检索结果-内蒙古大学图书馆

FIFAWC:a dataset with detailed annotation and rich semantics for group activity recognition

Frontiers of Computer Science 2024年第6期18卷 271-272页

作者： Duoxuan PEI Di HUANG Yunhong WANG State Key Laboratory of Software Development Environment School of Computer Science and EngineeringBeihang UniversityBeijing 100191China Intelligent Recognition and Image Processing Lab. School of Computer Science and EngineeringBeihang UniversityBeijing 100191China

1 *** Activity Recognition(GAR),which aims to identify activities performed collectively in videos,has gained significant attention *** conventional action recognition centered on single individuals,GAR explores the c... 详细信息

关键词： has collective gained

来源：评论

学校读者我要写书评

暂无评论

A Sentiment Classification Model Based on Syntactic Graph Attention Networks 24

A Sentiment Classification Model Based on Syntactic Graph At...

引用

2024 International Conference on intelligent Education and Computer Technology, IECT 2024

作者： Cheng, Yan Zhou, Ziwei School of Computer Information Engineering Jiangxi Normal University Jiangxi Nanchang330022 China Prov. Key Lab. of Intelligent Information Processing and Affective Computing of Jiangxi Province 330022 China School of Software Jiangxi Normal University 330022 China

ISBN: (纸本)9798400709920

Text Sentiment Classification, a significant task in Natural Language Processing, aims to comprehend user needs and expectations by categorizing the sentiments of texts posted on platforms. Despite their utility, existing models for this task do not fully account for the influence of contextual and syntactic text features on sentiment classification. To address these issues, a text sentiment classification model based on syntactic graph attention network is proposed in this study. The model begins by extracting the contextual features of a sentence using BiGRU. It then generates a syntactic graph through a syntactic analyzer, using the contextual features as the node features of the syntactic graph. A syntactic graph attention network is constructed to extract the syntactic features of the syntactic graph. These feature vectors are then input into a softmax function to achieve text sentiment classification. Experimental results indicate that the proposed model outperforms similar models on two public datasets in terms of classification accuracy, thus demonstrating its effectiveness. © 2024 ACM.

关键词： Syntactics

来源：评论

学校读者我要写书评

暂无评论

myOCR: Optical Character Recognition for Myanmar language with Post-OCR Error Correction

myOCR: Optical Character Recognition for Myanmar language wi...

引用

International Joint Symposium on Artificial Intelligence and Natural Language Processing (iSAI-NLP)

作者： Thura Aung Ye Kyaw Thu Myat Noe Oo LU Lab. Myanmar Software Engineering SIIE KMITL Bangkok Thailand LU Lab. Myanmar LST AINRU NECTEC NSTDA Pathum Thani Thailand Robotics and AI Engineering SIIE KMITL Bangkok Thailand

ISBN: (数字)9798331509910

ISBN: (纸本)9798331509927

This paper presents the Myanmar Optical Character Recognition (OCR), named myOCR. It utilizes a synthetic text image dataset with 14 different font styles that contains 25,790 text images. The system includes Convolutional Neural Networks (CNN) for feature extraction, Bidirectional Long-Short Term Memory (BiLSTM) networks for sequence modeling, and Connectionist Temporal Classification (CTC) for decoding, evaluated across various iterations (3,000, 6,000, 9,000) and hidden states (64, 128, 256). Statistical Post-OCR correction methods involve N(3,4,5)-grams and edit distances with the Symmetric Delete Spelling correction algorithm (SymSpell). For Neural Machine Translation-based correction, BiLSTM and Transformer models are employed, while the mT5-base and mBART-50 models are used for LLM-based correction. The best base (optical) model is the model with 9,000 iterations that achieved a chrF ++ score of over 97.90 and a Word Error Rate (WER) of 9.18%. Transformer correction improved its chrF ++ to 99.31 and reduced the WER to 0.66%.

关键词： Translation Optical character recognition Bidirectional long short term memory Transformers Optical imaging Feature extraction Adaptive optics Natural language processing Convolutional neural networks Iterative decoding

来源：评论

学校读者我要写书评

暂无评论

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Language-Image Pre-Training 24

FLIP-80M: 80 Million Visual-Linguistic Pairs for Facial Lang...

引用

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Yudong Hou, Xianxu Dezhi, Zheng Shen, Linlin Zhao, Zhe School of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen China School of AI and Advanced Computing Xi'an Jiaotong-Liverpool University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen University Shenzhen China Tencent AI Lab Beijing China

ISBN: (纸本)9798400706868

While significant progress has been made in multi-modal learning driven by large-scale image-text datasets, there is still a noticeable gap in the availab.lity of such datasets within the facial domain. To facilitate and advance the field of facial representation learning, we present FLIP-80M, a large-scale visual-linguistic dataset comprising over 80 million face images paired with text descriptions. FLIP-80M is constructed by leveraging the large openly availab.e image-text-pair dataset LAION-5B and a mixed-method approach to filter face-related pairs from both visual and linguistic perspectives. Our curation process involves face detection, face caption classification, text de-noising, and synthesis-based image augmentation. As a result, FLIP-80M stands as the largest face-text dataset to date. To evaluate the potential of our dataset, we fine-tune the CLIP model using the proposed FLIP-80M, to create FLIP (Facial Language-Image Pretraining) and assess its representation capabilities across various downstream tasks. Our experiments demonstrate that our FLIP model achieves state-of-the-art results in a range of face analysis tasks, including face parsing, face alignment, and face attribute classification. The dataset and models are availab.e at https://***/ydli-ai/FLIP. © 2024 ACM.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

An improved Pearson coefficient based literature recommendation system for small research teams 13

An improved Pearson coefficient based literature recommendat...

引用

13th International Conference on intelligent Human-Machine Systems and Cybernetics, IHMSC 2021

作者： Cai, Hongxia Wang, Cheng Liu, Zhishu Shanghai University Shanghai Key Lab. of Intelligent Mfg. and Robotics School of Mechatronic Engineering and Automation Shanghai China

ISBN: (纸本)9781665428361

Recommendation technologies can help users to solve the problem of information overload. In the academic and educational fields, the application of intelligent recommendation technology has largely improved the effective use of academic resources, especially for researchers whose research tasks are constantly updated by research teams. In this paper, we propose a recommendation method that takes into account the changing stages of researchers' tasks and the needs of researchers' tasks. The recommendation model first considers user task and demand changes over time, introduces the forgetting function based on the Ebbinghaus forgetting curve into user features to create a dynamic user preference matrix, then uses the improved TF-IDF algorithm to extract article features to correlate user task demands with article features to avoid the problem of irrelevance of literature and user tasks, and finally by linear combination of Finally, the similarity between users and the similarity between users and documents is linked to generate a list of document recommendations. The experimental results show that the proposed method can better take into account the phase change of researchers' tasks and the correlation between research tasks and articles, and it is confirmed through experiments that the method has higher recommendation quality than the traditional collab.rative filtering method. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

intelligent recommendation system based on knowledge graph for scientific research teams 13

Intelligent recommendation system based on knowledge graph f...

引用

13th International Conference on intelligent Human-Machine Systems and Cybernetics, IHMSC 2021

作者： Cai, Hongxia Liu, Zhishu Wang, Cheng Shanghai University Shanghai Key Lab. of Intelligent Mfg. and Robotics School of Mechatronic Engineering and Automation Shanghai China

ISBN: (纸本)9781665428361

With the continuous penetration of information technology into scientific research work, information resources with diverse structures have gathered into the scientific research team. Facing the needs of scientific research workers to manage and utilize scientific research resources, we provide a knowledge recommendation platform for university scientific research teams. In the face of multi-source heterogeneous resources in the scientific research field (such as literature data and work record data), we have established a resource knowledge base based on knowledge graph descriptions. In order to realize the effective recommendation of resources, we use the graph neural network model to design a personalized recommendation module while constantly updating our knowledge resources. After actual testing, our resource platform can better knowledge resources and push knowledge content. © 2021 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Concrete Structural Crack Damage Classification Using Nonlinear Dimension Reduction and Broad Learning System

Concrete Structural Crack Damage Classification Using Nonlin...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Wang, Bingshu Lin, Jia Zhuang, Xiaodong Zhang, Guanghui Chen, C.L. Philip School of Software Northwestern Polytechnical University Xi'an China Shenzhen University Guangdong Key Lab. of Intelligent Info. Processing and Shenzhen Key Laboratory of Media Security Shenzhen China School of Computer Science and Technology Shandong University Qingdao China School of Computer Science and Engineering South China University of Technology Guangzhou China

ISBN: (纸本)9781665410205

Concrete structural crack damage classification is of importance for road safety. This paper proposes a new method based on broad neural network for crack damage classification in concrete structures. It includes three stages. Firstly, a pre-trained deep neural network is used to extract the features from crack images. Secondly, principal component analysis is used to project the retrieved features from high dimensions to low dimensions. Thirdly, broad learning system is employed to predict the classification using the low-dimensional features. Experimental results demonstrate that this method reduces the model's training time and improves classification accuracy. © 2024 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Three-Dimensional Optimal Trajectory Tracking Control of Underactuated Autonomous Underwater Vehicles Using Double Closed-Loop Control 5

Three-Dimensional Optimal Trajectory Tracking Control of Und...

引用

5th International Conference on intelligent Autonomous Systems, ICoIAS 2022

作者： Gong, Huibin Joo, Meng Liu, Tianhe Zhao, Xudong Institute of Artificial Intelligence and Marine Robotics College of Marine Electrical Engineering Dalian Maritime University Dalian China Dalian University of Technology Key Lab. of Intelligent Control and Optimization for Industrial Equipment of Ministry of Education Dalian China

ISBN: (数字)9781665498388

ISBN: (纸本)9781665498388

In this paper, a double closed-loop control method is proposed for three-dimensional optimal trajectory tracking control of underactuated autonomous underwater vehicles (AUVs), Firstly, a five-degree-of-freedom mathematical model of under-Actuated AUV is established. Secondly, an output redefinition method is adopted to solve underactuated control problem. On this basis, a backstepping method is utilized to design the outer-loop controller where virtual velocity is derived using the error between input and output of the system. Next, an adaptive dynamic programming method is used to design the inner-loop controller, where the performance index function containing the disturbance upper bound is set, and a neural network is employed to solve the Hamilton-Jacobi-Bellman equation online. Finally, the Lyapunov theorem is used to establish that all signals of the closed-loop system are uniformly ultimately bounded. Simulation results demonstrate the effectiveness of the proposed method. © 2022 IEEE.

关键词： Autonomous underwater vehicles

来源：评论

学校读者我要写书评

暂无评论

A Multi-stage Prediction Framework for Pest Identification 9

A Multi-stage Prediction Framework for Pest Identification

引用

9th IEEE International Conference on Cloud Computing and Intelligence Systems, CCIS 2023

作者： Chen, Yanan Chen, Miao Guo, Minghui Wang, Fangfang Wang, Jianji Institute of Artificial Intelligence and Robotics Xi'An Jiaotong University Natl. Key Lab. of Hum.-Mach. Hybrid Augmented Intell Natl. Eng. Res. Ctr. for Vis. Info. and Applic. China Xi'An Jiaotong University School of Software Engineering China

ISBN: (纸本)9798350304428

With the development of computer vision technology and smart agriculture, deep learning techniques have been widely applied to crop pest identification tasks. However, existing studies do not consider the problem of large differences in pests across multiple growth stages, leading to unsatisfactory performance in pest identification in practical applications. This article proposes a simple framework for multi-stage prediction of pests, which can effectively predict the growth stage of pests and improve pest classification performance. The framework consists of a classification branch and a stage prediction branch. The stage prediction branch predicts the growth stage of pests based on feature similarity using K-Means, and guides the classification branch to classify images from different stages into different categories to avoid interfering with the performance of the classifier. In addition, to update the entire network parameters, we propose a multi-stage cross-entropy loss that optimizes feature extractors and classifiers by fusing image lab.ls and stage prediction outputs. Experimental results show that the proposed multi-stage prediction framework for pest identification can accurately classify pest stages and improve pest classification accuracy. In addition, our work provides research ideas for pest stage prediction and identification, which is expected to help achieve more efficient pest control. © 2023 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Graph Representations and Graph Neural Networks for Multivariate Time Series Classification

arXiv

引用

arXiv 2025年

作者： Yang, Wennuo Wu, Shiling Zhou, Yuzhi Luo, Cheng He, Xilin Xie, Weicheng Shen, Linlin Song, Siyang 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 HBUG Lab University of Exeter United Kingdom

Multivariate Time Series Classification (MTSC) enables the analysis if complex temporal data, and thus serves as a cornerstone in various real-world applications, ranging from healthcare to finance. Since the relationship among variables in MTS usually contain crucial cues, a large number of graph-based MTSC approaches have been proposed, as the graph topology and edges can explicitly represent relationships among variables (channels), where not only various MTS graph representation learning strategies but also different Graph Neural Networks (GNNs) have been explored. Despite such progresses, there is no comprehensive study that fairly benchmarks and investigates the performances of existing widely-used graph representation learning strategies/GNN classifiers in the application of different MTSC tasks. In this paper, we present the first benchmark which systematically investigates the effectiveness of the widely-used three node feature definition strategies, four edge feature learning strategies and five GNN architecture, resulting in 60 different variants for graph-based MTSC. These variants are developed and evaluated with a standardized data pipeline and training/validation/testing strategy on 26 widely-used suspensor MTSC datasets. Our experiments highlight that node features significantly influence MTSC performance, while the visualization of edge features illustrates why adaptive edge learning outperforms other edge feature learning methods. The code of the proposed benchmark is publicly availab.e at https://***/CVI-yangwn/*** Codes 68T10 © 2025, CC BY.

关键词： Graph neural networks

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：