检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Wang, Wenbin Ding, Liang Zeng, Minyan Zhou, Xiabin Shen, Li Luo, Yong Yu, Wei Tao, Dacheng School of Computer Science National Engineering Research Center for Multimedia Software Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China The University of Sydney Australia Jiangsu University China Shenzhen Campus of Sun Yat-sen University China College of Computing and Data Science Nanyang Technological University Singapore

ISBN: (纸本)157735897X

Multimodal large language models (MLLMs) have experienced significant advancements recently, but still struggle to recognize and interpret intricate details in high-resolution (HR) images effectively. While state-of-the-art (SOTA) MLLMs claim to process images at 4K resolution, existing MLLM benchmarks only support up to 2K, leaving the capabilities of SOTA models on true HR images largely untested. Furthermore, existing methods for enhancing HR image perception in MLLMs rely on computationally expensive visual instruction tuning. To address these limitations, we introduce HR-Bench, the first deliberately designed benchmark to rigorously evaluate MLLM performance on 4K&8K images. Through extensive experiments, we demonstrate that while downsampling HR images leads to vision information loss, leveraging complementary modalities, e.g., text, can effectively compensate for this loss. Building upon this insight, we propose Divide, Conquer and Combine, a novel training-free framework for enhancing MLLM perception of HR images. Our method follows a three-staged approach: 1) Divide: recursively partitioning the HR image into patches and merging similar patches to minimize computational overhead, 2) Conquer: leveraging the MLLM to generate accurate textual descriptions for each image patch, and 3) Combine: utilizing the generated text descriptions to enhance the MLLM's understanding of the overall HR image. Extensive experiments show that: 1) the SOTA MLLM achieves 63% accuracy, which is markedly lower than the 87% accuracy achieved by humans on HR-Bench;2) our method brings consistent and significant improvements (a relative increase of +6% on HR-Bench and +8% on general multimodal benchmarks). Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

A Battery Swapping Service Management System Reliability-Based Design Concerning Station Information Delay

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1063-1078页

作者： Li, Xinyu Cao, Yue Hu, Ziyi Zhang, Xu Liu, Zhi Lei, Xinhai Wuhan University School of Cyber Science and Engineering Wuhan430073 China Wuhan Institute of Technology Hubei Key Laboratory of Intelligent Robot Wuhan430250 China School of Computing Sciences Norwich United Kingdom University of Electro-Communications Department of Computer and Network Engineering Tokyo Japan Wuhan Public Resources Trading Center Wuhan China

Since the long duration associated with traditional plug-in charging modes inevitably causes range anxiety to electric vehicle (EV) drivers, the battery swapping technology has emerged as a promising alternative. It thus becomes imperative to develop a reliable battery swapping service system, efficiently managing the large-scale energy replenishing demands from EVs. Firstly, this paper considers drivers' trip destination to minimize total trip duration, and the expense paid for battery swapping service to save users' service cost. By optimizing the requirement of battery swapping service during peak-price period, the expenditure for energy supplement can be reduced. Secondly, concerning in practice that the transmission delay is a crucial factor impacting the overall network and system reliability, this paper further investigates the impact of station information delay between the global controller and battery swapping stations (BSSs). By characterizing the delay into two types, namely, low and large delays, the scenario based on a known delay type are investigated. Thirdly, delay cases with multiple BSSs are also taken into account and a mixed decision-making method is developed. Finally, simulation results indicate the desirable performance of proposed scheme in satisfying user demand and alleviating impact of station information delay. © 1975-2011 IEEE.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

A Cognitive Memory-Augmented network for Visual Anomaly Detection

引用

IEEE/CAA Journal of Automatica Sinica 2021年第7期8卷 1296-1307页

作者： Tian Wang Xing Xu Fumin Shen Yang Yang the Center for Future Multimedia and School of Computer Science and Engineering University of Electronic Science and Technology of China(UESTC)Chengdu 611731China the Center for Future Multimedia and School of Computer Science and Engineering University of Electronic Science and Technology of ChinaChengdu 611731 the Institute of Electronic and Information Engineering of UESTC in Guangdong Dongguan 523808China

With the rapid development of automated visual analysis,visual analysis systems have become a popular research topic in the field of computer vision and automated *** analysis systems can assist humans to detect anomalous events(e.g.,fighting,walking alone on the grass,etc).In general,the existing methods for visual anomaly detection are usually based on an autoencoder architecture,i.e.,reconstructing the current frame or predicting the future ***,the reconstruction error is adopted as the evaluation metric to identify whether an input is abnormal or *** flaws of the existing methods are that abnormal samples can also be reconstructed *** this paper,inspired by the human memory ability,we propose a novel deep neural network(DNN)based model termed cognitive memory-augmented network(CMAN)for the visual anomaly detection *** proposed CMAN model assumes that the visual analysis system imitates humans to remember normal samples and then distinguishes abnormal events from the collected ***,in the proposed CMAN model,we introduce a memory module that is able to simulate the memory capacity of humans and a density estimation network that can learn the data *** reconstruction errors and the novelty scores are used to distinguish abnormal events from *** addition,we develop a two-step scheme to train the proposed model so that the proposed memory module and the density estimation network can cooperate to improve *** experiments evaluated on various popular benchmarks show the superiority and effectiveness of the proposed CMAN model for visual anomaly detection comparing with the state-of-the-arts *** implementation code of our CMAN method can be accessed at https://***/CMANcode/CMAN_pytorch.

关键词： Cognitive computing density estimation memory visual analysis systems visual anomaly detection.

来源：评论

学校读者我要写书评

暂无评论

Mandarin Lombard Grid: A Noise Induced Lombard-Grid-Like Corpus of Standard Chinese 23

Mandarin Lombard Grid: A Noise Induced Lombard-Grid-Like Cor...

引用

23rd Annual Conference of the International Speech Communication Association, INTERSPEECH 2022

作者： Yang, Yuhong Chen, Xufeng Liu, Qingmu Tu, Weiping Chen, Hongyang Cai, Linjun National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan China

The Lombard effect is natural, whereby speakers automatically adjust the vocal effort to facilitate speech understanding in noise. Since real-world applications are generally involved in noisy environments, the Lombard effect of highly variable speech features due to changing background noise is one of those challenges to match these real scenarios. Existing Lombard corpora show variations in the background noise level, ranging from 35 to 96 dB sound pressure level (SPL). However, it remains unclear if we need to collect all SPLs to build a comprehensive Lombard corpus. And most existing Lombard corpora are built for English;however, Mandarin and English are different in pronunciation. This paper describes our effort to build the first open-source Lombard corpus of standard Chinese, the Mandarin Lombard Grid. The effort involves three steps: (1) Classify Mandarin Lombard styles according to different background noise levels. (2) Create the corpus containing each style. (3) Analyze Mandarin Lombard effects showing their differences from English. We found three critical Lombard styles ranging from 30 dB to 85 dB-SPL and built the corpus containing the three Lombard styles and one reference plain style. Lombard effect analyses on this corpus showed consistency and some differences with the English Lombard Grid corpus. Copyright © 2022 ISCA.

关键词： Speech communication

来源：评论

学校读者我要写书评

暂无评论

Knowledge Extraction and Application of Railway Operation Equipment Fault Diagnosis Based on Knowledge Graph 15

Knowledge Extraction and Application of Railway Operation Eq...

引用

15th IEEE Global Reliability and Prognostics and Health Management Conference, PHM-Beijing 2024

作者： He, Ruiyi Li, Honghui Liu, Shufang Yang, Xiaorui Wang, Zibo School of Computer Science and Technology Beijing Jiaotong University Beijing China School of Computer Science and Technology Beijing Jiaotong University Engineering Research Center of Network Management Technology for High Speed Railway of MOE Beijing China School of Railway Safety Theory and Technology Southwest Jiaotong University Sichuan China

ISBN: (纸本)9798350354010

Focusing on the issue where traditional fault diagnosis methods cannot effectively utilize the textual records of railway equipment faults and heavily rely on experts' experience, a knowledge graph-based fault analysis method for railway operation equipment is proposed. By designing preprocessing rules to process the text corpus to be annotated, and combining the attention mechanism (ATT) and bi-directional gated recurrent neural network (BiGRU) to complete the knowledge extraction, the knowledge graph of railway operation equipment faults is constructed. On this basis, a cause recommendation strategy combining query and reasoning is designed, which can give reasonable fault analysis suggestions based on the faults that have occurred. This research utilizes the dataset sourced from a railway administration, examines the effectiveness of the knowledge extraction method through experiments, and analyzes the feasibility of utilizing the constructed knowledge graph to assist in fault analysis through cause recommendation. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Enhancing Causal Discovery in Federated Settings with Limited Local Samples

Enhancing Causal Discovery in Federated Settings with Limi...

引用

International Workshop on Trustworthy Federated Learning, FL 2024

作者： Guo, Xianjie Yi, Liping Wu, Xiaohu Yu, Kui Wang, Gang School of Computer Science and Information Engineering Hefei University of Technology Hefei China College of Computer Science Nankai University Tianjin China National Engineering Research Center of Mobile Network Technologies Beijing University of Posts and Telecommunications Beijing China

ISBN: (纸本)9783031822391

Causal discovery from observational data is crucial for understanding complex systems, but traditional methods often require centralized data, conflicting with growing privacy concerns. Although federated causal discovery (FCD) has emerged as a solution, existing methods struggle when individual clients possess limited local samples. This paper introduces FedECD, a novel approach addressing causal discovery in federated settings with limited local samples. FedECD comprises two phases: 1) Federated Causal Skeleton Optimization and 2) Federated Causal Structure Refinement, both leveraging Bootstrapping techniques to enhance robustness and accuracy across distributed clients. Both phases employ a two-layer aggregation strategy: client-layer aggregates results from Bootstrapped sub-datasets within each client, while server-layer aggregates across all clients. The first phase uses weighted aggregation to iteratively remove false causal edges based on conditional independence tests. In contrast, the second phase utilizes majority voting to determine edge directions, ensuring robust estimation of the true causal structure. Extensive experiments on eight benchmark Bayesian network datasets demonstrate the superiority of FedECD over existing FCD methods, particularly with limited sample sizes. FedECD achieves an average improvement of 7.53% in the Ar_F1 score compared to the best baseline, addressing a critical challenge in FCD. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

A Robust Low-Rank Tensor Decomposition and Quantization based Compression Method 40

A Robust Low-Rank Tensor Decomposition and Quantization base...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Ouyang, Yudian Xie, Kun Wen, Jigang Xie, Gaogang Li, Kenli College of Computer Science and Electronics Engineering Hunan University Changsha China Hangzhou Institute of Advanced Technology Hangzhou China School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan China Institute of Computer Network Information Center Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798350317152

Tensor data is widely used in fields such as smart grids, cloud systems, and deep learning. As the scale of this data increases, storage and transmission costs rise significantly. Many tensor data exhibit low-rank structures, offering the potential for data compression through low-rank decomposition techniques. Tucker decomposition, a typical low-rank decomposition technique, achieves data compression and interpretability by capturing complex data correlations and representing the original tensor with a compact core tensor and factor matrices. However, the compression ratio provided by Tucker decomposition is often insufficient, particularly for large-scale tensors. To tackle this issue, we propose a robust low-rank tensor compression method that leverages Tucker decomposition with quantization and coding. Initially, we establish a robust Tucker decomposition framework that decomposes the low-rank tensor into a core tensor and factor matrices using well-designed Tucker rank-setting rules. This framework effectively handles noise and missing values. Subsequently, we conduct an in-depth analysis of the numerical characteristics of the core tensor and factor matrices within the Tucker decomposition framework. Based on their distinct characteristics, we design tailored quantization and coding schemes to compress the core tensor and factor matrices, respectively, thereby significantly improving the compression ratio of Tucker decomposition while maintaining high accu-racy. Through extensive experiments on four publicly available datasets (which can form 3 or 4 order tensors), we demonstrate that our approach can achieve compression ratios 4×-10× higher than the best competitor, with recovery errors improved by 8% -42%. © 2024 IEEE.

关键词： Tensors

来源：评论

学校读者我要写书评

暂无评论

A Near Lossless Learned Image Coding network Quantization Approach for Cross-Platform Inference

A Near Lossless Learned Image Coding Network Quantization Ap...

引用

2023 IEEE International Conference on Visual Communications and Image Processing, VCIP 2023

作者： Hang, Xinyu Jia, Chuanmin Ma, Siwei Gao, Wen Peking University National Engineering Research Center on Visual Technology School of Computer Science China Peking University National Key Laboratory for Multimedia Information Processing School of Computer Science China Peking University Wangxuan Institute of Computer Technology China

ISBN: (纸本)9798350359855

This paper presents an innovative pipeline design for the quantization of neural image codecs, ensuring robust and consistent deployment across various platform inferences. Our approach addresses a significant challenge prevalent in neural image compression networks: the lack of quantization methods for entropy probability hyper-priors, such as Gaussian mixture models (GMMs), in the existing literature. Our method serves as a solution to prevent decoding errors stemming from float-point discrepancies between the encoder and decoder, especially when executed on different platforms. By implementing a quantization scheme based on look-up tables (LUTs), we achieve precise quantization of GMM probability models with minimal performance degradation, approaching near losslessness. Moreover, our contribution offers a comprehensive quantization pipeline that facilitates dependable data transmission and harmonious synchronization of arithmetic coding algorithms between the encoder and decoder components. Empirical evidence highlights the effectiveness of our method, demonstrating seamless codec matching on diverse platforms and substantiating its capacity to enhance the integrity and security of compressed data. This work enhances the practical applicability of neural compression techniques across real-world scenarios. © 2023 IEEE.

关键词： Table lookup

来源：评论

学校读者我要写书评

暂无评论

TFSG: A Self-Supervised Guided Graph Learning Method for Traffic Flow Prediction

引用

IEEE Internet of Things Journal 2025年第13期12卷 24345-24357页

作者： Zheng, Yingran Luo, Chao Shao, Rui Shandong Normal University School of Information Science and Engineering Jinan250014 China Shandong Provincial Key Laboratory for Novel Distributed Computer Software Technology Jinan250014 China China Mobile Shandong Co. Ltd center of network optimization Jinan250014 China

With the rapid development of the Internet of Things, a large amount of real-time traffic data has been collected. How to fully utilize these traffic data for rational planning of intelligent transportation systems is an important issue. Graph learning has proved to be potential tools for modeling complex spatiotemporal relationships in addressing traffic flow prediction problems. Existing methods usually relied on the graph structure constructed from predefined distance information between different regions. However, affected by factors such as road capacity, traffic rules etc., distance bias is non-trivial to affect traffic flow in reality. Besides, the distance based static transportation network structure is also difficult to describe the dynamic and uncertainty of road traffic in complex situations. To address the aforementioned issues, this article proposes an enhanced graph generation approach for traffic flow prediction, which is based on Temporal-Frequency Self-Supervised Guided Graph Learning (TFSG). The method progressively guides the feature latent representation to approach the target latent representation in both the time domain and frequency domain. Meanwhile, a multi-head self-attention mechanism is introduced to capture dependencies among different time series patches, constructing an enhanced graph structure for downstream prediction tasks. Experimental results first independently evaluated the qualities of the generated graphs. Subsequently, by using five public traffic datasets, the feasibility and effectiveness of the proposed method are further verified. © 2014 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

A Self-Expressive Feature Selection Algorithm Based on Self-Representation of Data

A Self-Expressive Feature Selection Algorithm Based on Self-...

引用

2024 International Symposium on Digital Home, ISDH 2024

作者： Qiu, Jie Chen, Zuoyun Chen, Jianmei Lan, Wei Ding, Xiaojun Computer Science and Engineering College Yulin Normal University Center for Applied Mathematics of Guangxi Guangxi Yulin537000 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Center for Applied Mathematics of Guangxi Guangxi Nanning537000 China

ISBN: (纸本)9798331509873

Many biological data exhibit characteristics such as high dimensionality, large scale, high complexity, and high noise. In many cases, it is necessary to eliminate noise and identify truly useful features for better data analysis and modeling. In labeled data, algorithms such as correlation analysis or embedded selection methods can be used to select features most relevant to the labels. However, these algorithms are not effective for unlabeled data. Currently, common methods involve selecting features with higher variance or, based on feature correlation, identifying central features from a group of related features. This paper proposes a new method for feature selection using self-representation of data. The idea is that features in high-dimensional biological big data exhibit some redundancy, and redundant features can be represented by other features. Therefore, it is only necessary to find a subset of features, from which the entire dataset can be generated. This subset may represent more essential and important features. Using this subset for subsequent work can resist certain noise and reduce complexity, thereby improving algorithm performance. The paper presents a framework that can use linear models and non-linear neural network models to select feature subsets. Experiments compared the proposed method with popular unsupervised feature selection methods, using KMeans, KNN, and SVM as classification methods to classify the original data and the data after feature selection, and analyzed the results. The experiments ultimately demonstrated that the proposed method in this paper outperforms other popular unsupervised feature selection methods on multiple biological datasets. © 2024 IEEE.

关键词： Feature Selection

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：