检索结果-内蒙古大学图书馆

Video Corpus Moment Retrieval with Query-specific Context Learning and Progressive Localization

IEEE Transactions on Circuits and Systems for Video Technology 2025年第6期35卷 5659-5670页

作者： Zhang, Long Song, Peipei Duan, Zhangling Wang, Shuo Chang, Xiaojun Yang, Xun School of Information Science and Technology Hefei230026 China Hefei Comprehensive National Science Center Institute of Artificial Intelligence Hefei230026 China University of Science and Technology of China School of Information Science and Technology Hefei230026 China Department of Computer Vision Abu Dhabi United Arab Emirates University of Science and Technology of China MoE Key Laboratory of Brain-inspired Intelligent Perception and Cognition China

Video corpus moment retrieval (VCMR) aims to retrieve a moment from a large corpus of untrimmed videos corresponding to a given language query. However, existing methods often fall short due to their reliance on simple cross-modal attention mechanisms and one-stop localization, which fail to handle the complex multimodal information and large search space effectively. To address these challenges, we propose a novel VCMR method with Query-specific Context Learning and Progressive Localization (QCLPL). First, we construct query-specific multimodal contexts that capture complementary and consistent semantics across subtitles and frames, ensuring informative and efficient context building. We further introduce a semantic contrastive loss to refine these multimodal contexts, filtering out query-irrelevant information. Additionally, we introduce a progressive localization strategy that transforms the moment localization task into a two-stage process. By classifying frames into foreground and background regions, we present a simplified binary classification problem before boundary prediction, constrained by a region-aware loss. This progressive approach leverages region priors to improve subsequent moment localization. Extensive experiments on the TVR and DiDeMo datasets demonstrate that our method significantly outperforms existing approaches, setting a new state of the art for VCMR. © 1991-2012 IEEE.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

Activation Template Matching Loss for Explainable Face Recognition 17

Activation Template Matching Loss for Explainable Face Recog...

引用

17th IEEE International Conference on Automatic Face and Gesture Recognition, FG 2023

作者： Lin, Huawei Liu, Haozhe Li, Qiufu Shen, Linlin Computer Vision Institute School of Computer Science and Softwre Enginnering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China

ISBN: (纸本)9798350345445

Can we construct an explainable face recognition network able to learn a facial part-based feature like eyes, nose, mouth and so forth, without any manual annotation or additionalsion datasets? In this paper, we propose a generic Explainable Channel Loss (ECLoss) to construct an explainable face recognition network. The explainable network trained with ECLoss can easily learn the facial part-based representation on the target convolutional layer, where an individual channel can detect a certain face part. Our experiments on dozens of datasets show that ECLoss achieves superior explainability metrics, and at the same time improves the performance of face verification without face alignment. In addition, our visualization results also illustrate the effectiveness of the proposed ECLoss. © 2023 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Dependency-aware Task Offloading and Resource Pricing in Vehicular Edge Computing: A Stackelberg Game Approach 22

Dependency-aware Task Offloading and Resource Pricing in Veh...

引用

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

作者： Zhao, Liang Huang, Shuai Cao, Yuxiang Zhou, Huan Leung, Victor C. M. China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology Yichang China Northwestern Polytechnical University School of Computer Science Xi'an China The University of British Columbia Department of Electrical and Computer Engineering Vancouver Canada

ISBN: (纸本)9798331509712

Vehicular Edge Computing (VEC) allows vehicles to offload their delay-sensitive tasks to nearby Road Side Units (RSUs) for processing, which improves network quality of service (QoS). However, the self-interested SDN controller is unwilling to ask RSUs to provide free computing resources for vehicles. At the same time, complicated dependencies between vehicular subtasks may cause non-ideal task delay and energy consumption. In order to solve these problems, this paper proposes a Stackelberg game-based Dependency-aware task Offloading and resource Pricing framework (SDOP). Specifically, we first model a vehicular edge network that partially offloads dependency-aware tasks. Then, we depict the interaction between the SDN controller and vehicles as a Stackelberg game, with the goal of maximizing the utility of both parties. Next, we present a Gradient Ascent Plus Genetic algorithm (GAPG) to solve the problem. Finally, numerous simulations are performed, and the results show that compared with other baseline schemes, the proposed GAPG can significantly improve the utility of both the SDN controller and vehicles under various scenarios. © 2024 IEEE.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Towards Combating Frequency Simplicity-biased Learning for Domain Generalization 38

Towards Combating Frequency Simplicity-biased Learning for D...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： He, Xilin Hu, Jingyu Lin, Qinliang Luo, Cheng Xie, Weicheng Song, Siyang Khan, Muhammad Haris Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China Guangdong Provincial Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Mohamed bin Zayed University of Artificial Intelligence United Arab Emirates

Domain generalization methods aim to learn transferable knowledge from source domains that can generalize well to unseen target domains. Recent studies show that neural networks frequently suffer from a simplicity-biased learning behavior which leads to over-reliance on specific frequency sets, namely as frequency shortcuts, instead of semantic information, resulting in poor generalization performance. Despite previous data augmentation techniques successfully enhancing generalization performances, they intend to apply more frequency shortcuts, thereby causing hallucinations of generalization improvement. In this paper, we aim to prevent such learning behavior of applying frequency shortcuts from a data-driven perspective. Given the theoretical justification of models' biased learning behavior on different spatial frequency components, which is based on the dataset frequency properties, we argue that the learning behavior on various frequency components could be manipulated by changing the dataset statistical structure in the Fourier domain. Intuitively, as frequency shortcuts are hidden in the dominant and highly dependent frequencies of dataset structure, dynamically perturbating the over-reliance frequency components could prevent the application of frequency shortcuts. To this end, we propose two effective data augmentation modules designed to collaboratively and adaptively adjust the frequency characteristic of the dataset, aiming to dynamically influence the learning behavior of the model and ultimately serving as a strategy to mitigate shortcut learning. Code is available at AdvFrequency. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Variable-Speed Dubins Orienteering Problem

Variable-Speed Dubins Orienteering Problem

引用

IEEE Latin American robotics Symposium, LARS

作者： L. C. Vinícius Faria C. G. Caio Ribeiro Douglas G. Macharet Department of Computer Science Computer Vision and Robotics Laboratory (VeRLab) Universidade Federal de Minas Gerais Belo Horizonte MG Brazil

ISBN: (数字)9798331508807

ISBN: (纸本)9798331508814

The class of vehicle routing problems plays an important role in optimizing logistics and transportation strategies across various sectors. In this context, the Orienteering Problem (OP) seeks to determine an optimized path through a set of locations with associated rewards, aiming to maximize the total collected reward while respecting constraints such as time or distance limits. Nonholonomic motion planning, particularly considering Dubins vehicles, is crucial in real-world applications due to its ability to accurately capture the constraints and dynamics of many physical vehicles. In this paper, we extend the Dubins Orienteering Problem (DOP), where unlike the classical Dubins model with constant speed, the vehicle can vary its speed during navigation, enabling the discovery of more effective paths. Experiments comparing both the DOP and our novel formulation show that the VS-DOP achieves higher total collected rewards within the same budget compared to the conventional DOP.

关键词： Navigation Vehicle routing Dynamics Transportation Planning Time factors Vehicle dynamics Robots Logistics

来源：评论

学校读者我要写书评

暂无评论

Data-Driven Analysis of Skin Cancer Classification with Convolutional Neural Networks for E-Health Applications

Data-Driven Analysis of Skin Cancer Classification with Conv...

引用

2024 IEEE Global Communications Conference, GLOBECOM 2024

作者： Ahmed, Imran Ahmad, Misbah Chehri, Abdellah Jeon, Gwanggil Anglia Ruskin University School of Computing and Information Science Cambridge United Kingdom Hartpury University Animal and Agriculture Department Gloucester United Kingdom University of the West of England Centre for Machine Vision Bristol Robotics Laboratory Bristol United Kingdom Department of Mathematics and Computer Science Canada Incheon National University Department of Embedded Systems Engineering Incheon Korea Republic of

ISBN: (纸本)9798350351255

This study explores the effectiveness of Convolutional Neural Networks (CNNs) in automatically classifying skin cancer for e-health applications. The trained model showcases impressive performance by leveraging the HAM10000 dataset, which includes a wide range of skin lesion images from seven different classes. The parameters and architecture of the CNN model are presented in a systematic manner, providing valuable insights into the reasoning behind its design. The model is optimized using the Adam optimizer and annealing techniques to ensure efficient convergence. The model's performance is assessed on validation and test datasets, showcasing an accuracy of 78.55% and 76.49%, respectively, for skin cancer classification. This study highlights the significant potential of CNN as a powerful tool for automating the diagnosis of skin cancer, which is in line with the growing trend of using deep learning for medical image analysis. © 2024 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Dependency-Aware Tasks Offloading in Digital Twin Edge Networks

Reinforcement Learning for Dependency-Aware Tasks Offloading...

引用

2023 International Conference on Artificial Intelligence of Things and Systems, AIoTSys 2023

作者： Xiong, Jiaxin Chen, Lingxiao Zhao, Liang Chang, Wei China Three Gorges University Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering College of Computer and Information Technology Yichang China Saint Joseph's University Computer Science Department United States

ISBN: (纸本)9798350312270

Mobile Edge Computing (MEC) and Digital Twin (DT) technologies are crucial to meet the quality of service (QoS) of emerging applications. MEC sinks the processing power of the cloud to the edge and responds to users' requests in real time. DT can collect and analyze a large amount of data to make the optimal decision. However, the combination of MEC and DT is always ignored. Furthermore, it is more challenging to offload dependency-aware tasks efficiently. Therefore, this paper aims to present a more comprehensive survey of DT edge networks (DTEN). We first discuss prior knowledge about DTEN, such as its basic concepts, advantages, and application scenarios. Then, we highlight the research challenges for dependency-aware task offloading in recent years, including computation offloading, resource allocation, service caching, and edge collaboration. Furthermore, we introduce Reinforcement Learning (RL) for networking systems in detail. Finally, we conduct a typical dependency-aware task offloading case study to understand DTEN more deeply. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Topic Controlled Steganography via Graph-to-Text Generation

引用

computer Modeling in Engineering & sciences 2023年第7期136卷 157-176页

作者： Bowen Sun Yamin Li Jun Zhang Honghong Xu Xiaoqiang Ma Ping Xia School of Computer Science and Information Engineering Hubei UniversityWuhan430062China Hubei Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China Yichang Key Laboratory of Intelligent Vision Based Monitoring for Hydroelectric Engineering China Three Gorges UniversityYichang443002China Department of CSIS Douglas CollegeNewWestminsterBCV3L 5B2Canada College of Computer and Information Technology China Three Gorges UniversityYichang443002China

Generation-based linguistic steganography is a popular research area of information *** text generative steganographic method based on conditional probability coding is the direction that researchers have recently paid attention ***,in the course of our experiment,we found that the secret information hiding in the text tends to destroy the statistical distribution characteristics of the original text,which indicates that this method has the problem of the obvious reduction of text quality when the embedding rate increases,and that the topic of generated texts is uncontrollable,so there is still room for improvement in *** this paper,we propose a topic-controlled steganography method which is guided by graph-to-text *** proposed model can automatically generate steganographic texts carrying secret messages from knowledge graphs,and the topic of the generated texts is *** also provide a graph path coding method with corresponding detailed algorithms for graph-to-text *** from traditional linguistic steganography methods,we encode the secret information during graph path coding rather than using conditional *** test our method in different aspects and compare it with other text generative steganographic *** experimental results show that the model proposed in this paper can effectively improve the quality of the generated text and significantly improve the concealment of steganographic text.

关键词： information hiding linguistic steganography knowledge graph topic controlled text generation

来源：评论

学校读者我要写书评

暂无评论

An Efficient Medical Image Deep Fusion Model Based on Convolutional Neural Networks

引用

computers, Materials & Continua 2023年第2期74卷 2905-2925页

作者： Walid El-Shafai Noha A.El-Hag Ahmed Sedik Ghada Elbanby Fathi E.Abd El-Samie Naglaa F.Soliman Hussah Nasser AlEisa Mohammed E.Abdel Samea Department of Electronics and Electrical Communications Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Security Engineering Laboratory Department of Computer SciencePrince Sultan UniversityRiyadh11586Saudi Arabia Higher Institute of Commercial Science Management Information SystemsEl-Mahala El-KobraEgypt Department of the Robotics and Intelligent Machines Faculty of Artificial IntelligenceKafrelsheikh UniversityKafr El-SheikhEgypt Department of Industrial Electronics and Control Engineering Faculty of Electronic EngineeringMenoufia UniversityMenouf32952Egypt Department of Information Technology College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Department of Computer Sciences College of Computer and Information SciencesPrincess Nourah Bint Abdulrahman UniversityRiyadhSaudi Arabia Medical Imaging and Interventional Radiology National Liver InstituteMenoufia UniversityEgypt

Medical image fusion is considered the best method for obtaining one image with rich details for efficient medical diagnosis and *** learning provides a high performance for several medical image analysis *** paper proposes a deep learning model for the medical image fusion *** model depends on Convolutional Neural Network(CNN).The basic idea of the proposed model is to extract features from both CT and MR ***,an additional process is executed on the extracted *** that,the fused feature map is reconstructed to obtain the resulting fused ***,the quality of the resulting fused image is enhanced by various enhancement techniques such as Histogram Matching(HM),Histogram Equalization(HE),fuzzy technique,fuzzy type,and Contrast Limited Histogram Equalization(CLAHE).The performance of the proposed fusion-based CNN model is measured by various metrics of the fusion and enhancement *** realistic datasets of different modalities and diseases are tested and ***,real datasets are tested in the simulation analysis.

关键词： Image fusion CNN deep learning feature extraction evaluation metrics medical diagnosis

来源：评论

学校读者我要写书评

暂无评论

PLIP: Language-Image Pre-training for Person Representation Learning 38

PLIP: Language-Image Pre-training for Person Representation ...

引用

38th Conference on Neural information Processing Systems, NeurIPS 2024

作者： Zuo, Jialong Hong, Jiahao Zhang, Feng Yu, Changqian Zhou, Hanyu Gao, Changxin Sang, Nong Wang, Jingdong National Key Laboratory of Multispectral Information Intelligent Processing Technology School of Artificial Intelligence and Automation Huazhong University of Science and Technology China Skywork AI United States Department of Computer Vision Baidu Inc. China

Language-image pre-training is an effective technique for learning powerful representations in general domains. However, when directly turning to person representation learning, these general pre-training methods suffer from unsatisfactory performance. The reason is that they neglect critical person-related characteristics, i.e., fine-grained attributes and identities. To address this issue, we propose a novel language-image pre-training framework for person representation learning, termed PLIP. Specifically, we elaborately design three pretext tasks: 1) Text-guided Image Colorization, aims to establish the correspondence between the person-related image regions and the fine-grained color-part textual phrases. 2) Image-guided Attributes Prediction, aims to mine fine-grained attribute information of the person body in the image;and 3) Identity-based vision-Language Contrast, aims to correlate the cross-modal representations at the identity level rather than the instance level. Moreover, to implement our pre-train framework, we construct a large-scale person dataset with image-text pairs named SYNTH-PEDES by automatically generating textual annotations. We pre-train PLIP on SYNTH-PEDES and evaluate our models by spanning downstream person-centric tasks. PLIP not only significantly improves existing methods on all these tasks, but also shows great ability in the zero-shot and domain generalization settings. © 2024 Neural information processing systems foundation. All rights reserved.

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：