is proposed in this paper for FaaS applications over edge computing. First, a long-term optimization problem is formulated to reduce completion time and decoupled into time-slot sub-problems via Lyapunov optimization. To avoid the cross-edge redundant data transmission overhead of inter-functions, a two-level graph optimization is designed with vertical and horizontal data merging. Then, SFSM incorporates an online multi-armed bandit-based scheduling algorithm that only requires the context of requests without complete information of edge networks. Finally, extensive experimental results based on real-world datasets demonstrate the effectiveness and superiority of SFSM.

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：