检索结果-内蒙古大学图书馆

International Conference on Information and computer Technologies (ICICT)

作者： Haoling Dong Bin Wu School of Computer Science (National Pilot Software Engineering School) Beijing University of Post and Telecommunications Beijing China

ISBN: (数字)9798350385625

ISBN: (纸本)9798350385632

With the continuous enhancement of informatization in production safety, the need to strengthen the analysis capability of big data in production safety is increasingly growing. This is crucial for preventing major accidents and ensuring production safety. However, the main challenge currently faced is that information about safety hazards often appears in unstructured text formats, lacking a unified standard and normative system. This makes it difficult to standardize knowledge extraction from hazard information. Additionally, traditional named entity recognition methods arc inadequate in understanding sentence structures, lexical components, and the dependency relationships between words, especially in processing texts in specific complex domains, where their entity recognition effects arc still insufficient. Given this, the research focus of this paper includes: deeply exploring the concept and connotation of big data in hazard information, clarifying the classification system of hazard information; designing a standard hazard information annotation template specifically for the field of production safety; designing a named entity recognition method based on GBD; designing and implementing a named entity recognition method based on LLMs; and based on the recognition results, constructing a knowledge graph of the relevant field to promote its effective utilization in practical applications.

关键词： Analytical models Text recognition Annotations Computational modeling Production Knowledge graphs Big Data

来源：评论

学校读者我要写书评

暂无评论

ELTA: an enhancer against long-tail for aesthetics-oriented models 24

ELTA: an enhancer against long-tail for aesthetics-oriented ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Limin Liu Shuai He Anlong Ming Rui Xie Huadong Ma School of Computer Science National Pilot Software Engineering School Beijing University of Posts and Telecommunications Beijing China

Real-world datasets often exhibit long-tailed distributions, compromising the generalization and fairness of learning-based models. This issue is particularly pronounced in Image Aesthetics Assessment (IAA) tasks, where such imbalance is difficult to mitigate due to a severe distribution mismatch between features and labels, as well as the great sensitivity of aesthetics to image variations. To address these issues, we propose an Enhancer against Long-Tail for Aesthetics-oriented models (ELTA). ELTA first utilizes a dedicated mixup technique to enhance minority feature representation in high-level space while preserving their intrinsic aesthetic qualities. Next, it aligns features and labels through a similarity consistency approach, effectively alleviating the distribution mismatch. Finally, ELTA adopts a specific strategy to refine the output distribution, thereby enhancing the quality of pseudo-labels. Experiments on four representative datasets (AVA, AADB, TAD66K, and PARA) show that our proposed ELTA achieves state-of-the-art performance by effectively mitigating the long-tailed issue in IAA datasets. Moreover, ELTA is designed with plug-and-play capabilities for seamless integration with existing methods. To our knowledge, this is the first contribution in the IAA community addressing long-tail. All resources are available in https://***/woshidandan/Long-Tail-image-aesthetics-and-quality-assessment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

An Enhancing NSGA-II with Neighborhood Search-based Approach to Customized Bus Route Planning

An Enhancing NSGA-II with Neighborhood Search-based Approach...

引用

Electronic Communication and Artificial Intelligence (IWECAI), International Workshop on

作者： Hui Feng School of computer science (national pilot software engineering school) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350386943

ISBN: (纸本)9798350386950

In recent years, customized bus services have seen extensive application in cities meet the growing personalized travel needs. The core competitiveness of CB is that customized bus routes can be planned according to passenger reservation needs before operation. However, existing research often overlooks the impact of random factors on the overall system's operation. This study addresses passenger cancellations and incorporates the losses from unserved reserved passengers into a multi-objective optimization model. It also considers the impact of road congestion and detours on passenger arrival times during actual operations. We introduce an improved non-dominated sorting genetic algorithm (NSGA-II) with neighborhood search, incorporate a variety of improved operators, and develop a shielding mechanism to identify passenger cancellations within the system. Computational experiments of varying scales demonstrate that the improved algorithm excels in both solution quality and computational efficiency. This method effectively balances operational efficiency and service quality, making it a viable solution for practical customized bus operations.

关键词： Uncertainty Heuristic algorithms Roads Urban areas Search problems Planning Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

Cross-Domain Disentangled Learning for E-Commerce Live Streaming Recommendation 39

Cross-Domain Disentangled Learning for E-Commerce Live Strea...

引用

39th IEEE International Conference on Data engineering, ICDE 2023

作者： Zhang, Yixin Liu, Yong Xiong, Hao Liu, Yi Yu, Fuqiang He, Wei Xu, Yonghui Cui, Lizhen Miao, Chunyan School of Software Shandong University China Shandong University China Alibaba-NTU Singapore Joint Research Institute Singapore Alibaba Group China School of Computer Science and Engineering Nanyang Technological University Singapore

ISBN: (纸本)9798350322279

E-commerce live streaming as an increasingly popular sales model has generated a significant amount of gross merchandise value (GMV) for e-commerce platforms. Live streaming recommendation systems (LSRS) of e-commerce aim to recommend the most appropriate live channels for users to motivate them to buy products. Existing LSRS methods focus only on the user's interaction behaviors on the live channel (live domain) while ignoring the user's behaviors and intentions on the e-commerce product (product domain). As a result, the user's consistent purchase intentions in the cross-domain are not being fully captured, especially when user present differentiated purchase intentions in the cross-domain. How to disentangle user's consistent intentions and domain-specific intentions in the cross-domain poses a challenge to the LSRS of e-commerce platforms. In this paper, we present a live channel recommendation method, named eLiveRec, developed for Taobao, one of the largest e-commerce platform in the world. Specifically, eLiveRec employs the disentangled encoder module to learn user's cross-domain consistent intentions and domain-specific intentions. Then, an adaptive multi-task learning framework is developed to jointly optimize the multiple objectives (e.g., stay time, click goods bag, and click products after entering channel) related to live streaming recommendation. In this way, the performance of live streaming recommendation can be further improved and con-form to standard industry RS paradigms. Extensive experiments are conducted on a large-scale industry dataset collected from Taobao Live platform have been performed. Both online and offline experimental results indicate that eLiveRec consistently outperforms existing state-of-the-art baseline methods. © 2023 IEEE.

关键词： Electronic commerce

来源：评论

学校读者我要写书评

暂无评论

CSText: An Expansive and Diverse Dataset for Advancing Chinese Text Detection

CSText: An Expansive and Diverse Dataset for Advancing Chine...

引用

Artificial Intelligence Technology (ACAIT), Asian Conference on

作者： Ziqi Shi Danfeng Yan Deye Qiu Chenhao Guo School of Computer Science(National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798331517090

ISBN: (纸本)9798331517106

Being an integral part of computer vision, text detection plays a pivotal role. With Chinese being one of the most adopted languages worldwide, its text detection garners immense relevance in scholarly research and practical applications. Noticing an acute shortage of Chinese text datasets and the limitations of existing collections, we present CSText (Chinese Scene Text), an innovative dataset. It incorporates 5,161 images sourced from 34 provincial capitals of China. Thoroughly assembled, this dataset addresses the complexities of Chinese text detection in organic settings. The variety brought forth by multiple fonts, lighting conditions, and backgrounds in this comprehensive dataset poses substantial challenges. Encompassing 32,701 text instances, CSText is a versatile tool for gauging the robustness and effectiveness of text detection models. Along with the dataset, we furnish baseline results utilizing the latest text detection techniques and devise ablation studies based on text object size and image density. The dataset is accessible to the public.

关键词： Training computer vision Dictionaries Computational modeling Text detection Lighting Benchmark testing Robustness Complexity theory Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Real-time crowd counting via mobile-friendly Vision Transformer network 34

Real-time crowd counting via mobile-friendly Vision Transfor...

引用

Pattern Recognition and Tracking XXXIV 2023

作者： Ji, Peirong Wu, Zhiwei Chen, Yan Alam, Mohammad S. Sang, Jun School of Big Data & Software Engineering Chongqing University Chongqing401331 China Department of Electrical Engineering and Computer Science Texas A&M University - Kingsville KingsvilleTX78363-8202 United States

ISBN: (数字)9781510661691

ISBN: (纸本)9781510661684

Accurate crowd counting in congested scenes remain challengeable in the trade-off of efficiency and generalization. For solving this issue, we propose a mobile-friendly solution for the network deployment in high response speed demand scenarios. In order to introduce the profound potential of global crowd representations to lightweight counting model, this work suggests a novel crowd counting aimed mobile vision transformers architecture (CCMTNet), which strives for enhancing the efficiency of the model universality in real-time crowd counting tasks on resource constrained computing devices. The framework of linear CNN network interpolation structure with self-attention blocks endows the model with the ability of local feature extraction and global high-dimensional crowd information processing with low computational cost. In addition, several experimental networks with different scales based on the proposed architecture are comprehensively verified to balance the accuracy loss as compressing the computing costs. Extensive experiments on three mainstream datasets for crowd counting tasks well demonstrate the effectiveness of this proposed network. Particularly, CCMTNet achieves the feasibility of reconciling the counting accuracy and efficiency in comparisons with traditional lightweight CNN networks. © 2023 SPIE.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Data Augmentation for Sequential Recommendation: A Survey

arXiv

引用

arXiv 2024年

作者： Dang, Yizhou Yang, Enneng Liu, Yuting Guo, Guibing Jiang, Linying Zhao, Jianzhe Wang, Xingwei Software College Northeastern University China School of Computer Science and Engineering Northeastern University China

As an essential branch of recommender systems, sequential recommendation (SR) has received much attention due to its well-consistency with real-world situations. However, the widespread data sparsity issue limits the SR model’s performance. Therefore, researchers have proposed many data augmentation (DA) methods to mitigate this phenomenon and have achieved impressive progress. In this survey, we provide a comprehensive review of DA methods for SR. We start by introducing the research background and motivation. Then, we categorize existing methodologies regarding their augmentation principles, objects, and purposes. Next, we present a comparative discussion of their advantages and disadvantages, followed by the exhibition and analysis of representative experimental results. Finally, we outline directions for future research and summarize this survey. We also maintain a repository with a paper list at https://***/KingGugu/DA-CL-4Rec. © 2024, CC BY.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Hola-TTS: A Cross-Lingual Zero-Shot Text-to-Speech System for Chinese, English, Japanese, and Korean

Hola-TTS: A Cross-Lingual Zero-Shot Text-to-Speech System fo...

引用

International Symposium on Chinese Spoken Language Processing

作者： Hongwu Ding Yiquan Zhou Wenyu Wang JiaCheng Xu Jiaqi Mei School of Computer Science and Technology Anhui University Hefei School of Software Engineering Xi'an Jiaotong University Xi'an

ISBN: (数字)9798331516826

ISBN: (纸本)9798331516833

This paper presents Hola-TTS, a novel cross-lingual zero-shot text-to-speech system capable of synthesizing speech in Chinese, English, Japanese, and Korean. We introduce several key innovations, including a comprehensive data cleaning process, a multilingual phoneme representation strategy, and an improved model architecture. Hola-TTS employs a fully autoregressive method for token generation and utilizes a delay parttern approach, which significantly enhance dependencies between different codebooks at the same time step. Our model is trained on a diverse set of cleaned speech recognition datasets and uses phoneme-level language label to enhance cross-lingual synthesis capabilities. Comparative evaluations demonstrate that Hola-TTS outperforms state-of-the-art models like VALL-E X and X-TTS across various metrics. Ablation studies further confirm the effectiveness of our proposed improvements compare to VoiceCraft. This work represents a significant advancement in multilingual speech synthesis, offering improved quality, consistency, and cross-lingual capabilities in zero-shot TTS. We encourage readers to listen to the demos at https://***/

关键词： Measurement Technological innovation Speech coding Training data Speech recognition Data models Cleaning Text to speech Multilingual Delays

来源：评论

学校读者我要写书评

暂无评论

DFFNet: Dual-Channel Feature Fusion Network for End-to-End 6D Pose Estimation

DFFNet: Dual-Channel Feature Fusion Network for End-to-End 6...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yinning Lu Songwei Pei School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Recently, the popular RGB-based 6D pose estimation methods follow the two-stage paradigm, in which the sparse or dense 2D-3D correspondences between the RGB image and the CAD model are first established, and then the 6D pose is estimated based on the PnP/RANSAC algorithm or its variants. Although such methods are considered effective and achieve excellent performance, this two-stage pipeline cannot be end-to-end trainable and is time-consuming. In this work, we propose a one-stage Dual-Channel Feature Fusion Network for End-to-End 6D Pose Estimation (DFFNet), in which an Implicit Pose Feature Extraction Channel is designed to extract the implicit pose features inside each 2D-3D correspondence and an Implicit Topological Feature Extraction Channel is designed to extract the geometric topological features implicitly expressed by each group of 2D-3D correspondences. The different features extracted by the two channels are fused to regress the 6D pose of the object. DFFNet is generic and can be combined with the existing sparse 2D-3D correspondence-extraction network to eliminate the cumbersome RANSAC process and form an overall end-to-end trainable framework. Experiments show that our proposed method outperforms the one-stage and some other two-stage 6D pose estimation methods.

关键词： Solid modeling Network topology Pose estimation Pipelines Neural networks Channel estimation Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional Neural Network Approach for COVID-19 Detection

引用

computer Systems science & engineering 2022年第7期42卷 201-211页

作者： Yu Xue Bernard-Marie Onzo Romany F.Mansour Shoubao Su School of Computer and Software Nanjing University of Information Science and TechnologyNanjing210044China Engineering Research Center of Digital Forensics Ministry of EducationNanjing University of Information Science and TechnologyNanjingChina Department of Mathematics Faculty of ScienceNew Valley UniversityEl-Kharja72511Egypt Jiangsu Key Laboratory of Data Science and Smart Software Jinling Institute of TechnologyNanjing211169China

Coronavirus disease 2019(Covid-19)is a life-threatening infectious disease caused by a newly discovered strain of the *** by the end of 2020,Covid-19 is still not fully understood,but like other similar viruses,the main mode of transmission or spread is believed to be through droplets from coughs and sneezes of infected *** accurate detection of Covid-19 cases poses some questions to scientists and *** two main kinds of tests available for Covid-19 are viral tests,which tells you whether you are currently infected and antibody test,which tells if you had been infected ***-tine Covid-19 test can take up to 2 days to complete;in reducing chances of false negative results,serial testing is *** image processing by means of using Chest X-ray images and Computed Tomography(CT)can help radiologists detect the *** imaging approach can detect certain characteristic changes in the lung associated with *** this paper,a deep learning model or tech-nique based on the Convolutional Neural Network is proposed to improve the accuracy and precisely detect Covid-19 from Chest Xray scans by identifying structural abnormalities in scans or X-ray *** entire model proposed is categorized into three stages:dataset,data pre-processing andﬁnal stage being training and classiﬁcation.

关键词： COVID-19 deep learning convolutional neural network X-ray

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：