检索结果-内蒙古大学图书馆

2024 Findings of the Association for Computational Linguistics, EMNLP 2024

作者： Zhang, Yongheng Chen, Qiguang Zhou, Jingxuan Wang, Peng Si, Jiasheng Wang, Jin Lu, Wenpeng Qin, Libo School of Computer Science and Engineering Central South University China Research Center for SCIR Harbin Institute of Technology Harbin China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences China Yunnan University Kunming China

ISBN: (纸本)9798891761681

Chain-of-Thought (CoT) has become a vital technique for enhancing the performance of Large Language Models (LLMs), attracting increasing attention from researchers. One stream of approaches focuses on the iterative enhancement of LLMs by continuously verifying and refining their reasoning outputs for desired quality. Despite its impressive results, this paradigm faces two critical issues: (1) Single verification method: The current paradigm relies solely on a single verification method. (2) Wrong Information Ignorance: The traditional paradigm directly ignores wrong information during reasoning and refines the logic paths from scratch each time. To address these challenges, we propose Wrong-of-Thought (WoT), which includes two core modules: (1) Multi-Perspective Verification: A multi-perspective verification method for accurately refining the reasoning process and result, and (2) Wrong Information Utilization: Utilizing wrong information to alert LLMs and reduce the probability of LLMs making same mistakes. Experiments on 8 popular datasets and 5 LLMs demonstrate that WoT surpasses all previous baselines. In addition, WoT exhibits powerful capabilities in difficult computation tasks. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Improved Canny Algorithm in Image Edge Detection

Application of Improved Canny Algorithm in Image Edge Detect...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Siyang Xu Peng Zhang Xin Song Runfeng Zhang Hebei Key Laboratory of Marine Perception Network and Data Processing School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China

ISBN: (数字)9798350350210

ISBN: (纸本)9798350350227

To solve the problems of poor denoising effect and limited threshold accuracy in traditional Canny algorithm, an improved Canny algorithm is proposed in this paper. Firstly, an image preprocessing method based on hybrid filtering is developed. On the basis of Gaussian filtering, the adaptive median filtering is adopted to denoise the image, and homomorphic filtering is used to enhance the high frequency information of image in the frequency domain. Besides, Sobel operator is used instead of Roberts operator to calculate the gradient amplitude and direction of the image. Finally, an iterative threshold selection method combining MEM and Otsu is proposed. After obtaining the high and low thresholds by MEM and Otsu respectively, the optimal threshold is calculated using iterative algorithm, which can improve the accuracy and adaptability of threshold. It is proved that the proposed algorithm can preserve the image details while ensuring the denoising effect, and the detected edges have better connectivity and smoothness.

关键词： Micromechanical devices Accuracy Filtering Image edge detection Noise reduction Diversity reception Noise

来源：评论

学校读者我要写书评

暂无评论

Entity Disambiguation Based on UCL Knowledge Space

Entity Disambiguation Based on UCL Knowledge Space

引用

2021 IEEE International Conference on Artificial Intelligence and Industrial Design, AIID 2021

作者： Xinchen, Chang Peng, Yang School of Computer Science and Engineering Key Laboratory of Computer Network and Information Integration Ministry of Education Southeast University Nanjing China

ISBN: (纸本)9780738110837

Named entity disambiguation is an important task in the process of knowledge space construction and improvement, which builds a bridge between entities in text and entities in knowledge space. However, the existing entity disambiguation methods mainly rely on the similar or related entities in the context. For the short text widely appeared in the practical application scenarios, the performance of the existing methods drops sharply. In this paper, we propose an entity disambiguation method based on Uniform Content Label knowledge space (UCLKS-ED). This method uses UCL knowledge space to provide additional knowledge information for the matching task of candidate entities and the source entity, and extends the representation of the source entity by conceptualizing. The experimental results on a large manually annotated short-text dataset and another standard dataset demonstrate that the proposed method achieves significant improvement over the state-of-the-art baselines. © 2021 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Lis...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Kailai Shen Diqun Yan Li Dong Ying Ren Xiaoxun Wu Jing Hu Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Key Laboratory of Mobile Network Application Technology

In this paper, we propose the speech quality assessment transformer utilizing listener dependent modeling (SQAT-LD) mean opinion score (MOS) prediction system, which was submitted to the 2023 VoiceMOS Challenge. The system is based on a combination of self-supervised learning (SSL) models and listener-dependent modeling. Due to this challenge’s emphasis on real-world and challenging zero-shot out-of-domain MOS prediction in three different voice evaluation scenarios, we specifically designed a two-branch module to predict scores and weights for each frame, aiming to achieve better generalization. In the challenge, our system achieved fourth place in Track 1a, second place in Track 1b and first place in Track 2. Additionally, we conducted an ablation study to investigate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low Light RGB and IR Image Fusion with Selective CNN-Transformer network

Low Light RGB and IR Image Fusion with Selective CNN-Transfo...

引用

IEEE International Conference on Image Processing

作者： Haiyan Jin Yue Yang Haonan Su Zhaolin Xiao Bin Wang School of Computer Science and Engineering Xi’an University of Technology Shaanxi Key Laboratory for Network Computing and Security Technology

In low-light images, contrast and brightness are corrupted, making it difficult to accurately percept detail and edge information with the naked eye. Because of the development of multi sensor imaging, RGB-IR image fusion can enhance the imaging quality in low light conditions. However, the existing fusion algorithms have insufficient enhancement, distorted detail and low contrast, which make it difficult to generate high-quality fusion results. In this paper, we propose a Transformer-CNN image fusion method which considers global-local features fusion for low light image enhancement. The ConvGRU module is developed to alternatively select the global and local features with Transformer and CNN network. To effectively improve the network performance, a learnable weight adaptive loss function is proposed to adjust the weight of loss functions during training. Numerous experiments prove that our method can enrich fusion image information, improve image contrast and edge in low-light scenes compared to state of the art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algorithm

YOLOv8-GR: Gesture Recognition by Improving of YOLOv8 Algori...

引用

International Conference on Advanced Cloud and Big Data (CBD)

作者： Yi Ding Naixuan Guo Haitao Meng School of Information Engineering Yancheng Institute of Technology Yancheng China Key Laboratory of Computer Network and Information Integration (Southeast University) Ministry of Education

ISBN: (数字)9798331511074

ISBN: (纸本)9798331511081

Gesture recognition has been widely used in many situations, such as human-computer interaction, virtual reality and smart home. To meet the current demands for accuracy and speed in gesture recognition, this paper proposes an improved algorithm based on YOLOv8, referred to as YOLOv8-GR. By replacing the original YOLOv8 detection head with a Dynamic Head, we integrate scale-aware, spatial-aware, and task-aware attention mechanisms within a unified framework. To enhance context information capture, the SPPF (Spatial Pyramid Pooling - Fast) module is optimized to a modified SPPF-LSKA (Large Separable Kernel Attention) module. In addition, we employ the EIoU loss function for more accurate evaluation of object detection results. To evaluate our algorithm, we integrate a gesture dataset in complex and diverse scenarios through network and field shooting annotations. Compared to the original YOLOv8, the proposed YOLOv8-GR achieves a 22.5% improvement in mAP50 and a 10.0% improvement in mAP50-95 on our dataset. We also compare YOLOv8-GR with the MobileNetv2-based SSD, which is a kind of one-stage object detection algorithm. While maintaining similar recognition accuracy, the computational cost of YOLOv8-GR is 9.9 GFLOPs, which is 15.8% of SSD, and our algorithm can be deployed on Raspberry Pi 4B.

关键词： Human computer interaction Solid modeling Accuracy Convolution Heuristic algorithms Gesture recognition Object detection Virtual reality Smart homes Kernel

来源：评论

学校读者我要写书评

暂无评论

Logical Relation Modeling and Mining in Hyperbolic Space for Recommendation 40

Logical Relation Modeling and Mining in Hyperbolic Space for...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Tan, Yanchao Lv, Hang Zhou, Zihao Guo, Wenzhong Xiong, Bo Liu, Weiming Chen, Chaochao Wang, Shiping Yang, Carl College of Computer and Data Science Fuzhou University Fuzhou China Engineering Research Center of Big Data Intelligence Ministry of Education Fuzhou China Fujian Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Institute for Artificial Intelligence University of Stuttgart Stuttgart Germany College of Computer Science Zhejiang University Hangzhou China Emory University Department of Computer Science Atlanta United States

ISBN: (纸本)9798350317152

The sparse interactions between users and items have aggravated the difficulty of their representations in recommender systems. Existing methods leverage tags to alleviate the sparsity problem but ignore prevalent logical relations among items and tags (e.g., membership, hierarchy, and exclusion), which can be leveraged to enhance the accuracy of modeling user preferences and conducting recommendations. To this end, we propose to extract logical relations among item tags from existing tag taxonomies and exploit the individual strengths of the Poincaré and the Lorentz models in hyperbolic space for logical relation modeling towards enhanced recommendations. Moreover, we find that the logical relations directly extracted from existing tag taxonomies can be inaccurate and coarse. Therefore, we further devise innovative consistency-based and granularity-based weighting mechanisms based on user behavior patterns for data-driven logical relation mining that can be jointly optimized along with recommendations in an end-to-end fashion. Extensive experiments on four real-world benchmark datasets show drastic performance gains brought by our proposed framework, which constantly achieves an average of 8.25% improvement over state-of-the-art competitors regarding both Recall and NDCG metrics. Insightful case studies further demonstrate that our automatically refined logical relations are highly accurate and interpretable. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Efficient Short Video Identification Attack for Scenarios with Hybrid Transmission Modes and Preloading Mechanism

Efficient Short Video Identification Attack for Scenarios wi...

引用

International Conference on Mobile Ad-hoc and Sensor networks, MSN

作者： Jingwen Quan Jiajia Du Hua Wu Guang Cheng Xiaoyan Hu School of Cyber Science and Engineering Southeast University Nanjing China Key Laboratory of Computer Network and Information Integration Ministry of Education Nanjing Jiangsu

ISBN: (数字)9798331516024

ISBN: (纸本)9798331516031

To protect user privacy, video traffic is usually encrypted during transmission. Some research has been con-ducted to implement video identification attacks by analyzing the features of video traffic. However, short video platforms use hybrid transmission modes and a preloading mechanism to improve user experience. These new characteristics make video identification attacks targeted at long videos not appliable to short videos. In this paper, we proposed a method for extracting and correcting the hybrid fingerprints of application layer video resources, and designed an SVP-DOHMM matching method for video identification. Our method can identify each video for scenarios with hybrid transmission modes and preloading mechanism. We implemented our method on the dataset con-taining more than 100,000 video fingerprints of a short video platform. The experimental results show that the accuracy can reach 98.16% by sniffing the traffic for only 10 seconds in the closed world and can identify videos with 97.64 % accuracy in the open world.

关键词： Privacy Accuracy Streaming media Fingerprint recognition Feature extraction User experience Sensors Cryptography

来源：评论

学校读者我要写书评

暂无评论

Task Offloading Strategy with Emergency Handling and Blockchain Security in SDN-Empowered and Fog-Assisted Healthcare IoT

引用

Tsinghua Science and Technology 2022年第4期27卷 760-776页

作者： Junyu Ren Jinze Li Huaxing Liu Tuanfa Qin School of Electronic and Information Engineering South China University of TechnologyGuangzhou 510640China Guangxi University Xingjian College of Science and Liberal Arts Nanning 530004China Guangxi Key Laboratory of Multimedia Communications and Network Technology Guangxi UniversityNanning 530004China Guangxi Key Laboratory of Multimedia Communications and Network Technology School of ComputerElectronics and InformationGuangxi UniversityNanning 530004China Faculty of Earth Sciences&Geography Trinity CollegeUniversity of CambridgeCambridgeCB21TNUK

With the rapid advancement of the Internet of Things(IoT),the typical application of wireless body area networks(WBANs)based smart healthcare has drawn wide attention from all sectors of *** alleviate the pressing challenges,such as resource limitations,low-latency service provision,mass data processing,rigid security demands,and the lack of a central entity,the advanced solutions of fog computing,software-defined networking(SDN)and blockchain are leveraged in this *** the basis of these solutions,a task offloading strategy with a centralized low-latency,secure and reliable decision-making algorithm having powerful emergency handling capacity(LSRDM-EH)is designed to facilitate the resource-constrained edge devices for task ***,to well ensure the security of the entire network,a comprehensive blockchain-based two-layer and multidimensional security strategy is ***,to tackle the inherent time-inefficiency problem of blockchain,we propose a blockchain sharding scheme to reduce system time *** simulation has been conducted to validate the performance of the proposed measures,and numerical results verify the superiority of our methods with lower time-latency,higher reliability and security.

关键词： wireless body area networks(WBANs) healthcare IoT software-defined networking(SDN) fog computing blockchain task offloading blockchain sharding

来源：评论

学校读者我要写书评

暂无评论

UDT:U-shaped deformable transformer for subarachnoid haemorrhage image segmentation

引用

CAAI Transactions on Intelligence Technology 2024年第3期9卷 756-768页

作者： Wei Xie Lianghao Jin Shiqi Hua Hao Sun Bo Sun Zhigang Tu Jun Liu Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Central China Normal UniversityWuhanChina School of Computer Science Central China Normal UniversityWuhanChina National Language Resources Monitoring and Research Center for Network Media Central China Normal UniversityWuhanChina The First Affiliated Hospital of Dalian Medical University DalianChina State Key Laboratory of Information Engineering in Surveying Mapping and Remote SensingWuhan UniversityWuhanChina Information Systems Technology and Design Pillar Singapore University of Technology and DesignSingaporeSingapore

Subarachnoid haemorrhage(SAH),mostly caused by the rupture of intracranial aneu-rysm,is a common disease with a high fatality *** lesions are generally diffusely distributed,showing a variety of scales with irregular *** complex characteristics of lesions make SAH segmentation a challenging *** cope with these difficulties,a u-shaped deformable transformer(UDT)is proposed for SAH ***,first,a multi-scale deformable attention(MSDA)module is exploited to model the diffuseness and scale-variant characteristics of SAH lesions,where the MSDA module can fuse features in different scales and adjust the attention field of each element dynamically to generate discriminative multi-scale ***,the cross deformable attention-based skip connection(CDASC)module is designed to model the irregular edge char-acteristic of SAH lesions,where the CDASC module can utilise the spatial details from encoder features to refine the spatial information of decoder ***,the MSDA and CDASC modules are embedded into the backbone Res-UNet to construct the proposed *** experiments are conducted on the self-built SAH-CT dataset and two public medical datasets(GlaS and MoNuSeg).Experimental results show that the presented UDT achieves the state-of-the-art performance.

关键词： image segmentation medical image processing

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：