检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Deng, Kaijun Zheng, Dezhi Xie, Jindong Wang, Jinbao Xie, Weicheng Shen, Linlin Song, Siyang Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China Department of Computer Science University of Exeter United Kingdom

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code will be publicly available at https://***/CVI-SZU/DEGSTalk. Copyright © 2024, The Authors. All rights reserved.

关键词： Gaussian distribution

来源：评论

学校读者我要写书评

暂无评论

Lightweight helmet detection algorithm based on improved YOLOv5 2

Lightweight helmet detection algorithm based on improved YOL...

引用

2nd International Conference on Advanced Algorithms and Signal Image Processing, AASIP 2022

作者： Li, Jianning Zhang, Junzhao Zhang, Xinyu Wang, Shuai College of Electrical and Power Engineering Taiyuan University of Technology Shanxi Taiyuan030024 China Software Institute Nanjing University Jiangsu Nanjing210093 China Shanxi Electric Drive and Internet of Things Engineering Research Center Shanxi Taiyuan030024 China Shanxi Province 1331 Project-Smart City Based on Big Data Lighting Data Sharing and Public Service Engineering Technology Research Center Shanxi Taiyuan030024 China Shanxi Intelligent Digital Lighting Union Laboratory Shanxi Taiyuan030024 China Shanxi Intelligent Digital Cultural Tourism Industry Research Institute Shanxi Taiyuan030024 China

ISBN: (纸本)9781510660571

In the construction process, wearing safety helmet can effectively reduce the injury caused by falling objects and hard objects. In order to detect the wearing of safety helmet during the construction process, a lightweight safety helmet wearing detection algorithm YOLOv5-CS is proposed and applied to the embedded equipment at the construction site. The algorithm is based on the improvement of YOLOv5 target detection algorithm. The improved CAShuffle module is used to form the backbone feature extraction network, which reduces the size of the original algorithm and ensures the detection accuracy of the algorithm;DIoU as the loss function, which makes the algorithm more conducive to detecting small targets such as hard hats;modify dataset, add the dataset on the basis of the original dataset and mark the safety helmet and the anchor frame of the person separately, and judge whether the worker wears the safety helmet by analyzing positional relationship of the identified anchor frame, use the algorithm combining K-means and genetic algorithm to predict the anchor frame of the dataset, and use Mosaic algorithm to enhance the data. The results show that the parameter quantity of YOLOv5-CS algorithm is 2.4M, less than one third of YOLOv5;The average precision decreased by only 4.2%;640x640 pictures can be recognized at 31 frames per second on Jetson Nano, a embedded platform. © 2022 SPIE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

An Optimal Network Coverage-oriented Operators Network Automatic Planning Strategy 5

An Optimal Network Coverage-oriented Operators Network Autom...

引用

5th International Conference on Pattern Recognition and Artificial Intelligence, PRAI 2022

作者： Gou, Haosong Su, Ling Zhang, Gaoyi Huang, Wei Yang, Yang Rao, Yunbo China Mobile Communications Group Sichuan Co. Ltd. Chengdu China Chengdu Aerospace Science and Industry Big Data Research Institute Co. Ltd. Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering China

ISBN: (数字)9781665499163

ISBN: (纸本)9781665499163

With the constant expansion of the scale of the operators' network, the difficulty of network planning is also significantly increased. The traditional way of manual network planning highly depends on engineers' experience, which results in many quality and efficiency problems, especially in the issues of coverage holes in the existing network, which usually requires a lot of human resources for the network planning. This paper proposes an optimal network coverage-oriented operators' network automatic planning strategy, the mathematical model can quickly deduce the optimal network topology and base station location. The final experimental analysis shows that our proposed method achieves much better performance on automatic network planning through a mathematical model than manually network planning. It saves lots of human resources in network planning and improves the efficiency and quality of network planning. © 2022 IEEE.

关键词： Personnel

来源：评论

学校读者我要写书评

暂无评论

RAUIE: A Relation-Augmented Document-Level Event Extraction Model Based on UIE

RAUIE: A Relation-Augmented Document-Level Event Extraction ...

引用

Artificial Intelligence, Networking and Information Technology (AINIT), International Seminar on

作者： Yiyuan Liang Hong Jia Licai Wang Yangchen Huang Zhe Yang Big data research and development center North China Institute of Computing Technology Beijing China Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Engineering The Chinese University of Hong Kong China

ISBN: (数字)9798350385557

ISBN: (纸本)9798350385564

In document-level event extraction tasks, multiple event types often coexist within a document (the multi-event problem), and arguments may play different roles across different events (the argument intertwining problem). Existing methods often suffer from significantly reduced event extraction accuracy, mainly when focusing on scenarios with scarce annotated data and imbalanced event-type distributions. This paper emphasizes enhancing the correlation between event triggers and arguments to address these challenges. Therefore, we propose the Relation-Augmented UIE Model (RADIE), which introduces entity relationships into prompts using prompt-based learning and designs a relation-augmentation algorithm to improve the accuracy and completeness of event extraction. Experimental results demonstrate that this approach significantly outperforms baseline methods, mainly showcasing excellent performance on datasets with long-tail distributions.

关键词： Seminars Accuracy Correlation Focusing Feature extraction data mining Task analysis

来源：评论

学校读者我要写书评

暂无评论

research on the Improved YOLOv5 Algorithm Fall Monitoring System for Home Care for the Elderly 7

Research on the Improved YOLOv5 Algorithm Fall Monitoring Sy...

引用

7th International Conference on Computer Information science and Application Technology, CISAT 2024

作者： Xu, Wanchao Zhang, Junchao Zhang, Xinyu Li, Fengxia Tao, Jinyi Zhao, Rongli Taiyuan University of Technology College of Electrical and Power Engineering Shanxi Taiyuan030024 China Shanxi Provincial Engineering Research Center of Electric Drive and Internet of Things Shanxi Taiyuan030024 China Nanjing University College of Software Jiangsu Nanjing210093 China National Intelligent Lighting and Smart Wearable Technology Innovation Center Shanxi Province Taiyuan030024 China Eng. Technol. Res. Ctr. of Smart City Lighting Data Sharing and Pub. Serv. Platform Based on Big Data Shanxi Province Taiyuan030024 China Research Institute of New Materials and Chemical Engineering Shanxi Zhejiang University Shanxi Taiyuan030032 China

ISBN: (纸本)9798350375107

In view of the risk of fall for the elderly in the home care environment, a surveillance video display fall detection method of the improved YOLOv5 algorithm is improved, and the Transformer module that increases the human attention mechanism is combined with the CSPDarknet structure of the backbone part of the YOLOv5 algorithm. The system collects video data through the camera, trains and verifies the video data, and then judges the action and posture of the target person. It connects the WIFI module of Orange School to send the action and posture information to the guardian's mobile phone to remind the guardian to timely treat the person who fell down, so as to improve the rescue efficiency. On the basis of improving the algorithm structure, the loss function was improved and conducted repeated training. The experimental results showed that the improved algorithm mAP improved by 2.8%, the F1 score by 2.2%, the number of processing frames per second by 10% during inference, and achieved the fall detection accuracy of 98.6%. © 2024 IEEE.

关键词： Fall detection

来源：评论

学校读者我要写书评

暂无评论

Exploiting Six-Dimensional Movable Antenna (6DMA) for Wireless Sensing

arXiv

引用

arXiv 2024年

作者： Shao, Xiaodan Zhang, Rui Schober, Robert Erlangen91054 Germany School of Science and Engineering Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Guangdong Shenzhen518172 China The Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

Six-dimensional movable antenna (6DMA) is an emerging technology that is able to fully exploit the spatial variation of wireless channels by controlling the 3D positions and 3D rotations of distributed antennas/antenna surfaces at the transmitter/receiver. In this letter, we apply 6DMA at the base station (BS) to enhance its wireless sensing performance over a given set of regions. To this end, we first divide each region into a number of equal-size subregions and select one typical target location within each subregion. Then, we derive an expression for the Cramer-Rao bound (CRB) for estimating the directions of arrival (DoAs) from these typical target locations in all regions, which sheds light on the sensing performance of 6DMA enhanced systems in terms of a power gain and a geometric gain. Next, we minimize the CRB for DoA estimation via jointly optimizing the positions and rotations of all 6DMAs at the BS, subject to practical movement constraints, and propose an efficient algorithm to solve the resulting non-convex optimization problem sub-optimally. Finally, simulation results demonstrate the significant improvement in DoA estimation accuracy achieved by the proposed 6DMA sensing scheme as compared to various benchmark schemes, for both isotropic and directive antenna radiation patterns. Copyright © 2024, The Authors. All rights reserved.

关键词： Cramer-Rao bounds

来源：评论

学校读者我要写书评

暂无评论

Int-GNN: A User Intention Aware Graph Neural Network for Session-Based Recommendation

Int-GNN: A User Intention Aware Graph Neural Network for Ses...

引用

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

作者： Guangning Xu Jinyang Yang Jinjin Guo Zhichao Huang Bowen Zhang Computer Science & Technology Harbin Institute of Technology Shenzhen China JD Intelligent Cities Research JD iCity Beijing China College of Big Data and Internet Shenzhen Technology University Shenzhen China

Session-Based Recommendation (SBR) is a spotlight research problem. Although many efforts have been made, challenges still exist. The key to unlocking this shackle is the user intention, an intuitive but hard-to-model concept in the anonymous session. Unlike previous research, we suggest mining potential user intention by counting the number of item occurrences in a user session and considering the long interval between item re-interactions. Beyond these, we take user preference, a biased user intention, into account in the prediction stage. Forming these together, we propose a model named user Intention aware Graph Neural Network (Int-GNN) aiming at capturing user intention. Extensive experiments have been conducted on three real-world datasets, and the results show the superiority of our method. The code is available on GitHub: https://***/xuguangning1218/IntGNN_ICASSP2023

关键词： Codes Signal processing Graph neural networks Generators Acoustics Speech processing Software development management

来源：评论

学校读者我要写书评

暂无评论

BMDP:Blockchain-Based Multi-Cloud Storage data Provenance

BMDP:Blockchain-Based Multi-Cloud Storage Data Provenance

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Feiyu Wang Jian-Tao Zhou Xu Guo College of Computer Science Inner Mongolia University Hohhot Inner Mongolia China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Engineering Research Center of Ecological Big Data Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

In a multi-cloud storage system, provenance data records all operations and ownership during its lifecycle, which is critical for data security and audibility. However, recording provenance data also poses some challenging security and storage issues. In this paper, we present a secure and efficient multi-cloud storage data source scheme, BMDP. We use blockchain technology to ensure the secure storage of provenance data and design a smart contract to utilize the provenance data to ensure the proper operation of the multi-cloud storage system. Finally, we analyze the scheme’s safety and do simulation experiments to show that the scheme has practicality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Improving Cancer Gene Identification by Enhancing Common Information Between the PPI Network and Gene Functional Association 39

Improving Cancer Gene Identification by Enhancing Common Inf...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Deng, Chao Li, Hongdong Wang, Jianxin School of Computer Science and Engineering Central South University Changsha410083 China Hunan Provincial Key Lab on Bioinformatics Central South University Changsha410083 China Xinjiang Engineering Research Center of Big Data and Intelligent Software School of Software Xinjiang University Urumqi830091 China

ISBN: (纸本)157735897X

Identifying cancer genes is crucial for treatment and understanding pathogenesis. Recent methods typically leverage protein-protein interaction (PPI) networks or gene functional association data from annotated gene sets. There may be some shared neighborhood structure information between these two types of gene association data. While this common information may contain more accurate gene association information, existing methods often overlook this potential. To address this gap, we introduce DISFusion, which integrates multi-omics cancer data, PPI networks, and gene functional associations to identify cancer genes. A key innovation of DISFusion is the cross-view decorrelation loss, which enhances the common information between PPI networks and gene functional associations, thereby improving prediction accuracy. Extensive experiments indicate that DISFusion outperforms state-of-the-art methods and exhibits greater generalization ability. Moreover, analysis of CPTAC pan-cancer proteomic data highlights significant associations between the 30 novel cancer genes predicted by DISFusion and multiple cancer types, underscoring its practical utility. These findings validate the effectiveness of enhancing common information and provide new insights into cancer gene identification. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RGCnet: An Efficient Recursive Gated Convolutional Network for EEG-based Auditory Attention Detection

RGCnet: An Efficient Recursive Gated Convolutional Network f...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Siqi Cai Jia Li Hongmeng Yang Haizhou Li Department of Electrical and Computer Engineering National University of Singapore Singapore Shien-Ming Wu School of Intelligent Engineering South China University of Technology China Shenzhen Research Institute of Big Data School of Data Science The Chinese University of Hong Kong Shenzhen China Machine Listening Lab University of Bremen Germany

Humans are able to listen to one speaker and disregard others in a speaking crowd, referred to as the "cocktail party effect". EEG-based auditory attention detection (AAD) seeks to identify whom a listener is listening to by decoding one’s EEG signals. Recent research has demonstrated that the self-attention mechanism is effective for AAD. In this paper, we present the Recursive Gated Convolutional network (RGCnet) for AAD, which implements long-range and high-order interactions as a self-attention mechanism, while maintaining a low computational cost. The RGCnet expands the 2nd order feature interactions to a higher order to model the complex interactions between EEG features. We evaluate RGCnet on two public datasets and compare it with other AAD models. Our results demonstrate that RGCnet outperforms other comparative models under various conditions, thus potentially improving the control of neuro-steered hearing devices.

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：