检索结果-内蒙古大学图书馆

Diverse Co-saliency Feature Learning for Text-Based Person Retrieval

IEEE Transactions on Information Forensics and Security 2025年 20卷 5465-5477页

作者： You, Shuai Chen, Cuiqun Feng, Yujian Liu, Hai Ji, Yimu Ye, Mang School of Internet of Things Nanjing China Anhui University School of Computer Science and Technology Hefei China South China Normal University school of computer Guangdong China NJUPT School of Computer Science Nanjing China Wuhan University National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Institute of Artificial Intelligence School of Computer Science Wuhan430072 China

Text-based Person Retrieval (TPR) plays a pivotal role in video surveillance systems for safeguarding public safety. As a fine-grained retrieval task, TPR faces the significant challenge of precisely capturing highly discriminative features across image and text modalities. Existing methods primarily focus on establishing modality-shared feature spaces to bridge cross-modal discrepancies. However, these methods are prone to disturbances from irrelevant information, such as background noises in the visual modality, and often over-emphasize specific local regions while neglecting the capture of diverse discriminative modal features, thereby limiting the robustness of cross-modal matching. In this paper, we introduce a novel framework, termed the Diverse Co-saliency Feature Learning Network (DCFL), which mines the co-saliency information between image and text modalities and enhances the diversity of cross-modal discriminative features while mitigating the interference of noise. Specifically, to construct cross-modal co-saliency features, we devise the Intra-modal Saliency Feature Learning (ISFL) and Cross-modal Saliency Feature Matching (CSFM) modules. ISFL employs a weighted mask mechanism to guide the model in reducing the impact of noise information in both modalities. Complementing ISFL, CSFM establishes consistent relationships between saliency features across modalities, leveraging text descriptions to align pedestrian-relevant visual regions. Furthermore, we propose the Diverse Co-saliency Feature Mining (DCFM) to bolster the diversity of discriminative co-saliency features across both image and text modalities. This module integrates a diversity regularization term, enabling the extraction of varied visual cues and capturing comprehensive features of the target individual. Extensive benchmark experiments demonstrate a substantial superiority of our approach over the state-of-the-art methods. The code will be released publicly. © 2005-2012 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

A Deep Understanding Video Q&A System for Film Education in Acting Department

A Deep Understanding Video Q&A System for Film Education in ...

引用

2023 International Conference on Intelligent Education and Intelligent research, IEIR 2023

作者： Wu, Zhengqian Li, Ruizhe Guo, Jiahao Wang, Zhongyuan Liang, Chao Hubei Key Laboratory of Multimedia and Network Communication Engineering School of Computer Science China National Engineering Research Center for Multimedia Software School of Computer Science China Wuhan University School of Computer Science China

ISBN: (纸本)9798350342895

Recently, advancements in artificial intelligence technology have greatly influenced the field of education, particularly in the area of intelligent homework assistance. However, current approaches are primarily designed for procedural and logical tasks and often lack comprehension abilities. This limitation is particularly evident when it comes to multi-hop and continuous tasks. To address this challenge, the integration of Large Language Model (LLM) has significantly enhanced the capability of AI systems to handle multi-hop and highly interconnected inputs. In this study, we focus on the learning needs of students in Acting Department, specifically their study of movies and the significance of classic movie videos in their learning process. However, assessing deep comprehension of classic movies poses its own challenges. To overcome these challenges, we develop a quiz system utilizing Knowledge Graphs (KG) and LLM to facilitate a deeper understanding of classic films. The generation of video quiz pairs is achieved through the use of Automatic Speech Recognition (ASR) technology, which leverages movie subtitles for question generation. For answering these questions, we employ techniques KG and LLM to process questions and retrieve corresponding answers. The proposed method achieves good performance in Deep Video Understanding (DVU) task of NIST TRECVID, demonstrating its effectiveness. © 2023 IEEE.

关键词： Motion pictures

来源：评论

学校读者我要写书评

暂无评论

Metasurfaces for next-generation wireless communication systems

引用

National science Review 2023年第8期10卷 17-19页

作者： Younes Ra'di Nikita Nefedkin Petar Popovski Andrea Alù Department of Electrical Engineering and Computer Science Syracuse University Photonics Initiative Advanced Science Research Center City University of New York Department of Electronic Systems Aalborg University Physics Program Graduate Center City University of New York

The pace of development in the world of 5G communication systems has proven to be much more demanding than previous generations, with 5G-Advanced seemingly around the corner [1]. Extensive research is already underway to structure the next generation of wireless systems(i.e. 6G), which may potentially enable an unprecedented level of human–machine interaction [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

ReCSA:a dedicated sort accelerator using ReRAM-based content addressable memory

引用

Frontiers of computer science 2023年第2期17卷 1-13页

作者： Huize LI Hai JIN Long ZHENG Yu HUANG Xiaofei LIAO National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabClusters and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China

With the increasing amount of data,there is an urgent need for efficient sorting algorithms to process large data *** sorting algorithms have attracted much attention because they can take advantage of different hardware's *** the traditional hardware sort accelerators suffer“memory wall”problems since their multiple rounds of data transmission between the memory and the *** this paper,we utilize the in-situ processing ability of the ReRAM crossbar to design a new ReCAM array that can process the matrix-vector multiplication operation and the vector-scalar comparison in the same array *** this designed ReCAM array,we present ReCSA,which is the first dedicated ReCAM-based sort *** hardware designs,we also develop algorithms to maximize memory utilization and minimize memory exchanges to improve sorting *** sorting algorithm in ReCSA can process various data types,such as integer,float,double,and *** also present experiments to evaluate the performance and energy efficiency against the state-of-the-art sort *** experimental results show that ReCSA has 90.92×,46.13×,27.38×,84.57×,and 3.36×speedups against CPU-,GPU-,FPGA-,NDP-,and PIM-based platforms when processing numeric data *** also has 24.82×,32.94×,and 18.22×performance improvement when processing string data sets compared with CPU-,GPU-,and FPGA-based platforms.

关键词： ReCAM parallel sorting architecture design processing-in-memory

来源：评论

学校读者我要写书评

暂无评论

Community Smell Occurrence Prediction on Multi-Granularity by Developer-Oriented Features and Process Metrics

引用

Journal of computer science & Technology 2022年第1期37卷 182-206页

作者： Zi-Jie Huang Zhi-Qing Shao Gui-Sheng Fan Hui-Qun Yu Xing-Guang Yang Kang Yang Department of Computer Science and Engineering East China University of Science and TechnologyShanghai 200237China Shanghai Key Laboratory of Computer Software Testing and Evaluating Shanghai 200237China Shanghai Engineering Research Center of Smart Energy Shanghai 200237China

Community smells are sub-optimal developer community structures that hinder *** studies performed smell prediction and provided refactoring guidelines from a top-down aspect to help community ***,refactoring smells also requires bottom-up effort from every ***,supportive measures and guidelines for them are not available at a fine-grained *** recent work revealed developers'personalities and working states could influence community smells'emergence and variation,we build prediction models with experience,sentiment,and development process features of developers considering three smells including Organizational Silo,Lone Wolf,and Bottleneck,as well as two related classes including smelly developer and smelly *** predict the five classes in the individual granularity,and we also generate forecasts for the number of smelly developers in the community *** proposed models achieve F-measures ranging from 0.73 to 0.92 in individual-wide within-project,time-wise,and cross-project prediction,and mean R2 performance of 0.68 in community-wide Smelly Developer *** also exploit SHAP(SHapley Additive exPlanations)to assess feature importance to explain our *** conclusion,we suggest developers with heavy workload should foster more frequent communication in a straightforward and polite way to build healthier communities,and we recommend community shepherds to use the forecasting model for refactoring planning.

关键词： community smell developer sentiment socio-technical analysis empirical software engineering

来源：评论

学校读者我要写书评

暂无评论

Multi-Scale Fusion and Decomposition Network for Single Image Deraining

引用

IEEE Transactions on Image Processing 2024年 33卷 191-204页

作者： Wang, Qiong Jiang, Kui Wang, Zheng Ren, Wenqi Zhang, Jianhui Lin, Chia-Wen Wuhan University National Engineering Research Center for Multimedia Software School of Computer Science Wuhan430072 China Sun Yat-sen University School of Cyber Science and Technology Guangzhou510275 China Hangzhou Dianzi University College of Computer Science and Technology Hangzhou310018 China National Tsing Hua University Department of Electrical Engineering The Institute of Communications Engineering Hsinchu30013 Taiwan

Convolutional neural networks (CNNs) and self-attention (SA) have demonstrated remarkable success in low-level vision tasks, such as image super-resolution, deraining, and dehazing. The former excels in acquiring local connections with translation equivariance, while the latter is better at capturing long-range dependencies. However, both CNNs and Transformers suffer from individual limitations, such as limited receptive field and weak diversity representation of CNNs during low efficiency and weak local relation learning of SA. To this end, we propose a multi-scale fusion and decomposition network (MFDNet) for rain perturbation removal, which unifies the merits of these two architectures while maintaining both effectiveness and efficiency. To achieve the decomposition and association of rain and rain-free features, we introduce an asymmetrical scheme designed as a dual-path mutual representation network that enables iterative refinement. Additionally, we incorporate high-efficiency convolutions throughout the network and use resolution rescaling to balance computational complexity with performance. Comprehensive evaluations show that the proposed approach outperforms most of the latest SOTA deraining methods and is versatile and robust in various image restoration tasks, including underwater image enhancement, image dehazing, and low-light image enhancement. The source codes and pretrained models are available at https://***/qwangg/MFDNet. © 1992-2012 IEEE.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Design of ceiling light with air quality monitoring and heat dissipation structure based on duct technology 3

Design of ceiling light with air quality monitoring and heat...

引用

3rd International Conference on Electronic Information engineering and Data Processing, EIEDP 2024

作者： Yu, Liang Mo, Jiayu Lu, Jiancong Lai, Yangbing Tian, Liwei College of Computer Science Guangdong University of Science and Technology AIoT Edge Computing Engineering Technology Research Center Dongguan523000 China

ISBN: (纸本)9781510680531

Most air quality monitors and lighting fixtures are currently separate, with air quality monitors typically being stand-alone devices that require separate power supplies and mounting locations. This not only occupies valuable space but also complicates their use and management. The emergence of air quality monitoring ceiling lights in smart homes aims to address this issue. However, many existing ceiling light designs do not consider heat dissipation, which can lead to performance issues, reduced lifespan, and even fire hazards. To tackle these challenges, this study presents the design of an intelligent ceiling lamp for air quality monitoring utilizing air duct technology. Equipped with a seven-in-one air quality sensor, the ceiling lamp collects indoor air data and performs real-time intelligent control and anomaly identification through a cloud-side-end synergy approach. The incorporation of air ducts enhances the sensitivity and accuracy of air quality monitoring, facilitates thermal convection, and improves heat dissipation efficiency, ultimately enhancing performance and longevity. Physical product design and field tests conducted on the cloud-side-end platform demonstrate that the ceiling lamp's air quality monitoring and anomaly identification have an average inference time of less than 1 millisecond with an identification accuracy of over 98%. Furthermore, the air duct design improves thermal efficiency by approximately 28%. Overall, this intelligent ceiling lamp represents a practical, efficient, and intelligent multi-functional indoor lighting solution. © 2024 SPIE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

IDSDeep-CCD: intelligent decision support system based on deep learning for concrete cracks detection

引用

Multimedia Tools and Applications 2025年第12期84卷 10013-10026页

作者： Abualigah, Sayel M. Al-Naimi, Ahmad F. Sachdeva, Gagan AlAmri, Omran Abualigah, Laith Department of Computer Information Systems Jordan University of Science and Technology Irbid Jordan Gagan Sachdeva Dubai United Arab Emirates Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Computer Science Department Al al-Bayt University Mafraq25113 Jordan Research Center University of Tabuk Tabuk71491 Saudi Arabia MEU Research Unit Middle East University Amman11831 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Computer Sciences Universiti Sains Malaysia Pulau Pinang11800 Malaysia School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia Applied Science Research Center Applied Science Private University Amman11931 Jordan College of Engineering Yuan Ze University Taoyuan32003 Taiwan

In an era where Intelligent Decision Support Systems (IDSS) are integral to managing the vast data from Internet of Everything (IoE) systems, this study introduces IDSDeep-CCD, a novel IDSS approach for detecting concrete cracks, a critical issue in civil infrastructure maintenance. Traditional visual inspection methods for crack detection are time-consuming and error-prone. To address this, IDSDeep-CCD employs deep learning, utilizing an open-source dataset of concrete crack images for enhanced accuracy. The system's two-stage approach, featuring feature extraction via pre-trained models and a fully connected network for classification, significantly outperforms existing methods. Our results demonstrate a remarkable 99.9% accuracy rate in crack detection without data augmentation, marking a notable advancement in automatic detection technology. This breakthrough offers practical benefits for the industry by enabling more precise and efficient identification of concrete cracks, paving the way for timely and accurate remedial actions. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

SELF-JOINT SUPERVISED LEARNING 10

SELF-JOINT SUPERVISED LEARNING

引用

10th International Conference on Learning Representations, ICLR 2022

作者： Kardan, Navid Hill, Mitchell Shah, Mubarak Center for Research in Computer Vision Department of Computer Science Department of Statistics and Data Science University of Central Florida United States

Supervised learning is a fundamental framework used to train machine learning systems. A supervised learning problem is often formulated using an i.i.d. assumption that restricts model attention to a single relevant signal at a time when predicting. This contrasts with the human ability to actively use related samples as reference when making decisions. We hypothesize that the restriction to a single signal for each prediction in the standard i.i.d. framework contributes to well-known drawbacks of supervised learning: making overconfident predictions and vulnerability to overfitting, adversarial attacks, and out-of-distribution data. To address these limitations, we propose a new supervised learning paradigm called self-joint learning that generalizes the standard approach by modeling the joint conditional distribution of two observed samples, where each sample is an image and its label. Rather than assuming samples are independent, our models explicitly learn the sample-to-sample relation of conditional independence. Our framework can naturally incorporate auxiliary unlabeled data to further improve the performance. Experiments on benchmark image datasets show our method offers significant improvement over standard supervised learning in terms of accuracy, robustness against adversarial attacks, out-of-distribution detection, and overconfidence mitigation. © 2022 ICLR 2022 - 10th International Conference on Learning Representationss. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Optimal Power Flow Method Based on Reinforcement Learning for Offshore Wind Farms Considering Multiple Points of Common Coupling

引用

Journal of Modern Power Systems and Clean Energy 2024年第6期12卷 1749-1759页

作者： Yang Fu Zixu Ren Shurong Wei Lingling Huang Fangxing Li Yang Liu Engineering Research Center of Offshore Wind Technology Ministry of Education(Shanghai University of Electric Power) Shanghai 200090China Department of Electrical Power Engineering Shanghai University of Electric PowerShanghai 200090China Department of Electrical Engineering and Computer Science The University of TennesseeKnoxvilleTN 37996USA

The widespread adoption of renewable energy sources presents significant challenges for power system *** paper proposes a dynamic optimal power flow(DOPF)method based on reinforcement learning(RL)to ad-dress the dispatching *** proposed method consid-ers a scenario where large-scale offshore wind farms are inter-connected and have access to an onshore power grid through multiple points of common coupling(PCCs).First,the opera-tional area model of the offshore power grid at the PCCs is es-tablished by combining the prediction results and the transmis-sion capacity limit of the offshore power *** upon this,a dynamic optimization model of the power system and its RL en-vironment are constructed with the consideration of offshore power dispatching ***,an improved algorithm based on the conditional generative adversarial network(CGAN)and the soft actor-critic(SAC)algorithm is *** analyzing an improved IEEE 118-node system,the proposed method proves to have the advantage of economy over a longer *** resulting strategy satisfies power system opera-tion constraints,effectively addressing the constraint problem of action space of RL,and it has the added benefit of faster so-lution speeds.

关键词： Offshore power grid optimal scheduling dy-namic optimal power flow(DOPF) reinforcement learning(RL) renewable energy

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：