检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Yang, Jinxia Su, Bing Zhao, Wayne Xin Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China School of Information Renmin University of China China

Medical vision-language pre-training methods mainly leverage the correspondence between paired medical images and radiological reports. Although multi-view spatial images and temporal sequences of image-report pairs are available in off-the-shelf multi-modal medical datasets, most existing methods have not thoroughly tapped into such extensive supervision signals. In this paper, we introduce the Med-ST framework for fine-grained spatial and temporal modeling to exploit information from multiple spatial views of chest radiographs and temporal historical records. For spatial modeling, Med-ST employs the Mixture of View Expert (MoVE) architecture to integrate different visual features from both frontal and lateral views. To achieve a more comprehensive alignment, Med-ST not only establishes the global alignment between whole images and texts but also introduces modality-weighted local alignment between text tokens and spatial regions of images. For temporal modeling, we propose a novel cross-modal bidirectional cycle consistency objective by forward mapping classification (FMC) and reverse mapping regression (RMR). By perceiving temporal information from simple to complex, Med-ST can learn temporal semantics. Experimental results across four distinct tasks demonstrate the effectiveness of Med-ST, especially in temporal classification tasks. Our code and model are available at https://***/SVT-Yang/MedST. Copyright 2024 by the author(s)

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

A Multi-Stream Structure-Enhanced Network for Mesh Denoising

引用

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

作者： Yang, Yutian Liang, Lingyu Yan, Jie Xu, Yong South China University of Technology Guangzhou510641 China Henan Key Laboratory of Chronic Disease Prevention and Therapy & Intelligent Health Management Henan China Guangdong Provincial Key Laboratory of Multimodal Big Data Intelligent Analysis 510641 China

ISBN: (纸本)9781665410205

Triangular meshes provide an efficient representation of 3D shapes. Various applications such as 3D simulation suffer from degradation in geometric quality. This paper proposes a novel Multi-stream Structure-Enhanced Network (MSE-Net) based on graph convolutional networks. The network uses multi-scale features besides vertex position to guide face normal filtering, which can better preserve the geometric feature during the denoising process. In contrast to former methods that focus on filtering vertex coordinate and face normal apart, MSE-Net innovatively fuses more structure features like face area, inner product between face normal and vertex normals, and the interior angles of face to guide the face normal and vertex position updating, utilizing the inherent structural characteristic of Mesh. Our method achieves state-of-the-art performance on several publicly available datasets, demonstrating its effectiveness. © 2024 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

A Low-Rank Matching Attention Based Cross-Modal Feature Fusion Method for Conversational Emotion Recognition

引用

IEEE Transactions on Affective Computing 2024年第2期16卷 1177-1189页

作者： Shou, Yuntao Liu, Huan Cao, Xiangyong Meng, Deyu Dong, Bo Xi'An Jiaotong School of Computer Science and Technology Ministry of Education Key Laboratory for Intelligent Networks and Network Security Shaanxi Province Key Laboratory of Big Data Knowledge Engineering Shaanxi Xi'an710049 China Xi'An Jiaotong School of Computer Science and Technology Shaanxi Xi'an710049 China BigKEJoint Innovation Center SHMEEA Shanghai China Xi'An Jiaotong University School of Mathematics and Statistics Xi'an China

Conversational emotion recognition (CER) is an important research topic in human-computer interactions. Although recent advancements in transformer-based cross-modal fusion methods have shown promise in CER tasks, they tend to overlook the crucial intra-modal and inter-modal emotional interaction or suffer from high computational complexity. To address this, we introduce a novel and lightweight cross-modal feature fusion method called Low-Rank Matching Attention Method (LMAM). LMAM effectively captures contextual emotional semantic information in conversations while mitigating the quadratic complexity issue caused by the self-attention mechanism. Specifically, by setting a matching weight and calculating inter-modal features attention scores row by row, LMAM requires only one-third of the parameters of self-attention methods. We also employ the low-rank decomposition method on the weights to further reduce the number of parameters in LMAM. As a result, LMAM offers a lightweight model while avoiding overfitting problems caused by a large number of parameters. Moreover, LMAM is able to fully exploit the intra-modal emotional contextual information within each modality and integrates complementary emotional semantic information across modalities by computing and fusing similarities of intra-modal and inter-modal features simultaneously. Experimental results verify the superiority of LMAM compared with other popular cross-modal fusion methods on the premise of being more lightweight. Also, LMAM can be embedded into any existing state-of-the-art CER methods in a plug-and-play manner, and can be applied to other multi-modal recognition tasks, e.g., session recommendation and humour detection, demonstrating its remarkable generalization ability. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Uniform Attention Maps: Boosting Image Fidelity in Reconstruction and Editing

Uniform Attention Maps: Boosting Image Fidelity in Reconstru...

引用

2025 IEEE/CVF Winter Conference on Applications of Computer Vision, WACV 2025

作者： Mo, Wenyi Zhang, Tianyu Bai, Yalong Su, Bing Wen, Ji-Rong Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China Du Xiaoman Technology China

ISBN: (纸本)9798331510831

Text-guided image generation and editing using diffusion models have achieved remarkable advancements. Among these, tuning-free methods have gained attention for their ability to perform edits without extensive model adjustments, offering simplicity and efficiency. However, existing tuning-free approaches often struggle with balancing fidelity and editing precision. Reconstruction errors in DDIM Inversion are partly attributed to the cross-attention mechanism in U-Net, which introduces misalignments during the inversion and reconstruction process. To address this, we analyze reconstruction from a structural perspective and propose a novel approach that replaces traditional cross-attention with uniform attention maps, significantly enhancing image reconstruction fidelity. Our method effectively minimizes distortions caused by varying text conditions during noise prediction. To complement this improvement, we introduce an adaptive mask-guided editing technique that integrates seamlessly with our reconstruction approach, ensuring consistency and accuracy in editing tasks. Experimental results demonstrate that our approach not only excels in achieving high-fidelity image reconstruction but also performs robustly in real image composition and editing scenarios. This study underscores the potential of uniform attention maps to enhance the fidelity and versatility of diffusion-based image processing methods. Code is available at https://***/Mowenyii/Uniform-Attention-Maps. © 2025 IEEE.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

Analyzing Multiple Phenotypes Based on Principal Component Analysis

引用

Acta Mathematicae Applicatae Sinica 2022年第4期38卷 843-860页

作者： De-liang BU San-guo ZHANG Na LI School of Mathematical Sciences University of Chinese Academy of SciencesBeijing 100049China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of SciencesBeijing 100049China LSC NCMISAcademy of Mathematics and Systems ScienceChinese Academy of SciencesBeijing 100190China

Joint analysis of multiple phenotypes can have better interpretation of complex diseases and increase statistical power to detect more significant single nucleotide polymorphisms(SNPs)compare to traditional single phenotype analysis in genome-wide association *** component analysis(PCA),as a popular dimension reduction method,has been broadly used in the analysis of multiple *** PCA transforms the original phenotypes into principal components(PCs),it is natural to think that by analyzing these PCs,we can combine information across *** PCA-based methods can be divided into two categories,either selecting one particular PC manually or combining information from all *** this paper,we propose an adaptive principle component test(APCT)which selects and combines the PCs adaptively by using Cauchy combination *** proposed method can be seen as a generalization of traditional PCA based method since it contains two existing methods as special *** simulation shows that our method is robust and can generate powerful result in various *** real data analysis of stock mice data also demonstrate that our proposed APCT can identify significant SNPs that are missed by traditional methods.

关键词： multiple phenotypes principal component analysis cauchy combination method

来源：评论

学校读者我要写书评

暂无评论

Towards Tool Use Alignment of Large Language Models

Towards Tool Use Alignment of Large Language Models

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Chen, Zhi-Yuan Shen, Shiqi Shen, Guangyao Zhi, Gong Chen, Xu Lin, Yankai Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Tencent Inc. China

ISBN: (纸本)9798891761643

Recently, tool use with LLMs has become one of the primary research topics as it can help LLM generate truthful and helpful responses. Existing studies on tool use with LLMs primarily focus on enhancing the tool-calling ability of LLMs. In practice, like chat assistants, LLMs are also required to align with human values in the context of tool use. Specifically, LLMs should refuse to answer unsafe tool use relevant instructions and insecure tool responses to ensure their reliability and harmlessness. At the same time, LLMs should demonstrate autonomy in tool use to reduce the costs associated with tool calling. To tackle this issue, we first introduce the principle that LLMs should follow in tool use scenarios: H2A. The goal of H2A is to align LLMs with helpfulness, harmlessness, and autonomy. In addition, we propose ToolAlign, a dataset comprising instruction-tuning data and preference data to align LLMs with the H2A principle for tool use. Based on ToolAlign, we develop LLMs by supervised fine-tuning and preference learning, and experimental results demonstrate that the LLMs exhibit remarkable tool-calling capabilities, while also refusing to engage with harmful content, and displaying a high degree of autonomy in tool utilization. The code and datasets are available at: https://***/zhiyuanc2001/ToolAlign. © 2024 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

Are High-Degree Representations Really Unnecessary in Equivariant Graph Neural Networks? 38

Are High-Degree Representations Really Unnecessary in Equiva...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Cen, Jiacheng Li, Anyi Lin, Ning Ren, Yuxiang Wang, Zihe Huang, Wenbing Gaoling School of Artificial Intelligence Renmin University of China China Beijing Key Laboratory of Big Data Management and Analysis Methods China 2012 Laboratories Huawei Technologies Shanghai China

Equivariant Graph Neural Networks (GNNs) that incorporate the E(3) symmetry have achieved significant success in various scientific applications. As one of the most successful models, EGNN [1] leverages a simple scalarization technique to perform equivariant message passing over only Cartesian vectors (i.e., 1st-degree steerable vectors), enjoying greater efficiency and efficacy compared to equivariant GNNs using higher-degree steerable vectors. This success suggests that higher-degree representations might be unnecessary. In this paper, we disprove this hypothesis by exploring the expressivity of equivariant GNNs on symmetric structures, including k-fold rotations and regular polyhedra. We theoretically demonstrate that equivariant GNNs will always degenerate to a zero function if the degree of the output representations is fixed to 1 or other specific values. Based on this theoretical insight, we propose HEGNN, a high-degree version of EGNN to increase the expressivity by incorporating high-degree steerable vectors while still maintaining EGNN's advantage through the scalarization trick. Our extensive experiments demonstrate that HEGNN not only aligns with our theoretical analyses on a toy dataset consisting of symmetric structures, but also shows substantial improvements on other complicated datasets without obvious symmetry, including N-body and MD17. Our study potentially showcase an effective way of modeling high-degree representations in equivariant GNNs. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TGformer: A Graph Transformer Framework for knowledge Graph Embedding

引用

IEEE TRANSACTIONS ON knowledge AND data ENGINEERING 2025年第1期37卷 526-541页

作者： Shi, Fobo Li, Duantengchuan Wang, Xiaoguang Li, Bing Wu, Xindong Wuhan Univ Sch Informat Management Wuhan 430072 Peoples R China Wuhan Univ Intelligent Comp Lab Cultural Heritage Wuhan 430072 Peoples R China Wuhan Univ Sch Comp Sci Wuhan 430072 Peoples R China Hefei Univ Technol Key Lab Knowledge Engn Big Data Minist Educ China Hefei 230009 Peoples R China

knowledge graph embedding is efficient method for reasoning over known facts and inferring missing links. Existing methods are mainly triplet-based or graph-based. Triplet-based approaches learn the embedding of missing entities by a single triple only. They ignore the fact that the knowledge graph is essentially a graph structure. Graph-based methods consider graph structure information but ignore the contextual information of nodes in the knowledge graph, making them unable to discern valuable entity (relation) information. In response to the above limitations, we propose a general graph transformer framework for knowledge graph embedding (TGformer). It is the first to use a graph transformer to build knowledge embeddings with triplet-level and graph-level structural features in the static and temporal knowledge graph. Specifically, a context-level subgraph is constructed for each predicted triplet, which models the relation between triplets with the same entity. Afterward, we design a knowledge graph transformer network (KGTN) to fully explore multi-structural features in knowledge graphs, including triplet-level and graph-level, boosting the model to understand entities (relations) in different contexts. Finally, semantic matching is adopted to select the entity with the highest score. Experimental results on several public knowledge graph datasets show that our method can achieve state-of-the-art performance in link prediction.

关键词： knowledge graph graph transformer link prediction knowledge graph graph transformer link prediction

来源：评论

学校读者我要写书评

暂无评论

CITE: Compact Interactive TransformEr for Multilingual Image Captioning 23

CITE: Compact Interactive TransformEr for Multilingual Image...

引用

6th International Conference on Image and Graphics Processing, ICIGP 2023

作者： Xu, Yueyuan Hu, Zhenzhen Zhou, Yuanen Hao, Shijie Hong, Richang Key Laboratory of Knowledge Engineering with Big Data School of Computer and Information Hefei University of Technology China Institute of Artificial Intelligence Hefei Comprehensive National Science Center Hefei China

ISBN: (纸本)9781450398572

Current state-of-the-art image captioning models generate captions in a single language, requiring a combination of multiple language specific models to build a multilingual image captioning system. However, as the number of supported languages increases, it leads to the parameters of the multilingual image captioning system grow linearly. To tackle this issue, we propose a single Compact Interactive TransformEr (CITE) model, which can describe an image in multiple languages simultaneously, making the captioning system more compact. Specifically, based on the standard Transformer model, we share the encoder and decoder backbone parameters and replace the self-attention sub-layer in the decoder with the interactive attention sub-layer. In addition, we extend the traditional monolingual reinforcement learning mechanism to a multilingual version to promote better description generation. Due to the wide use of Chinese and English, we evaluate the performance of our CITE model by simultaneously generating English and Chinese captions. We expand the image captions of the whole MSCOCO dataset and release a COCO-EN-CN dataset. Extensive experiments on the COCO-EN-CN dataset show that our single CITE model with more parameter-efficient can maintain the competitive performance or even better than the monolingual captioning models. © 2023 ACM.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach for data-Literature Linking 23

A Hybrid Approach for Data-Literature Linking

引用

7th International Conference on Computer Science and Application Engineering, CSAE 2023

作者： Li, Jiao Huang, Yongwen Sun, Tan Xian, Guojian Key Laboratory of Knowledge Mining and Knowledge Services in Agricultural Converging Publishing National Press and Publication Administration Agricultural Information Institute of Caas Beijing100081 China Key Laboratory of Agricultural Big Data Ministry of Agriculture and Rural Affairs Chinese Academy of Agricultural Sciences Beijing100081 China

ISBN: (纸本)9798400700590

Current solutions that link research data with scientific literature are primarily constrained in the dimension and depth of relations, which is a necessity for the sharing and reuse of scholarly resources and accelerating scientific progress. This paper presents a data-literature linking framework that combines data enrichment techniques of entity extraction, discipline classification & subject indexing based on semantic knowledge bases, and further implement multi-scenario data-literature link discovery with data from persistent identifier provisions - dataCite and CrossRef, including research data retrieval and faceted browsing, data-literature and data-data bidirectional discovery, entity-based link browsing and navigation. © 2023 ACM.

关键词： knowledge based systems

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：