检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Liang, Jiye Li, Yixiao Cui, Junbiao Key Laboratory of Computational Intelligence and Chinese Information Processing of Ministry of Education School of Computer and Information Technology Shanxi University Shanxi Taiyuan 030006 China

ISBN: (纸本)157735897X

The ubiquitous and unavoidable label noise brings great challenges to the generalization performance of learning methods. Label noise correction aims to detect and correct label noise in the data, which is one of the most potential methods to address this challenge. Current methods for label noise filtering that utilize primitive features primarily concentrate on identifying noise, which often limits their capacity to adaptively learn features crucial for specific tasks, thereby resulting in a higher rate of noise identification within the noise recognition process. On the other hand, deep neural networks, endowed with robust feature extraction capabilities, typically exhibit lower noise identification, as they are prone to fitting noise patterns during the recognition process, potentially undermining their overall efficacy. Moreover, Fuzzy Learning Machine (FLM) excels not only in feature extraction but also in noise tolerance, adeptly navigating data uncertainties. FLM enhances the accuracy of the labels by calculating the membership degrees of samples across categories and determining their fuzzy memberships. The introduction of a two-stage FLM-based framework, which employs a secondary learning mechanism for precise noise filtering and correction, has shown substantial improvements in noise correction across various large-scale noisy datasets, thereby significantly enhancing samples' quality and boosting the generalization capabilities of classifiers. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Time Series Data Association Mining With High-Frequency Data Interference 24

Time Series Data Association Mining With High-Frequency Data...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data Science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Zhu, Rongjing Li, Peng Liu, Yu Deng, Miao School of Computer Science and Technology Wuhan University of Science and Technology China Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System China

ISBN: (纸本)9798350319934

Time series data mining is an important problem in data mining. It discovers the intrinsic correlation rules by analyzing a large amount of time series data. However, high-frequency data may exist in the dataset. High-frequency data is the data that occurs frequently in time series data, which will affect the mining of association rules. Traditional time series association mining tends to classify high-frequency data as correlated data because they co-occur too many times. In this paper, we propose the list mining framework to mine the association data by list co-occurrence to achieve the mining of massive data. We divide it into three phases, list generation phase, matrix generation phase, and rule generation phase. First, we create data lists based on time windows. Second, we create the initial count matrix, update the count matrix based on the list, and propose a GCPM algorithm to generate a conditional probability matrix based on the count matrix. Third, we propose a List Mining (LM) algorithm to generate the initial rules based on the conditional probability matrix and optimize the initial rules to get the final association rules. In addition, we weigh the rules according to the list mining method and propose a Weighted List Mining (WLM) algorithm to filter rules by reducing the weight of frequent item interference. The experimental results show that LM and WLM can effectively improve the accuracy of mining results. © 2022 IEEE.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

Prediction of GDP Carbon Emission Based on Grey Model and Neural Network 4th

Prediction of GDP Carbon Emission Based on Grey Model and Ne...

引用

4th EAI International Conference on Robotic Sensor Networks, 2020

作者： Zhang, Feng Zhao, Huihuang Ramasamy, Manimaran College of Computer Science and Technology Hengyang Normal University Hengyang China Hunan Provincial Key Laboratory of Intelligent Information Processing and Application Hengyang China

ISBN: (纸本)9783030704506

In order to improve the prediction accuracy of Gross Domestic Product (GDP) carbon emission, combining the advantages of grey prediction and neural network, a discrete grey neural network prediction model named DGMBP is established. This model not only has the advantages of less data sample and larger development coefficient range of GM 1,1 model but also combines the advantages of neural network to deal with nonlinear data sample. Taking the GDP carbon emission data of China, India, the United States and the European Union as an example, the prediction results obtained are stable, and the accuracy of the prediction data is over 95%, which is much higher than that obtained by the linear regression equation and the logical regression equation. Finally, the carbon emission of GDP in 2020–2030 is predicted by using this model. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Embedding expert demonstrations into clustering buffer for effective deep reinforcement learning

引用

Frontiers of information technology & Electronic Engineering 2023年第11期24卷 1541-1556页

作者： Shihmin WANG Binqi ZHAO Zhengfeng ZHANG Junping ZHANG Jian PU Shanghai Key Laboratory of Intelligent Information Processing School of Computer ScienceFudan UniversityShanghai 200433China Institute of Science and Technology for Brain-inspired Intelligence Fudan UniversityShanghai 200433China

As one of the most fundamental topics in reinforcement learning(RL),sample efficiency is essential to the deployment of deep RL *** most existing exploration methods that sample an action from different types of posterior distributions,we focus on the policy sampling process and propose an efficient selective sampling approach to improve sample efficiency by modeling the internal hierarchy of the ***,we first employ clustering methods in the policy sampling process to generate an action candidate *** we introduce a clustering buffer for modeling the internal hierarchy,which consists of on-policy data,off-policy data,and expert data to evaluate actions from the clusters in the action candidate set in the exploration *** this way,our approach is able to take advantage of the supervision information in the expert demonstration *** on six different continuous locomotion environments demonstrate superior reinforcement learning performance and faster convergence of selective *** particular,on the LGSVL task,our method can reduce the number of convergence steps by 46.7%and the convergence time by 28.5%.Furthermore,our code is open-source for *** code is available at https://***/Shihwin/SelectiveSampling.

关键词： Reinforcement learning Sample eficiency Sampling process Clustering methods Autonomous driving

来源：评论

学校读者我要写书评

暂无评论

An English Pronunciation Quality Evaluation Model Based on Multi-dimensional Features 2

An English Pronunciation Quality Evaluation Model Based on M...

引用

2021 2nd International Symposium on Automation, information and Computing, ISAIC 2021

作者： Li, Yiqun Huang, Guimin Guangxi Key Laboratory of Image and Graphic Intelligent Processing School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China

As a universal language, English has been paid more and more attention, among which oral English learning is very important. In this paper, the two key technologies of pronunciation error detection and quality evaluation are studied, both of them are effectively integrated, aiming to build a model for L2 learners' English pronunciation quality evaluation. This paper mainly studies two different methods of pronunciation error detection. Based on the speech recognition framework, the standard score is compared with the threshold to judge the correctness of phoneme pronunciation, and the phoneme-dependent threshold is set to improve the maximum Precision to 0.44. By judging the correct pronunciation and confusing phoneme, the accuracy of pronunciation error detection is improved to 81.26%. This paper proposes the fusion algorithm from multi-dimensions of speech fluency and intonation respectively, and a newly designed feature called word duration ratio, which significantly improve the correlation of pronunciation quality evaluation to 0.746. © Published under licence by IOP Publishing Ltd.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

UltraEdit: instruction-based fine-grained image editing at scale 24

UltraEdit: instruction-based fine-grained image editing at s...

引用

Proceedings of the 38th International Conference on Neural information processing Systems

作者： Haozhe Zhao Xiaojian Ma Liang Chen Shuzheng Si Rujie Wu Kaikai An Peiyu Yu Minjia Zhang Qing Li Baobao Chang National Key Laboratory for Multimedia Information Processing Peking University and School of Software and Microelectronics Peking University State Key Laboratory of General Artificial Intelligence BIGAI National Key Laboratory for Multimedia Information Processing Peking University and School of Computer Science Peking University China Department of Computer Science and Technology Tsinghua University School of Computer Science Peking University China UCLA UIUC National Key Laboratory for Multimedia Information Processing Peking University

ISBN: (纸本)9798331314385

This paper presents UltraEdit, a large-scale (~4M editing samples), automatically generated dataset for instruction-based image editing. Our key idea is to address the drawbacks in existing image editing datasets like InstructPix2Pix [10] and MagicBrush [71], and provide a systematic approach to producing massive and high-quality image editing samples. UltraEdit offers several distinct advantages: 1) It features a broader range of editing instructions by leveraging the creativity of large language models (LLMs) alongside in-context editing examples from human raters; 2) Its data sources are based on real images, including photographs and artworks, which provide greater diversity and reduced bias compared to datasets solely generated by text-to-image models; 3) It also supports region-based editing, enhanced by high-quality, automatically produced region annotations. Our experiments show that canonical diffusion-based editing baselines trained on UltraEdit set new records on MagicBrush and Emu-Edit benchmarks. Our analysis further confirms the crucial role of real image anchors and region-based editing data. The dataset, code, and models are available in ***/pkunlp-icler/UltraEdit.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese image captioning via double decoding based on visual prompts 5

Chinese image captioning via double decoding based on visual...

引用

5th International Conference on computer Vision and Data Mining, ICCVDM 2024

作者： Tan, Weiguo Xiao, Yannan Wen, Yayuan Deng, Zhenrong Huang, Wenming School of Computer Science and Information Security Guilin University of Electronic Technology Guangxi Guilin541004 China Guangxi Key Laboratory of Image and Graphic Intelligent Processing Guangxi Guilin China College of Electronic Engineering Guangxi Normal University Guangxi Guilin China

ISBN: (纸本)9781510682863

The significant progress of vision-language pre-trained models (VLMs) and large language models (LLMs) have provided a feasible new mode for image captioning, which relies on VLMs to process images and then utilizes LLMs to generate captions, simplifying the caption generation process and making it lighter. Based on this mode, to address the issues of deviation between the generated captions and the content of image expressions, incomplete descriptive information, and resource hungry in previous Chinese image captioning models, we propose a Chinese image captioning model via double decoding based on Visual Prompts, DDVP. This model employs the CLIP model as the encoder, the GPT2 model as the decoder, and introduces Visual Prompts, which are keywords related to image content. The model adopts a double decoding approach, first decoding to generate Visual Prompts and then decoding to generate the final captions based on the Visual Prompts. Through evaluation, we have demonstrated that our model achieves competitive results on the AIC-ICC dataset, and while maintaining fluency, the generated captions of DDVP can also cover the information in the image more comprehensively and accurately. © 2024 SPIE.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

ReconBoost: Boosting Can Achieve Modality Reconcilement 41

ReconBoost: Boosting Can Achieve Modality Reconcilement

引用

41st International Conference on Machine Learning, ICML 2024

作者： Hua, Cong Xu, Qianqian Bao, Shilong Yang, Zhiyong Huang, Qingming Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores a novel multi-modal alternating learning paradigm pursuing a reconciliation between the exploitation of uni-modal features and the exploration of cross-modal interactions. This is motivated by the fact that current paradigms of multi-modal learning tend to explore multi-modal features simultaneously. The resulting gradient prohibits further exploitation of the features in the weak modality, leading to modality competition, where the dominant modality overpowers the learning process. To address this issue, we study the modality-alternating learning paradigm to achieve reconcilement. Specifically, we propose a new method called ReconBoost to update a fixed modality each time. Herein, the learning objective is dynamically adjusted with a reconcilement regularization against competition with the historical models. By choosing a KL-based reconcilement, we show that the proposed method resembles Friedman's Gradient-Boosting (GB) algorithm, where the updated learner can correct errors made by others and help enhance the overall performance. The major difference with the classic GB is that we only preserve the newest model for each modality to avoid overfitting caused by ensembling strong learners. Furthermore, we propose a memory consolidation scheme and a global rectification scheme to make this strategy more effective. Experiments over six multi-modal benchmarks speak to the efficacy of the method. We release the code at https://***/huacong/ReconBoost. Copyright 2024 by the author(s)

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Coverage Enhancement Strategy Based on Novel Perception and Co-Evolution for Multimedia Sensor Networks

引用

Chinese Journal of Electronics 2023年第1期22卷 135-140页

作者： Fu Xiao Jing Wang Lijuan Sun Ruchuan Wang Jian Guo College of Computer Nanjing University of Posts and Telecommunications Nanjing China Jiangsu High Technology Research Key Laboratory for Wireless Sensor Networks Nanjing China Provincial Key Laboratory for Computer Information Processing Technology Soochow University Suzhou China Key Laboratory of Broadband Wireless Communication and Sensor Network Technology Ministry of Education Nanjing China

Coverage enhancement is one of the hot research topics in wireless multimedia sensor networks. A novel Coverage-enhancing algorithm based on three-dimensional Directional perception and co-evolution (DPCCA) is proposed in multimedia sensor networks on the basis of the model whose pitch angle and deviation angle can be adjusted. Based on the proposed elliptical cone sensing model, we can derive the coverage area of the node and calculate the optimal pitch angle according the information of monitoring area and the nodes, and then the deviation angle is optimized based on co-evolution algorithm, which eliminate the overlapped and blind sensing area effectively. A set of simulations demonstrate the effectiveness of our algorithm in coverage ratio.

关键词： Wireless communication Industries Solid modeling Wireless sensor networks Three-dimensional displays Medical services Sensors

来源：评论

学校读者我要写书评

暂无评论

STDNet: Spatio-Temporal Decomposed Network for Video Grounding

STDNet: Spatio-Temporal Decomposed Network for Video Groundi...

引用

2022 IEEE International Conference on Multimedia and Expo, ICME 2022

作者： Xu, Yuanwu Zhang, Yuejie Feng, Rui Zhao, Rui-Wei Zhang, Tao Lu, Xuequan Gao, Shang School of Computer Science Fudan University Shanghai Key Laboratory of Intelligent Information Processing China Academy for Engineering and Technology Fudan University China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai Key Laboratory of Financial Information Technology China School of Information Technology Deakin University Australia

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

Previous methods for video grounding treated either the query or the video as a whole, while neglecting their respective semantics in the orthogonal space and time dimensions. Since spatial semantics appears frequently in a video, temporal semantics is more discriminative and deserves more attention. Based on such considerations, we propose a novel Spatio-Temporal Decomposed Network (STDNet) which decomposes the query and the video into their spatial and temporal semantics, respectively. Specifically, spatial and temporal words are selected from the query, and the video is split into two pathways. Spatial cross-modal attention is computed first and serves as prior knowledge for temporal attention. A new localization strategy is also devised which regresses the segment's start conditioned on the end and essentially breaks the independence assumption made in previous methods. Experimental results on three public benchmark datasets show that our STDNet outperforms the state-of-the-art methods. © 2022 IEEE.

关键词： Semantics

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：