Query：
学者姓名：陈羽中
Refining：
Year
Type
Indexed by
Source
Complex
Co-
Language
Clean All
Abstract ：
Aspect-level multimodal sentiment analysis aims to ascertain the sentiment polarity of a given aspect from a text review and its accompanying image. Despite substantial progress made by existing research, aspect-level multimodal sentiment analysis still faces several challenges: (1) Inconsistency in feature granularity between the text and image modalities poses difficulties in capturing corresponding visual representations of aspect words. This inconsistency may introduce irrelevant or redundant information, thereby causing noise and interference in sentiment analysis. (2) Traditional aspect-level sentiment analysis predominantly relies on the fusion of semantic and syntactic information to determine the sentiment polarity of a given aspect. However, introducing image modality necessitates addressing the semantic gap in jointly understanding sentiment features in different modalities. To address these challenges, a multi-granularity visual-textual feature fusion model (MG-VTFM) is proposed to enable deep sentiment interactions among semantic, syntactic, and image information. First, the model introduces a multi-granularity hierarchical graph attention network that controls the granularity of semantic units interacting with images through constituent tree. This network extracts image sentiment information relevant to the specific granularity, reduces noise from images and ensures sentiment relevance in single-granularity cross-modal interactions. Building upon this, a multilayered graph attention module is employed to accomplish multi-granularity sentiment fusion, ranging from fine to coarse. Furthermore, a progressive multimodal attention fusion mechanism is introduced to maximize the extraction of abstract sentiment information from images. Lastly, a mapping mechanism is proposed to align cross-modal information based on aspect words, unifying semantic spaces across different modalities. Our model demonstrates excellent overall performance on two datasets.
Keyword ：
Aspect-level sentiment analysis Aspect-level sentiment analysis Constituent tree Constituent tree Multi-granularity Multi-granularity Multimodal data Multimodal data Visual-textual feature fusion Visual-textual feature fusion
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Chen, Yuzhong , Shi, Liyuan , Lin, Jiali et al. Multi-granularity visual-textual jointly modeling for aspect-level multimodal sentiment analysis [J]. | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (1) . |
| MLA | Chen, Yuzhong et al. "Multi-granularity visual-textual jointly modeling for aspect-level multimodal sentiment analysis" . | JOURNAL OF SUPERCOMPUTING 81 . 1 (2025) . |
| APA | Chen, Yuzhong , Shi, Liyuan , Lin, Jiali , Chen, Jingtian , Zhong, Jiayuan , Dong, Chen . Multi-granularity visual-textual jointly modeling for aspect-level multimodal sentiment analysis . | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (1) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The objective of dialogue state tracking (DST) is to dynamically track information within dialogue states by populating predefined state slots, which enhances the comprehension capabilities of task-oriented dialogue systems in processing user requests. Recently, there has been a growing popularity in using graph neural networks to model the relationships between slots and slots as well as between dialogue and slots. However, these models overlook the relationships between words and phrases in the current turn dialogue and dialogue history. Specific syntactic dependencies (e.g., the object of a preposition) and constituents (e.g., noun phrases) have a higher probability of being the slot values that need to be retrieved at current moment. Neglecting these syntactic dependency and constituent information may cause the loss of potential candidate slot values, thereby limiting the overall performance of DST models. To address this issue, we propose a Hierarchical Fine-grained State Aware Graph Attention Network for Dialogue State Tracking (HFSG-DST). HFSG-DST exploits the syntactic dependency and constituent tree information, such as phrase segmentation and hierarchical structure in dialogue utterances, to construct a relational graph between entities. It then employs a hierarchical graph attention network to facilitate the extraction of fine-grained candidate dialogue state information. Additionally, HFSG-DST designs a Schema-enhanced Dialogue History Selector to select the most relevant turn of dialogue history for current turn and incorporates schema description information for dialogue state tracking. Consequently, HFSG-DST is capable of constructing the dependency tree and constituent tree on noise-free utterances. Experimental results on two public benchmark datasets demonstrate that HFSG-DST outperforms other state-of-the-art models.
Keyword ：
Dialogue state tracking Dialogue state tracking Hierarchical graph attention network Hierarchical graph attention network Schema enhancement Schema enhancement Syntactic information Syntactic information
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liao, Hongmiao , Chen, Yuzhong , Chen, Deming et al. Hierarchical fine-grained state-aware graph attention network for dialogue state tracking [J]. | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (5) . |
| MLA | Liao, Hongmiao et al. "Hierarchical fine-grained state-aware graph attention network for dialogue state tracking" . | JOURNAL OF SUPERCOMPUTING 81 . 5 (2025) . |
| APA | Liao, Hongmiao , Chen, Yuzhong , Chen, Deming , Xu, Junjie , Zhong, Jiayuan , Dong, Chen . Hierarchical fine-grained state-aware graph attention network for dialogue state tracking . | JOURNAL OF SUPERCOMPUTING , 2025 , 81 (5) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Camouflaged object detection (COD) aims to resolve the tough issue of accurately segmenting objects hidden in the surroundings. However, the existing methods suffer from two major problems: the incomplete interior and the inaccurate boundary of the object. To address these difficulties, we propose a three-stage skeletonboundary-guided network (SBGNet) for the COD task. Specifically, we design a novel skeleton-boundary label to be complementary to the typical pixel-wise mask annotation, emphasizing the interior skeleton and the boundary of the camouflaged object. Furthermore, the proposed feature guidance module (FGM) leverages the skeleton-boundary feature to guide the model to focus on both the interior and the boundary of the camouflaged object. Besides, we design a bidirectional feature flow path with the information interaction module (IIM) to propagate and integrate the semantic and texture information. Finally, we propose the dual feature distillation module (DFDM) to progressively refine the segmentation results in a fine-grained manner. Comprehensive experiments demonstrate that our SBGNet outperforms 20 state-of-the-art methods on three benchmarks in both qualitative and quantitative comparisons. CCS Concepts: center dot Computing methodologies -> Scene understanding;
Keyword ：
Bidirectional feature flow path Bidirectional feature flow path Camouflaged object detection Camouflaged object detection Feature distillation Feature distillation Skeleton-boundary guidance Skeleton-boundary guidance
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Niu, Yuzhen , Xu, Yeyuan , Li, Yuezhou et al. Skeleton-Boundary-Guided Network for Camouflaged Object Detection [J]. | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2025 , 21 (3) . |
| MLA | Niu, Yuzhen et al. "Skeleton-Boundary-Guided Network for Camouflaged Object Detection" . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS 21 . 3 (2025) . |
| APA | Niu, Yuzhen , Xu, Yeyuan , Li, Yuezhou , Zhang, Jiabang , Chen., Yuzhong . Skeleton-Boundary-Guided Network for Camouflaged Object Detection . | ACM TRANSACTIONS ON MULTIMEDIA COMPUTING COMMUNICATIONS AND APPLICATIONS , 2025 , 21 (3) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
应用人工智能技术对高速公路路网道路状态进行监测已成为热点,然而,数据孤岛及隐私保护是高速路网智能决策面临的挑战.为实现分布式数据安全共享及智能决策,以拥堵问题为例,提出基于联邦学习的高速路网道路拥堵状态监测策略.利用摄像头实时数据,在密态可计算的同态加密联邦学习智能决策架构下,建立基于道路区间优化的拥堵状态监测模型.结果表明,在确保分布式数据安全共享的前提下,能够有效实现高速路网道路拥堵状态监测.
Keyword ：
同态加密 同态加密 数据安全共享 数据安全共享 智能决策 智能决策 联邦学习 联邦学习 道路拥堵状态 道路拥堵状态 高速公路路网 高速公路路网
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 李林锋 , 陈羽中 , 姚毅楠 et al. 面向分布式数据安全共享的高速公路路网拥堵监测 [J]. | 福建师范大学学报（自然科学版） , 2025 , 41 (1) : 11-20 . |
| MLA | 李林锋 et al. "面向分布式数据安全共享的高速公路路网拥堵监测" . | 福建师范大学学报（自然科学版） 41 . 1 (2025) : 11-20 . |
| APA | 李林锋 , 陈羽中 , 姚毅楠 , 邵伟杰 . 面向分布式数据安全共享的高速公路路网拥堵监测 . | 福建师范大学学报（自然科学版） , 2025 , 41 (1) , 11-20 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Low-light image enhancement (LLIE) is a challenging task, due to the multiple degradation problems involved, such as low brightness, color distortion, heavy noise, and detail degradation. Existing deep learning-based LLIE methods mainly use encoder-decoder networks or full-resolution networks, which excel at extracting context or detail information, respectively. Since detail and context information are both required for LLIE, existing methods cannot solve all the degradation problems. To solve the above problem, we propose an LLIE method based on collaboratively enhanced and integrated detail-context information (CoEIDC). Specifically, we propose a full-resolution network with two collaborative subnetworks, namely the detail extraction and enhancement subnetwork (DE2-Net) and context extraction and enhancement subnetwork (CE2-Net). CE2-Net extracts context information from the features of DE2-Net at different stages through large receptive field convolutions. Moreover, a collaborative attention module (CAM) and a detail-context integration module are proposed to enhance and integrate detail and context information. CAM is reused to enhance the detail features from multi-receptive fields and the context features from multiple stages. Extensive experimental results demonstrate that our method outperforms the state-of-the-art LLIE methods, and is applicable to other image enhancement tasks, such as underwater image enhancement.
Keyword ：
Collaborative enhancement and integration Collaborative enhancement and integration Color/brightness correction Color/brightness correction Detail reconstruction Detail reconstruction Low-light image enhancement Low-light image enhancement
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Niu, Yuzhen , Lin, Xiaofeng , Xu, Huangbiao et al. Collaboratively enhanced and integrated detail-context information for low enhancement [J]. | PATTERN RECOGNITION , 2025 , 162 . |
| MLA | Niu, Yuzhen et al. "Collaboratively enhanced and integrated detail-context information for low enhancement" . | PATTERN RECOGNITION 162 (2025) . |
| APA | Niu, Yuzhen , Lin, Xiaofeng , Xu, Huangbiao , Xu, Rui , Chen, Yuzhong . Collaboratively enhanced and integrated detail-context information for low enhancement . | PATTERN RECOGNITION , 2025 , 162 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Math word problem (MWP) represents a critical research area within reading comprehension, where accurate comprehension of math problem text is crucial for generating math expressions. However, current approaches still grapple with unresolved challenges in grasping the sensitivity of math problem text and delineating distinct roles across various clause types, and enhancing numerical representation. To address these challenges, this paper proposes a Numerical Magnitude Aware Multi-Channel Hierarchical Encoding Network (NMA-MHEA) for math expression generation. Firstly, NMA-MHEA implements a multi-channel hierarchical context encoding module to learn context representations at three different channels: intra-clause channel, inter-clause channel, and context-question interaction channel. NMA-MHEA constructs hierarchical constituent-dependency graphs for different levels of sentences and employs a Hierarchical Graph Attention Neural Network (HGAT) to learn syntactic and semantic information within these graphs at the intra-clause and inter-clause channels. NMA-MHEA then refines context clauses using question information at the context-question interaction channel. Secondly, NMA-MHEA designs a number encoding module to enhance the relative magnitude information among numerical values and type information of numerical values. Experimental results on two public benchmark datasets demonstrate that NMA-MHEA outperforms other state-of-the-art models. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.
Keyword ：
Benchmarking Benchmarking Encoding (symbols) Encoding (symbols) Graph algorithms Graph algorithms Graphic methods Graphic methods Graph neural networks Graph neural networks Network coding Network coding Network theory (graphs) Network theory (graphs) Semantics Semantics Syntactics Syntactics Word processing Word processing
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Xu, Junjie , Chen, Yuzhong , Xiao, Lingsheng et al. A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving [J]. | Neural Computing and Applications , 2025 , 37 (3) : 1651-1672 . |
| MLA | Xu, Junjie et al. "A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving" . | Neural Computing and Applications 37 . 3 (2025) : 1651-1672 . |
| APA | Xu, Junjie , Chen, Yuzhong , Xiao, Lingsheng , Liao, Hongmiao , Zhong, Jiayuan , Dong, Chen . A numerical magnitude aware multi-channel hierarchical encoding network for math word problem solving . | Neural Computing and Applications , 2025 , 37 (3) , 1651-1672 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Click-through rate (CTR) prediction aims to estimate the probability of a user clicking on a particular item, making it one of the core tasks in various recommendation platforms. In such systems, user behavior data are crucial for capturing user interests, which has garnered significant attention from both academia and industry, leading to the development of various user behavior modeling methods. However, existing models still face unresolved issues, as they fail to capture the complex diversity of user interests at the semantic level, refine user interests effectively, and uncover users’ potential interests. To address these challenges, we propose a novel model called knowledge-enhanced Interest segment division attention network (KISDAN), which can effectively and comprehensively model user interests. Specifically, to leverage the semantic information within user behavior sequences, we employ the structure of a knowledge graph to divide user behavior sequence into multiple interest segments. To provide a comprehensive representation of user interests, we further categorize user interests into strong and weak interests. By leveraging both the knowledge graph and the item co-occurrence graph, we explore users’ potential interests from two perspectives. This methodology allows KISDAN to better understand the diversity of user interests. Finally, we extensively evaluate KISDAN on three benchmark datasets, and the experimental results consistently demonstrate that the KISDAN model outperforms state-of-the-art models across various evaluation metrics, which validates the effectiveness and superiority of KISDAN. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2024.
Keyword ：
Contrastive Learning Contrastive Learning Knowledge graph Knowledge graph Prediction models Prediction models Semantic Segmentation Semantic Segmentation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Zhanghui , Chen, Shijie , Chen, Yuzhong et al. A knowledge-enhanced interest segment division attention network for click-through rate prediction [J]. | Neural Computing and Applications , 2024 , 36 (34) : 21817-21837 . |
| MLA | Liu, Zhanghui et al. "A knowledge-enhanced interest segment division attention network for click-through rate prediction" . | Neural Computing and Applications 36 . 34 (2024) : 21817-21837 . |
| APA | Liu, Zhanghui , Chen, Shijie , Chen, Yuzhong , Su, Jieyang , Zhong, Jiayuan , Dong, Chen . A knowledge-enhanced interest segment division attention network for click-through rate prediction . | Neural Computing and Applications , 2024 , 36 (34) , 21817-21837 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
与从现实场景中拍摄的自然图像不同，屏幕内容图像是一种合成图像，通常由计算机生成的文本、图形和动画等各种多媒体形式组合而成. 现有评估方法通常未能充分考虑图像边缘结构信息和全局上下文信息对屏幕内容图像质量感知的影响. 为解决上述问题，本文提出一种基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估模型. 首先，使用高斯拉普拉斯算子构造由失真屏幕内容图像高频信息组成的边缘结构图，然后通过卷积神经网络对输入的失真屏幕内容图像和相应的边缘结构图进行多尺度的特征提取与融合，以图像的边缘结构信息为模型训练提供额外的信息增益. 此外，本文进一步构建了基于Transformer的多尺度特征编码模块，从而在CNN获得的局部特征基础上更好地建模不同尺度图像和边缘特征的全局上下文信息. 实验结果表明，本文提出的方法在指标上优于其他现有的无参考和全参考屏幕内容图像质量评估方法，能够取得更高的主客观视觉感知一致性.
Keyword ：
Transformer Transformer 卷积神经网络 卷积神经网络 多尺度特征 多尺度特征 无参考屏幕内容图像质量评估 无参考屏幕内容图像质量评估 高斯拉普拉斯算子 高斯拉普拉斯算子
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈羽中 , 陈友昆 , 林闽沪 et al. 基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估 [J]. | 电子学报 , 2024 . |
| MLA | 陈羽中 et al. "基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估" . | 电子学报 (2024) . |
| APA | 陈羽中 , 陈友昆 , 林闽沪 , 牛玉贞 . 基于边缘辅助和多尺度Transformer的无参考屏幕内容图像质量评估 . | 电子学报 , 2024 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
检索式多轮对话是多轮对话中一个重要的分支,如何从众多的候选回复中选择出最适合当前上下文的答复是检索式多轮对话的关键问题.近年来,深度神经网络模型在多轮回复选择问题上取得了较大进展.然而,现有模型依然存在对上下文语义理解不准确,缺乏对上下文内部、话语内部蕴含的时序语义关系的学习等问题.针对上述问题,本文提出了一种基于预训练语言模型的多辅助任务优化的学习方法MSE-BERT.首先,通过区间掩码生成任务优化预训练模型,使其更好地适应当前领域的数据集.提出一种辅助任务是token乱序插入任务,该任务通过随机选择上下文中的一句话语并将其内部的token进行随机打乱,然后预测这句话在上下文中原本的位置,多粒度的学习蕴含在上下文之间的时序语义关系.最后,利用BERT特有的位置嵌入和深层注意力机制,提出了一种双向特征融合机制,将所有的局部信息进行融合,进一步优化模型进行回复选择的能力.在Ubuntu和E-commerce数据集上的实验结果表明,MSE-BERT模型的总体性能优于对比模型.
Keyword ：
双向特征融合 双向特征融合 回复选择 回复选择 多轮对话 多轮对话 语义关系 语义关系 辅助任务 辅助任务
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 刘律民 , 陈羽中 , 陈敬添 . 领域数据增强与多粒度语义理解的多轮对话模型 [J]. | 小型微型计算机系统 , 2024 , 45 (7) : 1585-1591 . |
| MLA | 刘律民 et al. "领域数据增强与多粒度语义理解的多轮对话模型" . | 小型微型计算机系统 45 . 7 (2024) : 1585-1591 . |
| APA | 刘律民 , 陈羽中 , 陈敬添 . 领域数据增强与多粒度语义理解的多轮对话模型 . | 小型微型计算机系统 , 2024 , 45 (7) , 1585-1591 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The recommendation system aims to recommend items to users by capturing their personalized interests. Traditional recommendation systems typically focus on modeling target behaviors between users and items. However, in practical application scenarios, various types of behaviors (e.g., click, favorite, purchase, etc.) occur between users and items. Despite recent efforts in modeling various behavior types, multi-behavior recommendation still faces two significant challenges. The first challenge is how to comprehensively capture the complex relationships between various types of behaviors, including their interest differences and interest commonalities. The second challenge is how to solve the sparsity of target behaviors while ensuring the authenticity of information from various types of behaviors. To address these issues, a multi-behavior recommendation framework based on Multi-View Multi-Behavior Interest Learning Network and Contrastive Learning (MMNCL) is proposed. This framework includes a multi-view multi-behavior interest learning module that consists of two submodules: the behavior difference aware submodule, which captures intra-behavior interests for each behavior type and the correlations between various types of behaviors, and the behavior commonality aware submodule, which captures the information of interest commonalities between various types of behaviors. Additionally, a multi-view contrastive learning module is proposed to conduct node self- discrimination, ensuring the authenticity of information integration among various types of behaviors, and facilitating an effective fusion of interest differences and interest commonalities. Experimental results on three real-world benchmark datasets demonstrate the effectiveness of MMNCL and its advantages over other state-of-the-art recommendation models. Our code is available at https://github.com/sujieyang/MMNCL.
Keyword ：
Contrastive learning Contrastive learning Interest learning network Interest learning network Meta learning Meta learning Multi-behavior recommendation Multi-behavior recommendation
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Su, Jieyang , Chen, Yuzhong , Lin, Xiuqiang et al. Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation [J]. | KNOWLEDGE-BASED SYSTEMS , 2024 , 305 . |
| MLA | Su, Jieyang et al. "Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation" . | KNOWLEDGE-BASED SYSTEMS 305 (2024) . |
| APA | Su, Jieyang , Chen, Yuzhong , Lin, Xiuqiang , Zhong, Jiayuan , Dong, Chen . Multi-view multi-behavior interest learning network and contrastive learning for multi-behavior recommendation . | KNOWLEDGE-BASED SYSTEMS , 2024 , 305 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
