检索结果-内蒙古大学图书馆

作者： Lei Liang Jeng-Shyang Pan Yongjun Zhuang Department of Computer Science and Technology Shenzhen Graduate School Harbin Institute of Technology Qihan Research Qihan Technology Co. LTD Fujian Provincial Key Lab of Big Data Mining and Applications Fujian University of Techology

There are two type tone mapping operators for high dynamic range(HDR) image visualization. HDR image mapped by perceptual operators have strong sense of reality, but will lose local details. Empirical operators can maximize local detail information of HDR image, but realism is not strong. A common tone mapping operator suitable for all applications is not available. This paper proposes a novel integrated tone mapping framework which can achieve conversion between empirical operators and perceptual operators. In this framework, the empirical operator is rendered based on improved saliency map, which simulates the visual attention mechanism of the human eye to the natural scene. The results of objective evaluation prove the effectiveness of the proposed solution.

关键词： image An Integrated Tone Mapping for High Dynamic Range Image Visualization HDR Mapping

来源：评论

学校读者我要写书评

暂无评论

Semi-supervised Multi-label Learning with Missing labels via Correlation Information

Semi-supervised Multi-Label Learning with Missing Labels via...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Zexian Xie Peipei Li Jinling Jiang Xindong Wu Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China) Hefei University of Technology School of Computer Science and Information Engineering Hefei University of Technology Hefei Anhui China Knowledge Engineering Research Center Zhejiang Lab Hangzhou Zhejiang China

In multi-label learning, each instance is associated with a set of labels simultaneously. Most existing studies assume that the set of labels for each instance is complete. However, it is generally difficult to obtain all the relevant labels of each instance, and only a partial or even empty set of relevant labels is available, which is called semi-supervised multi-label learning with missing labels. To tackle this problem, we propose a novel framework that considers label correlations and instance correlations to recover the missing labels and utilizes a large amount of unlabeled data simultaneously to improve the classification performance. Specifically, a new supplementary label matrix is firstly obtained by learning the label correlation. Secondly, considering each class label may be decided by some specific characteristics of its own, a label-specific data representation is hence learned for each class label. Thirdly, instance correlations are utilized not only to recover the missing labels, but also to propagate the supervision information from labeled instances to unlabeled ones. In addition, a united objective function is designed to facilitate the above processing and an accelerated proximal gradient method is adopted to solve the optimization problem. Finally, extensive experimental results conducted on several benchmark datasets demonstrate the effectiveness of the proposed method compared to competing ones.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Structure Aware Loss for Deep Unsupervised Industrial Image Registration

Structure Aware Loss for Deep Unsupervised Industrial Image ...

引用

IEEE International Conference on data mining Workshops (ICDM Workshops)

作者： Yong Shi Mengjin Lyu Zhiquan Qi Research Center on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China College of Information Science and Technology University of Nebraska at Omaha Omaha USA School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China School of Economics and Management University of Chinese Academy of Sciences Beijing China

ISBN: (数字)9798331530631

ISBN: (纸本)9798331530648

Image registration is extensively utilized in industrial applications. However, specific challenges inherent to these environments—such as low texture, significant displacement, and poor lighting conditions—complicate the registration process. This paper introduces a structure-aware loss module tailored to the unique characteristics of industrial images. This module promotes the network’s focus on salient regions while emphasizing structural features. Additionally, it is designed as a plug-in component, facilitating integration with any loss function and homography estimation method. We develop an unsupervised registration network and create an industrial dataset to evaluate the module’s effectiveness. A series of experiments demonstrate that our structure-aware module significantly enhances registration performance.

关键词： Deep learning Image registration Conferences Lighting Estimation data mining

来源：评论

学校读者我要写书评

暂无评论

Personalized Financial News Recommendation Algorithm Based on Ontology

引用

Procedia computer science 2015年 55卷 843-851页

作者： Rui Ren Lingling Zhang Limeng Cui Bo Deng Yong Shi School of Management University of Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Research Centre on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing 100190 China School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing 100190 China Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China

To deal with the challenge of information overload, in this paper, we propose a financial news recommendation algorithm which help users find the articles that are interesting to read. To settle the ambiguity problem, a new presented OF-IDF method is employed to represent the unstructured text data in the form of key concepts, synonyms and synsets which are all stored in the domain ontology. For users, the recommendation algorithm build the profiles based on their behaviors to detect the genuine interests and predict current interests automatically and in real time by applying the thinking of relevance feedback. Finally, the experiment conducted on a financial news dataset demonstrates that the proposed algorithm significantly outperforms the performance of a traditional recommender.

关键词： news recommendation algorithm ontology relevence feedback OF-IDF

来源：评论

学校读者我要写书评

暂无评论

D4M: dataset Distillation via Disentangled Diffusion Model

arXiv

引用

arXiv 2024年

作者： Su, Duo Hou, Junjie Gao, Weizhi Tian, Yingjie Tang, Bowen School of Computer Science and Technology UCAS United Kingdom Sino-Danish College UCAS United Kingdom Department of Computer Science NCSU United States School of Economics and Management UCAS United Kingdom Research Center on Fictitious Economy and Data Science CAS China Key Laboratory of Big Data Mining and Knowledge Management CAS China MOE Social Science Laboratory of Digital Economic Forecasts and Policy Simulation UCAS United Kingdom Institute of Computing Technology CAS China

dataset distillation offers a lightweight synthetic dataset for fast network training with promising test accuracy. To imitate the performance of the original dataset, most approaches employ bi-level optimization and the distillation space relies on the matching architecture. Nevertheless, these approaches either suffer significant computational costs on large-scale datasets or experience performance decline on cross-architectures. We advocate for designing an economical dataset distillation framework that is independent of the matching architectures. With empirical observations, we argue that constraining the consistency of the real and synthetic image spaces will enhance the cross-architecture generalization. Motivated by this, we introduce dataset Distillation via Disentangled Diffusion Model (D4M), an efficient framework for dataset distillation. Compared to architecture-dependent methods, D4M employs latent diffusion model to guarantee consistency and incorporates label information into category prototypes. The distilled datasets are versatile, eliminating the need for repeated generation of distinct datasets for various architectures. Through comprehensive experiments, D4M demonstrates superior performance and robust generalization, surpassing the SOTA methods across most aspects. Copyright © 2024, The Authors. All rights reserved.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Ppdf-Fedtmi: A Federated Learning-Based Transport Mode Inference Model with Privacy-Preserving data Fusion

SSRN

引用

SSRN 2023年

作者： Huang, Qihan Zhang, Jing Zeng, Zuanyang He, Ding Ye, Xiucai Chen, Yi School of Computer Science and Mathematics Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Computer Science University of Tsukuba Tsukuba Japan Department of Computer and Information Security Management Fujian Police College Fuzhou China

Mobile Crowd-Sensing (MCS) is a distributed data fusion system that leverages multiple data sources to improve the performance. By incorporating data from numerous individuals, MCS can provide more accurate, comprehensive, and valuable information than any single source could offer alone. As an essential application in MCS, intelligent transportation system deploys a large number of Transport Mode Inference (TMI) models. However, tens of thousands of trajectories are utilized for TMI model training, which will bring the risk of privacy disclosure. Existing solutions cannot address the privacy concerns of trajectories in MCS. In order to achieve the secure distributed architecture for eliminating such concerns in collaboration, a Federated Learning-based Transport Mode Inference Model with Privacy-Preserving data Fusion (PPDF-FedTMI) is proposed in this paper. Firstly, federated learning is utilized in the TMI model to solve the isolated data islands problem of MCS systems. Subsequently, a fuzzy fusion algorithm based on the fuzzy clustering of label information is proposed to train models stably and effectively under non-IID distributed datasets. Furthermore, a privacy-preserving joint training method applying local differential privacy is designed to enhance the gradient privacy, which can prevent attackers from deriving the original through the gradient. Finally, the experimental results demonstrate that PPDF-FedTMI can provide higher accuracy of mode inference and effective privacy-preserving compared to other models. © 2023, The Authors. All rights reserved.

关键词： data fusion

来源：评论

学校读者我要写书评

暂无评论

A knowledge graph constructed for job-related crimes

引用

Procedia computer science 2022年 199卷 540-547页

作者： Yong Shi Wenlu An Jiayu Xue Yi Qu School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 CHINA Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 CHINA Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 CHINA College of Information Science and Technology University of Nebraska at Omaha NE 68182 USA People’s Procuratorate of Shanghai Pudong New District Shanghai 200135 CHINA School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100190 China

Since the 18th National Congress, the Party Central Committee has greatly enhanced its efforts to "fight corruption and advocate honesty". While achieving excellent results, the rising number of crime cases has also brought great challenges to the work of the prosecution organs. At the same time, the traditional relational database has become more and more disadvantageous in dealing with large-scale, unstructured and complex dynamic data, and can no longer meet the actual needs. In order to further improve the efficiency and quality of prosecutors’ work, alleviate the problem of "too many cases and too few people", and promote the construction of "smart prosecution", this paper uses knowledge extraction and other methods to identify the key entities and relationships in the job-related crimes indictments of the Shanghai Pudong New District Procuratorate. Then using Neo4j graph database to store the extracted information and build a knowledge graph for job-related crime cases, which realizes the visualization and deep mining of job-related crime, providing a new way and tool for prosecution work as well as prosecution personnel to analyze and handle job-related crime cases.

关键词： big data in prosecution knowledge graph job-related crimes Neo4j

来源：评论

学校读者我要写书评

暂无评论

DenoiseRep: Denoising Model for Representation Learning

arXiv

引用

arXiv 2024年

作者： Xu, Zhengrui Wang, Guan'an Huang, Xiaowen Sang, Jitao School of Computer Science and Technology Beijing Jiaotong University China Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China

The denoising model has been proven a powerful generative model but has little exploration of discriminative tasks. Representation learning is important in discriminative tasks, which is defined as "learning representations (or features) of the data that make it easier to extract useful information when building classifiers or other predictors" [4]. In this paper, we propose a novel Denoising Model for Representation Learning (DenoiseRep) to improve feature discrimination with joint feature extraction and denoising. DenoiseRep views each embedding layer in a backbone as a denoising layer, processing the cascaded embedding layers as if we are recursively denoise features step-by-step. This unifies the frameworks of feature extraction and denoising, where the former progressively embeds features from low-level to high-level, and the latter recursively denoises features step-by-step. After that, DenoiseRep fus es the parameters of feature extraction and denoising layers, and theoretically demonstrates its equivalence before and after the fusion, thus making feature denoising computation-free. DenoiseRep is a label-free algorithm that incrementally improves features but also complementary to the label if available. Experimental results on various discriminative vision tasks, including re-identification (Market-1501, DukeMTMC-reID, MSMT17, CUHK-03, vehicleID), image classification (ImageNet, UB200, Oxford-Pet, Flowers), object detection (COCO), image segmentation (ADE20K) show stability and impressive improvements. We also validate its effectiveness on the CNN (ResNet) and Transformer (ViT, Swin, Vmamda) architectures. Code is available at https://***/wangguanan/DenoiseRep. © 2024, CC BY.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

Towards Robust Recommendation: A Review and an Adversarial Robustness Evaluation Library

arXiv

引用

arXiv 2024年

作者： Cheng, Lei Huang, Xiaowen Sang, Jitao Yu, Jian The School of Computer Science and Technology Beijing Jiaotong University China The Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University China The Key Laboratory of Big Data & Artificial Intelligence in Transportation Beijing Jiaotong University Ministry of Education China

Recently, recommender system has achieved significant success. However, due to the openness of recommender systems, they remain vulnerable to malicious attacks. Additionally, natural noise in training data and issues such as data sparsity can also degrade the performance of recommender systems. Therefore, enhancing the robustness of recommender systems has become an increasingly important research topic. In this survey, we provide a comprehensive overview of the robustness of recommender systems. Based on our investigation, we categorize the robustness of recommender systems into adversarial robustness and non-adversarial robustness. In the adversarial robustness, we introduce the fundamental principles and classical methods of recommender system adversarial attacks and defenses. In the non-adversarial robustness, we analyze non-adversarial robustness from the perspectives of data sparsity, natural noise, and data imbalance. Additionally, we summarize commonly used datasets and evaluation metrics for evaluating the robustness of recommender systems. Finally, we also discuss the current challenges in the field of recommender system robustness and potential future research directions. Additionally, to facilitate fair and efficient evaluation of attack and defense methods in adversarial robustness, we propose an adversarial robustness evaluation library–ShillingREC, and we conduct evaluations of basic attack models and recommendation models. ShillingREC project is released at https://***/chengleileilei/ShillingREC. Copyright © 2024, The Authors. All rights reserved.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Overview of Essential Components in deep learning reference-based super resolution methods

引用

Procedia computer science 2024年 242卷 1243-1248页

作者： Jiayu Xue Junjie Liu Yong Shi School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 101408 China Research Center on Fictitious Economy & Data Science Chinese Academy of Sciences Beijing 100190 China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing 100190 China Sino-Danish College University of Chinese Academy of Sciences Beijing 100049 China School of Economics and Management University of Chinese Academy of Sciences Beijing 100190 China College of Information Science and Technology University of Nebraska at Omaha Omaha NE 68182 USA

Reference-based super resolution (RefSR) aims to recover the lost details in a low-resolution image and generate a high-resolution result, guided by a high-resolution reference image with similar contents or textures. In contrast to the traditional single-image super-resolution, which focuses on the intrinsic properties of the single low-resolution image, the challenge of RefSR lies in matching and aggregating highly-related but misaligned reference images with low-resolution images. Several effective but complex designs have been proposed to address this challenge, which poses difficulties in implementing RefSR in real-world applications. In order to better understand the working mechanism of RefSR and design a more efficient and lightweight architecture, we provide a review about the essential components of the existing deep learning-based RefSR. We decompose and classify the common pipeline into four submodules according to the functionalities. Then, we summarize and describe the implementation details of the commonly-adopted approaches in each submodule. Finally, we discuss the challenges and promising research directions.

关键词： Reference-based super resolution Deep learning Feature matching Feature alignment

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：