检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Zhang, Pei Wang, Dong Wu, Chanyue Yang, Jing Kang, Lei Bai, Zongwen Li, Ying Shen, Qiang School of Computer Science Northwestern Polytechnical University Xi'an China Shaanxi Key Laboratory of Intelligent Processing for Big Energy Data Yan'an University Yan'an China School of Automation and Software Engineering Shanxi University Taiyuan China Qingdao Topscomm Communication Co. Ltd. Qingdao China Department of Computer Science Aberystwyth University Aberystwyth United Kingdom

ISBN: (纸本)9798350368741

Hyperspectral Image (HSI) cross-scene classification is a challenging task in remote sensing, particularly when real-time processing of Target Domain (TD) HSI is required, and data cannot be reused for training. While deep learning methods have shown promising results, the generalization ability of HSI representations remains limited, mainly due to class label imbalance. This paper introduces a dual-stage learning framework based on transfer learning to enhance classification accuracy in the TD. The framework includes a self-supervised learning stage and a supervised fine-tuning stage. The self-supervised stage focuses on learning robust representations by leveraging inherent structures within HSI data, while the fine-tuning stage uses training labels to extract semantic information. A masked diffusion model predicts masked tokens from unmasked ones, capturing both high-level structures and fine details in HSI data. An efficient spatiospectral Transformer, which removes self-attention from the decoder, is proposed to enhance the self-supervised process. This design allows mask tokens to obtain information from visible tokens without interacting with each other, reducing sequence length and computational costs. By decoding each mask token conditionally independently, only a subset of masked tokens is processed. Extensive experiments on two public HSI datasets demonstrate that the proposed method outperforms state-of-the-art techniques. © 2025 IEEE.

关键词： Cross-scene classification Diffusion model Hyperspectral image Transformer

来源：评论

学校读者我要写书评

暂无评论

CHARACTERIZATION OF DIM LIGHT RESPONSE IN DVS PIXEL: DISCONTINUITY OF EVENT TRIGGERING TIME

arXiv

引用

arXiv 2024年

作者： Jiang, Xiao Zhou, Fei College of Electronic and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China Peng Cheng Laboratory Shenzhen China

Dynamic Vision Sensors (DVS) have recently generated great interest because of the advantages of wide dynamic range and low latency compared with conventional frame-based cameras. However, the complicated behaviors in dim light conditions are still not clear, restricting the applications of DVS. In this paper, we analyze the typical DVS circuit, and find that there exists discontinuity of event triggering time. In dim light conditions, the discontinuity becomes prominent. We point out that the discontinuity depends exclusively on the changing speed of light intensity. Experimental results on real event data validate the analysis and the existence of discontinuity that reveals the non-first-order behaviors of DVS in dim light conditions. © 2024, CC BY.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

ChartKG: A Knowledge-Graph-Based Representation for Chart Images

arXiv

引用

arXiv 2024年

作者： Zhou, Zhiguang Wang, Haoxuan Zhao, Zhengqing Zheng, Fengling Wang, Yongheng Chen, Wei Wang, Yong School of Media and Design Hangzhou Dianzi University CO Hangzhou310018 China School of Media and Design Hangzhou Dianzi University China Big Data Visualization and Human Computer Collaborative Intelligent Laboratory Hangzhou Dianzi University China Research Center of Big Data Intelligence Zhejiang Lab Hangzhou China State Key Lab of CAD&CG Zhejiang University China College of Computing and Data Science Nanyang Technological University Singapore

Chart images, such as bar charts, pie charts, and line charts, are explosively produced due to the wide usage of data visualizations. Accordingly, knowledge mining from chart images is becoming increasingly important, which can benefit downstream tasks like chart retrieval and knowledge graph completion. However, existing methods for chart knowledge mining mainly focus on converting chart images into raw data and often ignore their visual encodings and semantic meanings, which can result in information loss for many downstream tasks. In this paper, we propose ChartKG, a novel knowledge graph (KG) based representation for chart images, which can model the visual elements in a chart image and semantic relations among them including visual encodings and visual insights in a unified ***, we develop a general framework to convert chart images to the proposed KG-based representation. It integrates a series of image processing techniques to identify visual elements and relations, e.g., CNNs to classify charts, yolov5 and optical character recognition to parse charts, and rule-based methods to construct graphs. We present four cases to illustrate how our knowledge-graph-based representation can model the detailed visual elements and semantic relations in charts, and further demonstrate how our approach can benefit downstream applications such as semantic-aware chart retrieval and chart question answering. We also conduct quantitative evaluations to assess the two fundamental building blocks of our chart-to-KG framework, i.e., object recognition and optical character recognition. The results provide support for the usefulness and effectiveness of ChartKG. © 2024, CC BY.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

OpenViewer: Openness-Aware Multi-View Learning 39

OpenViewer: Openness-Aware Multi-View Learning

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Du, Shide Fang, Zihan Tan, Yanchao Wang, Changwei Wang, Shiping Guo, Wenzhong College of Computer and Data Science Fuzhou University Fuzhou China Fujian Provincial Key Laboratory of Network Computing and Intelligent Information Processing Fuzhou University Fuzhou China Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology Jinan China

ISBN: (纸本)157735897X

Multi-view learning methods leverage multiple data sources to enhance perception by mining correlations across views, typically relying on predefined categories. However, deploying these models in real-world scenarios presents two primary openness challenges. 1) Lack of Interpretability: The integration mechanisms of multi-view data in existing black-box models remain poorly explained;2) Insufficient Generalization: Most models are not adapted to multi-view scenarios involving unknown categories. To address these challenges, we propose OpenViewer, an openness-aware multi-view learning framework with theoretical support. This framework begins with a Pseudo-Unknown Sample Generation Mechanism to efficiently simulate open multi-view environments and previously adapt to potential unknown samples. Subsequently, we introduce an Expression-Enhanced Deep Unfolding Network to intuitively promote interpretability by systematically constructing functional prior-mapping modules and effectively providing a more transparent integration mechanism for multi-view data. Additionally, we establish a Perception-Augmented Open-Set Training Regime to significantly enhance generalization by precisely boosting confidences for known categories and carefully suppressing inappropriate confidences for unknown ones. Experimental results demonstrate that OpenViewer effectively addresses openness challenges while ensuring recognition performance for both known and unknown samples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

An Interpretable Framework for Pulmonary Nodule Malignancy Prediction 11th

An Interpretable Framework for Pulmonary Nodule Malignancy ...

引用

11th International Joint Conference on Rough Sets, IJCRS 2025

作者： Wang, Ruqi Wang, Guoyin Zhou, Yunfei Liu, Qun Key Laboratory of Cyberspace Big Data Intelligent Security Ministry of Education Chongqing University of Posts and Telecommunications Chongqing400065 China Chongqing Key Laboratory of Computational Intelligence Chongqing University of Posts and Telecommunications Chongqing400065 China National Center for Applied Mathematics in Chongqing Chongqing Normal University Chongqing401331 China Department of Neurosurgery The First Affiliated Hospital of Xi’an Jiaotong University Xi’an71004 China

ISBN: (纸本)9783031927409

Achieving the reliable and automatic pulmonary nodule malignancy prediction is a critical step in reducing the workload of physicians and advancing towards intelligent medical treatment. The ‘black-box’ of deep neural networks is a major obstacle in achieving reliable prediction. An interpretable neural network framework for pulmonary nodule malignancy prediction is proposed to ensure reliable predictions. It mainly includes image generation module, mapping network module, reversible network module and reliable classifier module. The latent space constructed based on the image generation module can completely and accurately represent the features of pulmonary nodules. By mapping the input images to the latent space, the accurate representations of pulmonary nodules can be obtained, and then they are mapped to the feature space through the reversible network module. Finally, based on data-driven knowledge in feature space and knowledge-driven medical knowledge, the reliable malignancy prediction is achieved. The experiment shows that our model can accurately extract the features of pulmonary nodules and reliably predict malignancy based on those specific features and medical knowledge. In addition, this model can be used to analyze the difference between data-driven knowledge and knowledge-driven knowledge, which helps enrich and refine medical knowledge while interpreting the basis for prediction. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Robustness May be at Odds with Stability in Adversarial Training based Feature Selection?

Robustness May be at Odds with Stability in Adversarial Trai...

引用

IEEE International Conference on data Mining (ICDM)

作者： Yue Liu Yun Li Jiangsu Key Laboratory of Big Data Security and Intelligent Processing Nanjing University of Posts and Telecommunications Nanjing China

As an important stage in machine learning pipeline, feature selection techniques are mainly used to improve the generalization performance and training efficiency of machine learning model, but few works have focused on the robustness of machine learning models from the perspective of feature selection when dealing with adversarial attacks. In this paper, we propose the adversarial training (AT) based feature selection framework, i.e. AT based feature selection, to improve the robustness of machine learning model built on the feature selection result, which is inspired by using adversarial training to improve the robustness of deep learning model. AT based feature selection framework is the combination of adversarial training with some traditional feature selection algorithm, which can be divided into AT in-processing and AT post-processing feature selection. On the other hand, stability is also a very important property for feature selection. Then we experimentally analyze the relationship between robustness and stability of AT based feature selection, especially theoretically analyze the stability of $\ell_{2}$ regularized AT in-processing feature selection algorithm in two different adversarial training forms. Our experimental results on benchmark data sets show that AT based feature selection algorithm is effective to improve the robustness of machine learning model, however, obtain lower stability than corresponding feature selection model without AT.

关键词： Training Deep learning Machine learning algorithms Pipelines Benchmark testing Feature extraction Stability analysis

来源：评论

学校读者我要写书评

暂无评论

Characterization Of Dim Light Response In DVS Pixel: Discontinuity of Event Triggering Time

Characterization Of Dim Light Response In DVS Pixel: Discont...

引用

IEEE International Conference on Image Processing

作者： Xiao Jiang Fei Zhou College of Electronic and Information Engineering Shenzhen University Shenzhen China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication China Peng Cheng Laboratory Shenzhen China

ISBN: (数字)9798350349399

ISBN: (纸本)9798350349405

Dynamic Vision Sensors (DVS) have recently generated great interest because of the advantages of wide dynamic range and low latency compared with conventional frame-based cameras. However, the complicated behaviors in dim light conditions are still not clear, restricting the applications of DVS. In this paper, we analyze the typical DVS circuit, and find that there exists discontinuity of event triggering time. In dim light conditions, the discontinuity becomes prominent. We point out that the discontinuity depends exclusively on the changing speed of intensity of light. Experimental results on real event data validate the analysis and the existence of discontinuity that reveals the non-first-order behaviors of DVS in dim light conditions.

关键词： Delay effects Image processing Vision sensors Cameras High dynamic range Voltage control Low latency communication

来源：评论

学校读者我要写书评

暂无评论

Dynamical relaxation of a long-range XY chain

arXiv

引用

arXiv 2023年

作者： Huang, Yu-Huan Zou, Yin-Tao Ding, Chengxiang School of Microelectronics & Data Science Anhui University of Technology Maanshan243002 China Anhui Provincial Joint Key Laboratory of Disciplines for Industrial Big Data Analysis and Intelligent Decision Maanshan243002 China

We study the universal real-time relaxation behaviors of a long-range quantum XY chain following a quench. Our research includes both the noncritical and critical quench. In the case of noncritical quench, i.e., neither the initial state nor the postquench Hamiltonian is at a critical point of equilibrium phase transition, a quench to the commensurate phase or incommensurate phase gives a scaling of t−3/2 or t−1/2, respectively, which is the same as the counterpart of the short-range XY model. However, for a quench to the boundary line between the commensurate and incommensurate phases, the scaling law t−µ may be different from the t−3/4 law of the counterpart of the short-range model. More interestingly, the decaying exponent µ may depend on the choice of the parameters of the postquench Hamiltonian because of the different asymptotic behaviors of the energy spectrum. Furthermore, in certain cases, the scaling behavior may be outside the range of predictions made by the stationary phase approximation, because an inflection point emerges in the energy spectrum. For the critical quench, i.e., the initial state or the postquench Hamiltonian is at a critical point of equilibrium phase transition, the aforementioned scaling law t−µ may be changed because of the gap-closing property of the energy spectrum of the critical point. © 2023, CC BY.

关键词： Hamiltonians

来源：评论

学校读者我要写书评

暂无评论

Classic4Children: Adapting Chinese Literary Classics for Children with Large Language Model

arXiv

引用

arXiv 2025年

作者： Chen, Jiali Hei, Xusen Xue, Yuqi Wu, Zihan Xie, Jiayuan Cai, Yi Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China School of Software Engineering South China University of Technology China The Hong Kong Polytechnic University Hong Kong

Chinese literary classics hold significant cultural and educational value, offering deep insights into morality, history, and human nature. These works often include classical Chinese and complex narratives, making them difficult for children to read. To bridge this gap, we introduce a child-friendly literary adaptation (CLA) task to adapt the Chinese literary classic into engaging and accessible text for children. However, recent large language models (LLMs) overlook children’s reading preferences (i.e., vivid character portrayals, concise narrative structures, and appropriate readability), which poses challenges in CLA. In this paper, we propose a method called InstructChild, which augments the LLM with these preferences for adaptation. Specifically, we first obtain the characters’ personalities and narrative structure as additional information for fine-grained instruction tuning. Then, we devise a readability metric as the reward to align the LLM with the children’s reading level. Finally, a lookahead decoding strategy is applied to improve the readability of the generated text during inference. To support the evaluation of CLA task, we construct the Classic4Children dataset, which comprises both the original and child-friendly versions of the Four Great Classical Novels of Chinese literature. Experimental results show that our InstructChild significantly improves automatic and human evaluation performance. Copyright © 2025, The Authors. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Government intervention model based on behavioral heterogeneity for China’s stock market

引用

Financial Innovation 2022年第1期8卷 2569-2587页

作者： Zhong-Qiang Zhou Jie Li Wei Zhang Xiong Xiong School of Big Data Applications and Economics Guizhou University of Finance and EconomicsGuiyang 550025China Guizhou Key Laboratory of Big Data Statistical Analysis Guizhou University of Finance and EconomicsGuiyang 550025China School of Finance Nanjing Audit UniversityNanjing 211815JiangsuChina College of Management and Economics Tianjin UniversityTianjin 300072China China Center for Social Computing and Analytics Tianjin UniversityTianjin 300072China

Active government intervention is a striking characteristic of the Chinese stock *** study develops a behavioral heterogeneous agent model(HAM)comprising fundamentalists,chartists,and stabilizers to investigate investors’dynamic switching mechanisms under government *** model introduces a new player,the stabilizer,into the HAM as a proxy for the *** use the model to examine government programs during the 2015 China stock market crash and find that it can replicate the dynamics of investor sentiment and asset *** addition,our analysis of two simulations,specifically the data-generating processes and shock response analysis,further corroborates the key conclusion that our intervention model not only maintains market stability but also promotes the return of risk asset prices to their fun-damental *** study concludes that government interventions guided by the new HAM can alleviate the dilemma between reducing price volatility and improving price efficiency in future intervention programs.

关键词： Government intervention Excess volatility Behavioral heterogeneity Heterogeneous agent model

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：