检索结果-内蒙古大学图书馆

31st International Conference on Computational Linguistics, COLING 2025

作者： Fan, Rui Li, Shu He, Tingting Liu, Yu Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning China National Language Resources Monitor Research Center for Network Media China Faculty of Artificial Intelligence in Education China School of Computer Central China Normal University Wuhan China

ISBN: (纸本)9798891761964

Despite the impressive capabilities of large language models (LLMs) in aspect-based sentiment analysis (ABSA), the role of syntactic information remains underexplored in LLMs. Syntactic structures are known to be crucial for capturing aspect-opinion relationships. To explore whether LLMs can effectively leverage syntactic information to improve ABSA performance, we propose a novel multi-step reasoning framework, the Syntax-Opinion-Sentiment Reasoning Chain (Syn-Chain). Syn-Chain sequentially analyzes syntactic dependencies, extracts opinions, and classifies sentiment. We introduce Syn-Chain into LLMs via zero-shot prompting, and results show that Syn-Chain significantly enhances ABSA performance, though smaller LLMs exhibit weaker performance. Furthermore, we enhance smaller LLMs via distillation using GPT-3.5-generated Syn-Chain responses, achieving state-of-the-art ABSA performance. Our findings highlight the importance of syntactic information for improving LLMs in ABSA and offer valuable insights for future research. © 2025 Association for Computational Linguistics.

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Boundary-Guided Global-Local feature fusion Network for polyp segmentation

引用

IEEE Transactions on Instrumentation and Measurement 2025年

作者： Liu, Guoqi Yao, Sheng Zhou, Yanan Liu, Dong Chang, Baofang Henan Normal University College of Computer and Information Engineering Henan Xinxiang453000 China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Henan Xinxiang453000 China

Colon polyp segmentation can assist physicians in screening colonoscopy images, which is crucial in preventing colorectal cancer. Due to the limited area occupied by small object polyp objects within images, there is a high risk of overlooking them. That makes it one of the more challenging aspects to address. Additionally, the current segmentation of small object polyps also faces difficulties such as boundary blurring, diverse lesion shapes, and uneven image brightness. While deep learning methods based on convolutional neural networks(CNNs) have been successfully applied to polyp segmentation tasks, three significant challenges persist: (1) limited ability to extract boundary information, (2) inadequate robustness capture of global context information, and (3) insufficient ability for integrating global and local information. To address the issues mentioned above, we propose the Boundary-Guided Global-Local feature fusion network for small polyp segmentation(BGGL-Net), with the following contributions: (1) The local information encoder and boundary feature extraction module leverage convolutional blocks and Laplacian operators to mine feature boundaries and fine-grained detail features. (2) We design a global information fusion module to enhance the model's representational capacity and acquire rich and accurate global information. (3) Boundary-guided module using a cross-attention mechanism, capturing the inherent relationship between the feature and establishes long-range dependencies between global and low-level features. We enhance boundary accuracy by employing local boundary features to guide the global features, facilitating the effective fusion of global and local information. In the experiment, we compared ten state-of-the-art(SOTA) networks with BGGL-Net. The BGGL-Net achieves the highest segmentation accuracy on small object polyp datasets. Concerning generalization performance, the BGGL-Net outperforms CaraNet by up to 12.4% in the mDice metric on the

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Novel Anti-rounding Image Steganography Method for Improved UNet++ 7th

A Novel Anti-rounding Image Steganography Method for Improv...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision, PRCV 2024

作者： Duan, Xintao Zhang, Meng Bai, Luwei Xu, Kaiou Bao, Mengru Wu, Yinhang Qin, Chuan College of Computer and Information Engineering Henan Normal University Henan Xinxiang453007 China Key Laboratory Foundation of Artificial Intelligence and Personalized Learning in Education of Henan Province Henan Normal University Henan Xinxiang453007 China School of Optical-Electrical and Computer Engineering University of Shanghai for Science and Technology Shanghai200093 China

ISBN: (纸本)9789819786916

Deep hiding involves embedding a secret image within a cover image so that the secret becomes imperceptible to ensure the security of steganography. However, in practical applications, accuracy loss is due to data conversion during encoding and decoding. The encoder generates the tensor matrix during training, while the practical application corresponds to the image preservation extraction process;the error caused by the rounding operation in this process will affect the accuracy of the secret information extraction during decoding. Aiming at the currently existing methods ignoring the rounding error problem, this paper proposes a novel anti-rounding image steganography method for improved UNet++. We design an anti-rounding function (ARF) to simulate the real steganographic environment, training the model to overcome the non-differentiable rounding distortion problem. When rounding error is considered, the accuracy of the extracted image decreases. To ensure the image quality in real application scenarios, in this paper, we use the improved UNet++ to ensure the quality of steganographic images by cascading convolution and ECA attention mechanisms and propose the Multiscale Mixing Module (MSMM) for feature fusion. In the extraction stage, the corresponding cover image is selected through a shared cover image library, followed by processing the stego image to obtain a different image before feeding it to the extraction network to guarantee the steganography process’s safety. The experiment results indicate the method’s capability to enhance the imperceptibility of steganography significantly, and the steganography process has better security. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

A Knowledge Acquisition Method for Consumer Electronics Based on Triadic Hesitant Fuzzy Concept

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Xin, Xianwei Zhao, Ye Wang, Chenyang Xu, Jiucheng Taleb, Tarik Henan Normal University School of Computer and Information Engineering Xinxiang453007 China Key Laboratory of Computational Intelligence and Chinese Information Processing Ministry of Education Taiyuan237016 China Computer and Software Engineering School of College of Shenzhen University Guangdong Shenzhen518060 China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Henan Province 453007 China Ruhr University Bochum Faculty of Electrical Engineering and Information Technology Bochum44801 Germany

With the growing intelligence and personalization of consumer electronic products, extracting effective information has become a key challenge in Consumer Electronics (CE). Triadic Concept Analysis (TCA), an important extension of Formal Concept Analysis (FCA), is widely applied but often struggles to handle the hesitant fuzzy characteristics in real-world data. To address this gap, we propose a Triadic Hesitant Fuzzy Concept (THFC) model. First, we introduce the concept of a triadic hesitant fuzzy background, integrating the fuzzy and hesitant nature of data in the CE environment. We propose a knowledge acquisition method based on THFC, which constructs a multi-granularity knowledge space with a dynamic adjustment mechanism. This method captures subtle distinctions between different types of information and their hierarchical structures in the context of CE, offering significant support for knowledge discovery and decision-making in complex environments. Building on this, we design a variable-precision hybrid similarity measurement (VP-HSM) method to extract core, adjunct, and edge concepts, thus providing more precise and structured knowledge for data analysis and decision-making in CE. Experimental results on publicly available datasets show that the proposed method significantly improves classification accuracy and stability, effectively handling hesitant fuzzy data and improving the accuracy of concept extraction. © 1975-2011 IEEE.

关键词： Data accuracy

来源：评论

学校读者我要写书评

暂无评论

AdptDilatedGCN: Protein-ligand binding affinity prediction based on multi-scale interaction fusion mechanism and dilated GCN

引用

International Journal of Biological Macromolecules 2025年 311卷 143751页

作者： Wang, Wei Ma, Linchong Liu, Dong Zhang, Hongjun Wu, Guangsheng Zhou, Yun College of Computer and Information Engineering Henan Normal University Xinxiang453000 China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang453000 China Hebi Instiute of Engineering and Technology Henan Polytechnic University Hebi458030 China School of Mathematics and Computer Science Xinyu University Xinyu338004 China

Predicting protein-ligand binding affinity is crucial for drug discovery. However, existing prediction methods often make insufficient use of the features of proteins and ligands, lack interactions between different information, and have difficulty in capturing and integrating both fine- and coarse-grained information of proteins and ligands at the same time. Therefore, we propose a deep learning method called AdptDilatedGCN, which fully interacts with protein and ligand features through multi-scale interaction and fusion mechanism, mining potential fine-grained and coarsely grained information and fusing it, combining skip connections and multi-scale fusion strategy to improve feature utilization and enhance features. In the model, dilated Graph Convolutional Network(GCN) combines multi-head attention mechanism and dilated convolution to overcome the limitations of traditional GCN, while taking into account the interactions between amino acid nodes in the protein graph. In addition, an adaptive Gated Recurrent Unit(GRU) is designed to dynamically enhance the model's ability to integrate multi-source information in adaptive GCN. The Vina weights obtained from AutoDock Vina are used to supplement and further enhance the features learned from GCN. Finally, The model achieves Pearson correlation coefficients of 0.837 and 0.803 on the CASF-2016 and CASF-2013 public test sets, respectively. © 2025 Elsevier B.V.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

ResaPred: A Deep Residual Network With Self-Attention to Predict Protein Flexibility

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第1期22卷 216-227页

作者： Wei Wang Shitong Wan Hu Jin Dong Liu Hongjun Zhang Yun Zhou Xianfang Wang College of computer and Information Engineering Henan Normal University Xinxiang China Key Laboratory of Artificial Intelligence and Personalized Learning in Education of Henan Province Xinxiang China School of Electrical Engineering Hanyang University Ansan South Korea School of Computer Science and Technology Anyang University Anyang China College of Computer Science and Technology Engineering Henan Institute of Technology Xinxiang China

Grasping the intrinsic properties of protein structure is crucial for comprehending relevant biological mechanisms, with protein flexibility standing out as a critical aspect. Therefore, the prediction of protein flexibility is of great importance in understanding molecular mechanisms. We propose a deep learning method named ResaPred, which extracts diverse features from protein sequences, such as secondary structure, torsion angle, solvent accessibility, etc. ResaPred is a novel deep network based on a modified 1D residual module and a self-attention mechanism, which effectively extracts deep key features related to flexibility. The modified 1D residual module consists of three convolution layers, with batchnorm and relu layers added after each layer to prevent gradient explosion or vanishing. Incorporating self-attention mechanisms into neural network architectures introduces a significant advantage in capturing long-range dependencies within sequential data. We conduct experiments on the non-strict and strict cases, and achieve state-of-the-art results in predicting flexibility compared to existing methods. Furthermore, we extended our analysis to explore the correlation between protein secondary structure and solvent accessibility with flexibility. Finally, we used two important viral proteins as case studies, confirming the effectiveness of our method in recognizing the flexibility of protein structures.

关键词： Proteins Feature extraction Amino acids Protein sequence Neural networks Accuracy Training Solvents Shape Computational biology

来源：评论

学校读者我要写书评

暂无评论

Asymmetric Visual Semantic Embedding Framework for Efficient Vision-Language Alignment

arXiv

引用

arXiv 2025年

作者： Liu, Yang Liu, Mengyuan Huang, Shudong Lv, Jiancheng College of Computer Science Sichuan University Chengdu610065 China Engineering Research Center of Machine Learning and Industry Intelligence Ministry of Education Chengdu China State Key Laboratory of General Artificial Intelligence Peking University Shenzhen Graduate School Shenzhen China

learning visual semantic similarity is a critical challenge in bridging the gap between images and texts. However, there exist inherent variations between vision and language data, such as information density, i.e., images can contain textual information from multiple different views, which makes it difficult to compute the similarity between these two modalities accurately and efficiently. In this paper, we propose a novel framework called Asymmetric Visual Semantic Embedding (AVSE) to dynamically select features from various regions of images tailored to different textual inputs for similarity calculation. To capture information from different views in the image, we design a radial bias sampling module to sample image patches and obtain image features from various views, Furthermore, AVSE introduces a novel module for efficient computation of visual semantic similarity between asymmetric image and text embeddings. Central to this module is the presumption of foundational semantic units within the embeddings, denoted as "meta-semantic embeddings." It segments all embeddings into meta-semantic embeddings with the same dimension and calculates visual semantic similarity by finding the optimal match of meta-semantic embeddings of two modalities. Our proposed AVSE model is extensively evaluated on the large-scale MS-COCO and Flickr30K datasets, demonstrating its superiority over recent state-of-the-art methods. Copyright © 2025, The Authors. All rights reserved.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

A Diversity-Enhanced Knowledge Distillation Model for Practical Math Word Problem Solving

arXiv

引用

arXiv 2025年

作者： Zhang, Yi Zhou, Guangyou Xie, Zhiwen Ma, Jinjin Huang, Jimmy Xiangji Faculty of Artificial Intelligence in Education Central China Normal University Hubei Wuhan430079 China School of Information and Safety Engineering Zhongnan University of Economics and Law Hubei Wuhan430073 China Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning School of Computer Central China Normal University Hubei Wuhan430079 China Information Retrieval and Knowledge Management Research Lab York University Toronto Canada

Math Word Problem (MWP) solving is a critical task in natural language processing, has garnered significant research interest in recent years. Various recent studies heavily rely on Seq2Seq models and their extensions (e.g., Seq2Tree and Graph2Tree) to generate mathematical equations. While effective, these models struggle to generate diverse but counterpart solution equations, limiting their generalization across various math problem scenarios. In this paper, we introduce a novel Diversity-enhanced Knowledge Distillation (DivKD) model for practical MWP solving. Our approach proposes an adaptive diversity distillation method, in which a student model learns diverse equations by selectively transferring high-quality knowledge from a teacher model. Additionally, we design a diversity prior-enhanced student model to better capture the diversity distribution of equations by incorporating a conditional variational auto-encoder. Extensive experiments on four MWP benchmark datasets demonstrate that our approach achieves higher answer accuracy than strong baselines while maintaining high efficiency for practical applications. Copyright © 2025, The Authors. All rights reserved.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Decoupled Doubly Contrastive learning for Cross Domain Facial Action Unit Detection

arXiv

引用

arXiv 2025年

作者： Li, Yong Liu, Menglin Cui, Zhen Ding, Yi Zong, Yuan Zheng, Wenming Shan, Shiguang Guan, Cuntai School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Artificial Intelligence Beijing Normal University Beijing100875 China Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Key Laboratory of Child Development and Learning Science of Ministry of Education School of Biological Science and Medical Engineering Nanjing210096 China

Despite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods are under-explored. In response to this challenge, we propose a decoupled doubly contrastive adaptation (D2CA) approach to learn a purified AU representation that is semantically aligned for the source and target domains. Specifically, we decompose latent representations into AU-relevant and AU-irrelevant components, with the objective of exclusively facilitating adaptation within the AU-relevant subspace. To achieve the feature decoupling, D2CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified. To further strengthen feature decoupling, particularly in scenarios with limited AU data diversity, D2CA employs a doubly contrastive learning mechanism comprising image and feature-level contrastive learning to ensure the quality of synthesized faces and mitigate feature ambiguities. This new framework leads to an automatically learned, dedicated separation of AU-relevant and domain-relevant factors, and it enables intuitive, scale-specific control of the cross-domain facial image synthesis. Extensive experiments demonstrate the efficacy of D2CA in successfully decoupling AU and domain factors, yielding visually pleasing cross-domain synthesized facial images. Meanwhile, D2CA consistently outperforms state-of-the-art cross-domain AU detection approaches, achieving an average F1 score improvement of 6%-14% across various cross-domain scenarios. © 2025, CC BY-NC-SA.

关键词： Contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Construction and Implementation of artificial intelligence Classroom Teaching Model Based on the AI Open Platform 5th

Construction and Implementation of Artificial Intelligence C...

引用

5th International Conference on Computer Science and educational Informatization, CSEI 2023

作者： Wang, Yi Zhang, Congpin Gong, Xin Ye, Siqi Computer and Information Engineering Henan Normal University Xinxiang China Key Laboratory of Artificial Intelligence and Personalized Learning in Education Xinxiang China

ISBN: (纸本)9789819994915

With the development of the intelligent era, artificial intelligence education is gradually carried out in primary and secondary schools in order to cultivate artificial intelligence talents. To address the current problem of insufficient artificial intelligence classroom experience, the article constructs an artificial intelligence classroom teaching model based on David Cooper's experiential learning theory, combined with the AI open platform, and carries out practical classroom teaching activities in primary school F based on the teaching model. After the implementation of the course, the students made an evaluation and analysed the data to find out the effect of the course implementation, thus verifying the feasibility and effectiveness of the teaching model, with a view to providing teachers with new ideas to solve the problem of artificial intelligence classroom teaching. The practical experience shows that the teaching is effective. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： artificial intelligence

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：