检索结果-内蒙古大学图书馆

18th Chinese Conference on Biometric Recognition, CCBR 2024

作者： Ma, Shuai He, Jinrong Wang, Yao Bi, Yingzhou Yang, Li College of Mathematics and Computer Science Yan’an University Yan’an716000 China Yan’an University Affiliated Hospital Yan’an716000 China Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning530100 China School Hospital Yan’an University Yan’an716000 China

ISBN: (纸本)9789819610709

Early diagnosis of pediatric adenoidal hypertrophy is crucial for timely identification of respiratory obstructions, thereby preventing declines in sleep quality that can lead to impaired growth, development, and cognitive function. Currently, the most common clinical diagnostic methods involve nasopharyngeal endoscopy and X-ray imaging assessments, which are time-consuming, labor-intensive, and costly. This paper presents an intelligent diagnostic model based on natural light facial images, employing a state space model (SSM). The model combines the local feature extraction capability of convolutional layers with the SSM’s ability to capture long-range dependencies for facial feature extraction. Furthermore, it incorporates a feature fusion strategy to enhance the features of facial images. Experimentation on a self-constructed dataset of adenoid facies images demonstrated that the model achieves an accuracy of 86.55% and an F1-score of 86.21%. The data and code are available at https://***/hejinrong/AF-SSM. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical imaging

来源：评论

学校读者我要写书评

暂无评论

Lightweight Method for Plant Disease Identification Using Deep Learning

引用

intelligent Automation & Soft Computing 2023年第7期37卷 525-544页

作者： Jianbo Lu Ruxin Shi Jin Tong Wenqi Cheng Xiaoya Ma Xiaobin Liu Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal UniversityNanning530001China School of Computer and Information Engineering Nanning Normal UniversityNanning530001China School of Logistics Management and Engineering Nanning Normal UniversityNanning530001China Hangzhou Hikvision Digital Technology Co.Ltd. Hangzhou310052China

In the deep learning approach for identifying plant diseases,the high complexity of the network model,the large number of parameters,and great computational effort make it challenging to deploy the model on terminal devices with limited computational *** this study,a lightweight method for plant diseases identification that is an improved version of the ShuffleNetV2 model is *** the proposed model,the depthwise convolution in the basic module of ShuffleNetV2 is replaced with mixed depthwise convolution to capture crop pest images with different resolutions;the efficient channel attention module is added into the ShuffleNetV2 model network structure to enhance the channel features;and the ReLU activation function is replaced with the ReLU6 activation function to prevent the gen-eration of large *** are conducted on the public dataset *** results show that the proposed model achieves an accuracy of 99.43%,which is an improvement of 0.6 percentage points compared to the ShuffleNetV2 *** to lightweight network models,such as MobileNetV2,MobileNetV3,EfficientNet,and EfficientNetV2,and classical convolutional neural network models,such as ResNet34,ResNet50,and ResNet101,the proposed model has fewer parameters and higher recognition accuracy,which provides guidance for deploying crop pest identification methods on resource-constrained devices,including mobile terminals.

关键词： Plant disease identification mixed depthwise convolution lightweight ShuffleNetV2 attention mechanism

来源：评论

学校读者我要写书评

暂无评论

Span-level Emotion-Cause-Category Triplet Extraction with Instruction Tuning LLMs and Data Augmentation

arXiv

引用

arXiv 2025年

作者： Li, Xiangju Yang, Dong Zhu, Xiaogang Huang, Faliang Zhang, Peng Zhao, Zhongying College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266500 China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning530100 China

Span-level emotion-cause-category triplet extraction represents a novel and complex challenge within emotion cause analysis. This task involves identifying emotion spans, cause spans, and their associated emotion categories within the text to form structured triplets. While prior research has predominantly concentrated on clause-level emotion-cause pair extraction and span-level emotion-cause detection, these methods often confront challenges originating from redundant information retrieval and difficulty in accurately determining emotion categories, particularly when emotions are expressed implicitly or ambiguously. To overcome these challenges, this study explores a fine-grained approach to span-level emotion-cause-category triplet extraction and introduces an innovative framework that leverages instruction tuning and data augmentation techniques based on large language models. The proposed method employs task-specific triplet extraction instructions and utilizes low-rank adaptation to fine-tune large language models, eliminating the necessity for intricate task-specific architectures. Furthermore, a prompt-based data augmentation strategy is developed to address data scarcity by guiding large language models in generating high-quality synthetic training data. Extensive experimental evaluations demonstrate that the proposed approach significantly outperforms existing baseline methods, achieving at least a 12.8% improvement in span-level emotion-cause-category triplet extraction metrics. The results demonstrate the method’s effectiveness and robustness, offering a promising avenue for advancing research in emotion cause analysis. The source code is available at https://***/zxgnlp/InstruDa-LLM. Copyright © 2025, The Authors. All rights reserved.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Please don't answer out of context: Personalized Dialogue Generation Fusing Persona and Context

Please don't answer out of context: Personalized Dialogue Ge...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Fucheng Wang Yunfei Yin Faliang Huang Kaigui Wu College of Computer Science Chongqing University Chongqing China Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China

In realistic conversations, “responses” are closely related to persona and context. However, current personalized dialogue generation methods only focus on the consistency of the persona of responses and yet ignore context coherence, as may produce low-quality responses. To address the issue, we propose a novel model, named PCF (Persona and Context Fusion), which builds two decoders for understanding personality consistency and context coherence respectively on a common encoder-decoder architecture. In this model, an inter-layer attention fusion mechanism is designed for the two decoders to effectively fuse persona and context, and a decoupled way of training is conducted on an additional large-scale non-dialogue inference dataset to enhance the consistent understanding ability of the two decoders. Furthermore, considering that generating responses may be tedious, the ScaleGrad loss function is applied to enhance the diversity of responses. Experimental results on two publicly available datasets show that the dialogues generated by our PCF are significantly higher in quality than strong baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Conditional Diffusion Model for Missing Value Imputation

SSRN

引用

SSRN 2024年

作者： Chen, Long Yuan, Changan Yuan, Guoqin Zhu, Xiaofeng Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Guangxi Academic of Sciences China University of Electronic Science and Technology of China China Key Laboratory of Airborne Optical Imaging and Measurement Fine Mechanics and Physics Chinese Academy of Science Changchun Institute of Optics China

With the rapid proliferation of social data, the prevalence of missing values has become increasingly commonplace. Data sets containing missing values not only consume storage space but also pose a significant obstacle to direct utilization, resulting in substantial resource wastage. Generative missing value imputation methods, leveraging generative models, have demonstrated notable efficacy in recent years by directly generating values for missing components based on observable data values. This paper introduces a novel generative method for missing value imputation based on a diffusion denoising model, termed the Conditional Diffusion Model for Missing Value Imputation (CDMVI). Specifically, CDMVI trains a conditional diffusion model using complete data samples and subsequently utilizes the trained model to impute missing values in datasets. During the training stage , a subset of feature is randomly selected from complete data samples, and varying levels of random noise are introduced as condition inputs to the noise predictor within the diffusion model. In the imputation stage, the missing segments of the data are initially replaced with random noise, serving as a guide for the diffusion model to generate complete samples. Experimental evaluations across multiple datasets demonstrate the competitive performance of our proposed CDMVI method. © 2024, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Personalized News Recommendation with Multi-granularity Candidate-aware User Modeling

arXiv

引用

arXiv 2025年

作者： Li, Qiang Lin, Xinze Lv, Shenghao Huang, Faliang Li, Xiangju Shandong Women’s University School of Data and Computer Science Jinan250002 China Shandong University of Science and Technology College of Computer Science and Engineering Qiangdao266500 China Nanning Normal University Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning530100 China

Matching candidate news with user interests is crucial for personalized news recommendations. Most existing methods can represent a user’s reading interests through a single profile based on clicked news, which may not fully capture the diversity of user interests. Although some approaches incorporate candidate news or topic information, they remain insufficient because they neglect the multi-granularity relatedness between candidate news and user interests. To address this, this study proposed a multi-granularity candidate-aware user modeling framework that integrated user interest features across various levels of granularity. It consisted of two main components: candidate news encoding and user modeling. A news textual information extractor and a knowledge-enhanced entity information extractor can capture candidate news features, and word-level, entity-level, and news-level candidate-aware mechanisms can provide a comprehensive representation of user interests. Extensive experiments on a real-world dataset demonstrated that the proposed model could significantly outperform baseline models∗ Copyright © 2025, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Chinese Text Classification Method Based on Double Pre-Processed Graph Aggregation Network

Chinese Text Classification Method Based on Double Pre-Proce...

引用

Data Intelligence and Innovative Application (DIIA), IEEE International Conference on

作者： Yixian He Jianhui Jiang Dingjia Chen Molan Tang Biquan Chen Weiqing Chen School of System and Computer Engineering North China Electric Power University Beijing China Guangxi Academy Sciences Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning China Guangxi Zhuang Autonomous Region Communication Industry Service Co. Ltd. Nanning China Guangxi Technology and Business Vocational College Nanning China

ISBN: (数字)9798331504434

ISBN: (纸本)9798331504441

To address the problem of insufficient node feature recognition and shallow network layers in Chinese text classification, this paper proposes a Chinese text classification method called Dual Preprocessing Graph Information Aggregation Network (DPGIAN). This method solves the problem of insufficient initial feature recognition of nodes and the inability of edge weights to highlight the weight ratio between keywords through a dual preprocessing strategy of node preprocessing and edge weight preprocessing; At the same time, a deeper graph information aggregation feature extraction method was used to solve the problem of excessive feature smoothing when obtaining deep semantic features in graph structured networks, improving the accuracy of Chinese text classification. By conducting experiments on multiple Chinese text classification datasets and comparing the experimental results with multiple mainstream text classification methods on the same dataset, our method outperforms the current mainstream text classification methods on the same dataset. Multiple ablation comparison experiments were also conducted to further verify the effectiveness of our method.

关键词： Smoothing methods Accuracy Text recognition Text categorization Semantics Feature extraction Graph neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

DRDM: A Disentangled Representations Diffusion Model for Syn...

引用

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

作者： Enbo Huang Yuan Zhang Faliang Huang Guangyu Zhang Yang Liu Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning China School of Computer and Information Engineering Nanning Normal University Nanning China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-sen University Guangzhou China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photorealistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control. The associated project can be found at https://***/lovemusiceb/DRDM

关键词： Limbs Image synthesis Shape Clothing Semantics Production Feature extraction Diffusion models Sampling methods Speech processing

来源：评论

学校读者我要写书评

暂无评论

Confidence-oriented Contrastive Graph Clustering

Confidence-oriented Contrastive Graph Clustering

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yan-Di Huang Guang-Yu Zhang Dong Huang Chang-Dong Wang Yang Liu Enbo Huang College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangdong Provincial Key Laboratory of Intellectual Property and Big Data Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China Guangxi Key Lab of Human-Machine Interaction and Intelligent Decision Nanning Normal University Nanning China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Contrastive clustering has recently been an emerging topic in deep unsupervised learning. Nevertheless, the previous works mostly adopt the stochastic data augmentations, which easily leads to the semantic drift problem by limited transformations. Moreover, these approaches ignore the data distribution information when generating the positive and negative pair-wise samples. In light of this, this paper proposes a simple yet effective unsupervised clustering network termed Confidence-oriented Contrastive Graph Clustering (CoCGC). Particularly, we design an end-to-end network paradigm with un-shared weights, among which a hybrid graph filter is utilized to generate two views of reliable augmentations. Guided by the non-dominated sorting theory, we further construct a confidence-oriented sample set from the latent data distribution perspective. By considering the local density and cluster distribution of the embedding representations, the discriminative sample pairs can be derived from the confidence-oriented sets in a two-view contrastive manner. Finally, a cross-view neighbor contrastive loss is devised for better exploiting the self-supervised network signals. Extensive experimental results on five benchmark datasets demonstrate the effectiveness of our method against the existing state-of-the-art deep graph clustering methods.

关键词： Network topology Semantics Neural networks Reliability theory Reliability engineering Information filters Filtering theory

来源：评论

学校读者我要写书评

暂无评论

DRDM: A Disentangled Representations Diffusion Model for Synthesizing Realistic Person Images

arXiv

引用

arXiv 2024年

作者： Huang, Enbo Zhang, Yuan Huang, Faliang Zhang, Guangyu Liu, Yang Guangxi Key Lab of Human-machine Interaction and Intelligent Decision Nanning Normal University Nanning China Zhidayuan AI Lab. Nanning China College of Mathematics and Informatics South China Agricultural University Guangzhou China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

Person image synthesis with controllable body poses and appearances is an essential task owing to the practical needs in the context of virtual try-on, image editing and video production. However, existing methods face significant challenges with details missing, limbs distortion and the garment style deviation. To address these issues, we propose a Disentangled Representations Diffusion Model (DRDM) to generate photo-realistic images from source portraits in specific desired poses and appearances. First, a pose encoder is responsible for encoding pose features into a high-dimensional space to guide the generation of person images. Second, a body-part subspace decoupling block (BSDB) disentangles features from the different body parts of a source figure and feeds them to the various layers of the noise prediction block, thereby supplying the network with rich disentangled features for generating a realistic target image. Moreover, during inference, we develop a parsing map-based disentangled classifier-free guided sampling method, which amplifies the conditional signals of texture and pose. Extensive experimental results on the Deepfashion dataset demonstrate the effectiveness of our approach in achieving pose transfer and appearance control. Copyright © 2024, The Authors. All rights reserved.

关键词： Signal encoding

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：