检索结果-内蒙古大学图书馆

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ruizhou Liu Zongsheng Cao Zhe Wu Qianqian Xu Qingming Huang School of Computer Science and Technology University of Chinese Academy Sciences Beijing China Department of Networked Intelligence Pengcheng Laboratory Shenzhen China Institute of Information Engineering Chinese Academy Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology CAS Beijing China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Multimodal knowledge graph embeddings (MKGE) have recently garnered significant attention. Unlike traditional unimodal knowledge graph embeddings, MKGE integrates both structural and multimodal knowledge to represent entities within a unified framework. However, real-world entities exhibit heterogeneity, often resulting in semantic inconsistencies where structurally similar embeddings may diverge significantly in their multimodal representations. Previous approaches primarily focus on directly fusing structural and multimodal embeddings, thus overlooking the issue of semantic-embedding inconsistency. To tackle this issue, we propose a new multimodal knowledge graph embedding method via Lorentz-based contrastive learning (LCKGE). we firstly introduce a well-designed nearest-neighbor fusion module via contrastive learning for multimodal fusion. Then, an attention-based Lorentz transformation is proposed for capturing more complex geometric information in MKGs. Furthermore, a series of comprehensive experiments are conducted to demonstrate the effectiveness of our model. We provide the code and appendix of LCKGE in https://***/RuizhouLiu/LCKGE

关键词： Codes Semantics Knowledge graphs Contrastive learning Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Analysis of Different Methods for Forecasting Transport Carbon Dioxide Emissions in the Philippines

引用

Transportation Research Procedia 2025年 82卷 3768-3789页

作者： Aaron Michael Salang Virgilio Ma. Ramos Arse John Salison John Justine Villar Intelligent Transportation Systems Laboratory National Center for Transportation Studies University of the Philippines Diliman Quezon City Philippines Department of Logistics and Information Engineering Tokyo University of Marine Science and Technology Tokyo Japan Scientific Computing Laboratory Department of Computer Science University of the Philippines Diliman Quezon City Philippines

Emission forecasts can be an important way of creating awareness among the public and decision-makers on solving environmental problems. The main goal of this study is to forecast and compare the transport CO2 emissions of the Philippines using four different forecasting models. We use the models of Holt-Winters Exponential Smoothing, Autoregressive Integrated Moving Average (ARIMA), Vector Autoregressive (VAR), and the Artificial Neural Network (ANN). The performance of the different forecasting methods was compared using the coefficient of determination (R2) and the root mean squared error (RMSE) values. Several economic variables from 1990 to 2019 and the transport Carbon Dioxide (CO2) emissions in the Philippines were utilized in this study. The result show that all four methods exhibit goodness of fit and accuracy results according to the statistical measures. In comparison, the multivariate methods (ANN & VAR) performed better than univariate methods (ARIMA & Holt-Winters).

关键词： Transport Emissions Forecasting Time-series modeling ARIMA ANN VAR Holt-Winters

来源：评论

学校读者我要写书评

暂无评论

SILTD: Structural information for LLM-Generated Text Detection

引用

International Journal of Machine Learning and Cybernetics 2025年

作者： Yang, Jing Wang, Shi Zi, Kangli Sun, Yanshun Huang, Yuwei Luo, Tianyu Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China University of Chinese Academy of Sciences Beijing 100049 China

The rapid development of large language models (LLMs) has significantly improved the quality and diversity of AI-generated content(AIGC). LLM-Generated text detection plays an important role in preventing the harmful misuse of large language models. Existing approaches primarily analyze texts individually, overlooking the structural relationships between them. This limitation restricts their ability to generalize across diverse LLMs, as they fail to capture the shared statistical patterns inherent in generated texts. To address this, an unsupervised-based structural information for LLM-generated text detection (SILTD) method is proposed. The key insight is that texts from different LLMs exhibit latent similarities in their generative statistical space, which can be modeled to improve cross-model generalization. First, we construct a multi-relational text graph based on the similarity of text features, which aims to model the intricate similarities and correlations between texts. Second, we propose a novel unsupervised graph clustering method. The multi-relational graph is transformed into an encoding tree, which is then optimized based on a two-dimensional structure entropy minimization algorithm to achieve hierarchical clustering of texts. Structural entropy minimization enables achieving high-quality clusters, by measuring the uncertainty of random walks within the graph. Finally, we introduce a new method that measures text similarity and computes the intensity of text aggregation within each cluster, to perform in-cluster label inference. Extensive experiments show that, compared to baseline methods, our approach is more effective and generalizable in detecting six popular LLMs across five datasets. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Clustering LLM-generated text detection Multi-relational graph Structural information

来源：评论

学校读者我要写书评

暂无评论

Wavelet-Driven Masked Image Modeling: A Path to Efficient Visual Representation

arXiv

引用

arXiv 2025年

作者： Xiang, Wenzhao Liu, Chang Yu, Hongyang Chen, Xilin Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China Peng Cheng Laboratory China University of Chinese Academy of Sciences China Department of Electronic Engineering Shanghai Jiao Tong University China

Masked Image Modeling (MIM) has garnered significant attention in self-supervised learning, thanks to its impressive capacity to learn scalable visual representations tailored for downstream tasks. However, images inherently contain abundant redundant information, leading the pixel-based MIM reconstruction process to focus excessively on finer details such as textures, thus prolonging training times unnecessarily. Addressing this challenge requires a shift towards a compact representation of features during MIM reconstruction. Frequency domain analysis provides a promising avenue for achieving compact image feature representation. In contrast to the commonly used Fourier transform, wavelet transform not only offers frequency information but also preserves spatial characteristics and multi-level features of the image. Additionally, the multi-level decomposition process of wavelet transformation aligns well with the hierarchical architecture of modern neural networks. In this study, we leverage wavelet transform as a tool for efficient representation learning to expedite the training process of MIM. Specifically, we conduct multi-level decomposition of images using wavelet transform, utilizing wavelet coefficients from different levels to construct distinct reconstruction targets representing various frequencies and scales. These reconstruction targets are then integrated into the MIM process, with adjustable weights assigned to prioritize the most crucial information. Extensive experiments demonstrate that our method achieves comparable or superior performance across various downstream tasks while exhibiting higher training efficiency. Copyright © 2025, The Authors. All rights reserved.

关键词： Frequency domain analysis

来源：评论

学校读者我要写书评

暂无评论

Bidirectional Logits Tree: Pursuing Granularity Reconcilement in Fine-Grained Classification 39

Bidirectional Logits Tree: Pursuing Granularity Reconcilemen...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

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

ISBN: (纸本)157735897X

This paper addresses the challenge of Granularity Competition in fine-grained classification tasks, which arises due to the semantic gap between multi-granularity labels. Existing approaches typically develop independent hierarchy-aware models based on shared features extracted from a common base encoder. However, because coarse-grained levels are inherently easier to learn than finer ones, the base encoder tends to prioritize coarse feature abstractions, which impedes the learning of fine-grained features. To overcome this challenge, we propose a novel framework called the Bidirectional Logits Tree (BiLT) for Granularity Reconcilement. The key idea is to develop classifiers sequentially from the finest to the coarsest granularities, rather than parallelly constructing a set of classifiers based on the same input features. In this setup, the outputs of finer-grained classifiers serve as inputs for coarser-grained ones, facilitating the flow of hierarchical semantic information across different granularities. On top of this, we further introduce an Adaptive Intra-Granularity Difference Learning (AIGDL) approach to uncover subtle semantic differences between classes within the same granularity. Extensive experiments demonstrate the effectiveness of our proposed method. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

DeepMesh: A Comprehensive Survey of Deep Learning-Based Routing Performance in Wireless Mesh Networks 18

DeepMesh: A Comprehensive Survey of Deep Learning-Based Rout...

引用

18th International Conference on intelligent Systems and Knowledge Engineering, ISKE 2023

作者： Xiaoping, Qiu Alam, Md Zahidul Du, Shiling Yue, Zhongjian Wang, Yulan School of Computing and Artificial Intelligence Southwest Jiaotong University Chengdu610031 China Tangshan Institute of Southwest Jiaotong University Tangshan063000 China National United Engineering Laboratory of Integrated and Intelligent Transportation Chengdu611756 China Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education Chengdu611756 China Manufacturing Industry Chains Collaboration and Information Support Technology Key Laboratory of Sichuan Province Chengdu610031 China Sichuan Institute of Industrial Software Technology Sichuan Chengdu China

ISBN: (纸本)9798350318401

This paper provides a analysis of the challenges faced in routing in wireless mesh networks and how deep learning can be used to improve performance. Wireless mesh networks (WMNs) are a particular kind of wireless network that use mesh routers and mesh clients that talk to one another to provide wireless coverage over a wide area. The paper discusses the limitations of traditional routing methods in WMNs and highlights the potential of deep learning-based routing approaches to revolutionize WMNs. The survey evaluates the literature focusing on the various routing approaches, performances, and research methodologies. The study aims to provide several potential areas for further investigation in deep learning-based routing approaches for WMNs and discusses several research challenges and opportunities in the field. The identification of trends and challenges, and recommendations for future research directions provide valuable insights for researchers and practitioners in the field of wireless mesh networks. © 2023 IEEE.

关键词： Mesh generation

来源：评论

学校读者我要写书评

暂无评论

FUZZY ALIGNMENTS IN DIRECTED ACYCLIC GRAPH FOR NON-AUTOREGRESSIVE MACHINE TRANSLATION

arXiv

引用

arXiv 2023年

作者： Ma, Zhengrui Shao, Chenze Gui, Shangtong Zhang, Min Feng, Yang Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences China University of Chinese Academy of Sciences China Harbin Institute of Technology Shenzhen China

Non-autoregressive translation (NAT) reduces the decoding latency but suffers from performance degradation due to the multi-modality problem. Recently, the structure of directed acyclic graph has achieved great success in NAT, which tackles the multi-modality problem by introducing dependency between vertices. However, training it with negative log-likelihood loss implicitly requires a strict alignment between reference tokens and vertices, weakening its ability to handle multiple translation modalities. In this paper, we hold the view that all paths in the graph are fuzzily aligned with the reference sentence. We do not require the exact alignment but train the model to maximize a fuzzy alignment score between the graph and reference, which takes captured translations in all modalities into account. Extensive experiments on major WMT benchmarks show that our method substantially improves translation performance and increases prediction confidence, setting a new state of the art for NAT on the raw training data.1 Copyright © 2023, The Authors. All rights reserved.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Meta-Causal Learning for Single Domain Generalization

Meta-Causal Learning for Single Domain Generalization

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Jin Chen Zhi Gao Xinxiao Wu Jiebo Luo Beijing Key Laboratory of Intelligent Information Technology School of Computer Science & Technology Beijing Institute of Technology China Guangdong Laboratory of Machine Perception and Intelligent Computing Shenzhen MSU-BIT University China Department of Computer Science University of Rochester Rochester NY USA

Single domain generalization aims to learn a model from a single training domain (source domain) and apply it to multiple unseen test domains (target domains). Existing methods focus on expanding the distribution of the training domain to cover the target domains, but without estimating the domain shift between the source and target domains. In this paper, we propose a new learning paradigm, namely simulate-analyze-reduce, which first simulates the domain shift by building an auxiliary domain as the target domain, then learns to analyze the causes of domain shift, and finally learns to reduce the domain shift for model adaptation. Under this paradigm, we propose a meta-causal learning method to learn meta-knowledge, that is, how to infer the causes of domain shift between the auxiliary and source domains during training. We use the meta-knowledge to analyze the shift between the target and source domains during testing. Specifically, we perform multiple transformations on source data to generate the auxiliary domain, perform counterfactual inference to learn to discover the causal factors of the shift between the auxiliary and source domains, and incorporate the inferred causality into factor-aware domain alignments. Extensive experiments on several benchmarks of image classification show the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SELF-SUPERVISED DIFFUSION MRI DENOISING VIA ITERATIVE AND STABLE REFINEMENT

arXiv

引用

arXiv 2025年

作者： Wu, Chenxu Kong, Qingpeng Jiang, Zihang Kevin Zhou, S. School of Biomedical Engineering Division of Life Sciences and Medicine USTC China MIRACLE Center Suzhou Institute for Advance Research USTC China State Key Laboratory of Precision and Intelligent Chemistry USTC China Key Laboratory of Intelligent Information Processing of CAS Institute of Computing Technology CAS China

Magnetic Resonance Imaging (MRI), including diffusion MRI (dMRI), serves as a "microscope" for anatomical structures and routinely mitigates the influence of low signal-to-noise ratio scans by compromising temporal or spatial resolution. However, these compromises fail to meet clinical demands for both efficiency and precision. Consequently, denoising is a vital preprocessing step, particularly for dMRI, where clean data is unavailable. In this paper, we introduce Di-Fusion, a fully self-supervised denoising method that leverages the latter diffusion steps and an adaptive sampling process. Unlike previous approaches, our single-stage framework achieves efficient and stable training without extra noise model training and offers adaptive and controllable results in the sampling process. Our thorough experiments on real and simulated data demonstrate that Di-Fusion achieves state-of-the-art performance in microstructure modeling, tractography tracking, and other downstream tasks. Code is available at https://***/FouierL/Di-Fusion. Copyright © 2025, The Authors. All rights reserved.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Circular Decomposition and Cross-Modal Recombination for Multimodal Sentiment Analysis

Circular Decomposition and Cross-Modal Recombination for Mul...

引用

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

作者： Haijian Liang Weicheng Xie Xilin He Siyang Song Linlin Shen School of Computer Science & Software Engineering Computer Vision Institue Shenzhen University Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University School of Computing and Mathematical Sciences University of Leicester National Engineering Laboratory for Big Data System Computing Technology Shenzhen University

Multimodal Sentiment Analysis is a burgeoning research area, leveraging various modalities to predict the sentiment score. Nevertheless, previous studies have disregarded the impact of noise interference on specific modal sentiments during video recording, thereby compromising the accuracy of sentiment prediction. In this paper, we propose the Guided Circular Decomposition and Cross-Modal Recombination (GCD-CMR) model, which aims to eliminate contaminated sentiment features in a fine-grained way. To achieve this, we utilize tailored global information specific to each modality to guide the circular decomposing process in the GCD module, to produce a set of sentiment prototypes. Subsequently, in the CMR module, we align cross-modal sentiment prototypes and remove the contaminated prototypes for recombination. Experimental results on two publicly available datasets demonstrate that our model surpasses state-of-the-art models, confirming the effectiveness of our proposed method. We release the code at: https://***/nianhua20/GCD-CMR.

关键词：

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：