检索结果-内蒙古大学图书馆

IEEE WIC ACM International Conference on Web Intelligence (WI)

作者： Han Yu Zhiqi Shen Chunyan Miao Bo An School of Computer Engineering Nanyang Technological University Singapore The Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China

Crowd sourcing (CS) systems offer a new way for businesses and individuals to leverage on the power of mass collaboration to accomplish complex tasks in a divide-and-conquer manner. In existing CS systems, no facility has been provided for analyzing the trustworthiness of workers and providing decision support for allocating tasks to workers, which leads to high dependency of the quality of work on the behavior of workers in CS systems as shown in this paper. To address this problem, trust management mechanisms are urgently needed. Traditional trust management techniques are focused on identifying the most trustworthy service providers (SPs) as accurately as possible. Little thoughts were given to the question of how to utilize these SPs due to two common assumptions: 1) an SP can serve an unlimited number of requests in one time unit, and 2) a service consumer (SC) only needs to select one SP for interaction to complete a task. However, in CS systems, these two assumptions are no longer valid. Thus, existing models cannot be directly used for trust management in CS systems. This paper takes the first step towards a systematic investigation of trust management in CS systems by extending existing trust management models for CS trust management and conducting extensive experiments to study and analyze the performance of various trust management models in crowd sourcing. In this paper, the following key contributions are made. We 1) propose extensions to existing trust management approaches to enable them to operate in CS systems, 2) design a simulation test-bed based on the system characteristics of Amazon's Mechanical Turk (AMT) to make evaluation close to practical CS systems, 3) discuss the effect of incorporating trust management into CS system on the overall social welfare, and 4) identify the challenges and opportunities for future trust management research in CS systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Combining Method for Tumors Detection from Near-infrared Breast Imaging

A Combining Method for Tumors Detection from Near-infrared B...

引用

Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)

作者： Zhicheng Wang Jian Liu Jinwen Tian Zeping Xie State Education Commission Key Laboratory for Image Processing and Intelligent Control Institute for Pattern Recognition and Artificial Intelligence Huazhong Univ. of Sci. & Tech. Wuhan 430074 China Key Lab. for Image Process. & Intelligent Control State Educ. Comm. School of Life Science & Technology Huazhong University of Science and Technology Wuhan China

This paper introduces the new qualitative and quantitative methods, which can diagnose breast tumors. Qualitative methods include blood vessel display inside and outside of pathological changes part of breast, display of equivalent pixel curves at the part of pathological changes and display of breast tumor image edge. Accordingly, three feature extraction operators are proposed, i.e. the combination operators of anisotropic gradient and smoothing operator, an improved Sobel operator and an edge sharpening operator. Furthermore, quantitative diagnostic approaches are discussed based on blood and oxygen contents according to abundant clinical data and pathological mechanism of breast tumors. The results of clinic show that the methods of combining qualitative and quantitative diagnose are effective for breast tumor images, especially for early and potential breast cancer

关键词： Breast tumors Displays Pathology Blood vessels Biomedical imaging Pixel Feature extraction Anisotropic magnetoresistance Smoothing methods Breast cancer

来源：评论

学校读者我要写书评

暂无评论

Rethinking Super-Resolution as Text-Guided Details Generation

arXiv

引用

arXiv 2022年

作者： Ma, Chenxi Yan, Bo Lin, Qing Tan, Weimin Chen, Siming School of Computer Science Shanghai Key Laboratory of Intelligent Information Processing Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China School of Data Science Fudan University China

Deep neural networks have greatly promoted the performance of single image super-resolution (SISR). Conventional methods still resort to restoring the single high-resolution (HR) solution only based on the input of image modality. However, the image-level information is insufficient to predict adequate details and photo-realistic visual quality facing large upscaling factors (×8, ×16). In this paper, we propose a new perspective that regards the SISR as a semantic image detail enhancement problem to generate semantically reasonable HR image that are faithful to the ground truth. To enhance the semantic accuracy and the visual quality of the reconstructed image, we explore the multi-modal fusion learning in SISR by proposing a Text-Guided Super-Resolution (TGSR) framework, which can effectively utilize the information from the text and image modalities. Different from existing methods, the proposed TGSR could generate HR image details that match the text descriptions through a coarse-to-fine process. Extensive experiments and ablation studies demonstrate the effect of the TGSR, which exploits the text reference to recover realistic images. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Large-scale Multiobjective Optimization via Problem Decomposition and Reformulation

Large-scale Multiobjective Optimization via Problem Decompos...

引用

Congress on Evolutionary Computation

作者： Lianghao Li Cheng He Ran Cheng Linqiang Pan Key Laboratory of Image Information Processing and Intelligent Control of Education Ministry of China School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan China Guangdong Provincial Key Laboratory of Brain-inspired Intelligent Computation Southern University of Science and Technology Shenzhen China

Large-scale multiobjective optimization problems (LSMOPs) are challenging for existing approaches due to the complexity of objective functions and the massive volume of decision space. Some large-scale multiobjective evolutionary algorithms (LSMOEAs) have recently been proposed, which have shown their effectiveness in solving some benchmarks and real-world applications. They merely focus on handling the massive volume of decision space and ignore the complexity of LSMOPs in terms of objective functions. The complexity issue is also important since the complexity grows along with the increment in the number of decision variables. Our previous study proposed a framework to accelerate evolutionary large-scale multiobjective optimization via problem reformulation for handling large-scale decision variables. Here, we investigate the effectiveness of LSMOF combined with decomposition-based MOEA (MOEA/D), aiming to handle the complexity of LSMOPs in both the decision and objective spaces. Specifically, MOEA/D is embedded in LSMOF via two different strategies, and the proposed algorithm is tested on various benchmark LSMOPs. Experimental results indicate the encouraging performance improvement benefited from the solution of the complexity issue in large-scale multiobjective optimization.

关键词： Sociology Evolutionary computation Benchmark testing Linear programming Complexity theory Statistics Optimization

来源：评论

学校读者我要写书评

暂无评论

ForensicsForest Family: A Series of Multi-scale Hierarchical Cascade Forests for Detecting GAN-generated Faces

arXiv

引用

arXiv 2023年

作者： Lu, Jiucui Zhou, Jiaran Dong, Junyu Li, Bin Lyu, Siwei Li, Yuezun The College of Computer Science and Technology Ocean University of China Qingdao China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen Key Laboratory of Media Security Shenzhen University Shenzhen518060 China The University at Buffalo SUNY United States

The prominent progress in generative models has significantly improved the authenticity of generated faces, raising serious concerns in society. To combat GAN-generated faces, many countermeasures based on Convolutional Neural Networks (CNNs) have been spawned due to their strong learning capabilities. In this paper, we rethink this problem and explore a new approach based on forest models instead of CNNs. Concretely, we describe a simple and effective forest-based method set, termed ForensicsForest Family, to detect GAN-generate faces. The ForensicsForest family is composed of three variants: ForensicsForest, Hybrid ForensicsForest and Divide-and-Conquer ForensicsForest. ForenscisForest is a novel Multi-scale Hierarchical Cascade Forest that takes appearance, frequency, and biological features as input, hierarchically cascades different levels of features for authenticity prediction, and employs a multi-scale ensemble scheme to consider different levels of information comprehensively for further performance improvement. Building upon ForensicsForest, we create Hybrid ForensicsForest, an extended version that integrates the CNN layers into models, to further enhance the efficacy of augmented features. Furthermore, to reduce memory usage during training, we introduce Divide- and-Conquer ForensicsForest, which can construct a forest model using only a portion of training samplings. In the training stage, we train several candidate forest models using the subsets of training samples. Then, a ForensicsForest is assembled by selecting suitable components from these candidate forest models. Our method is validated on state-of-the-art GAN-generated face datasets and compared with several CNN models, demonstrating the surprising effectiveness of our method in detecting GAN-generated faces. Copyright © 2023, The Authors. All rights reserved.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

DriveEditor: A Unified 3D information-Guided Framework for Controllable Object Editing in Driving Scenes

arXiv

引用

arXiv 2024年

作者： Liang, Yiyuan Yan, Zhiying Chen, Liqun Zhou, Jiahuan Yan, Luxin Zhong, Sheng Zou, Xu Huazhong University of Science and Technology China National Key Laboratory of Multispectral Information Intelligent Processing Technology China Wangxuan Institute of Computer Technology Peking University China

Vision-centric autonomous driving systems require diverse data for robust training and evaluation, which can be augmented by manipulating object positions and appearances within existing scene captures. While recent advancements in diffusion models have shown promise in video editing, their application to object manipulation in driving scenarios remains challenging due to imprecise positional control and difficulties in preserving high-fidelity object appearances. To address these challenges in position and appearance control, we introduce DriveEditor, a diffusion-based framework for object editing in driving videos. DriveEditor offers a unified framework for comprehensive object editing operations, including repositioning, replacement, deletion, and insertion. These diverse manipulations are all achieved through a shared set of varying inputs, processed by identical position control and appearance maintenance modules. The position control module projects the given 3D bounding box while preserving depth information and hierarchically injects it into the diffusion process, enabling precise control over object position and orientation. The appearance maintenance module preserves consistent attributes with a single reference image by employing a three-tiered approach: low-level detail preservation, high-level semantic maintenance, and the integration of 3D priors from a novel view synthesis model. Extensive qualitative and quantitative evaluations on the nuScenes dataset demonstrate DriveEditor’s exceptional fidelity and controllability in generating diverse driving scene edits, as well as its remarkable ability to facilitate downstream tasks. Copyright © 2024, 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

Dynamical Decomposition and Selection Based Evolutionary Algorithm for Many-Objective Evolutionary Optimization

SSRN

引用

SSRN 2022年

作者： Bao, Qian Wang, Maocai Dai, Guangming Chen, Xiaoyu Song, Zhiming School of Computer China University of Geosciences Wuhan430074 China Hubei Key Laboratory of Intelligent Geo-Information Processing China University of Geosciences Wuhan430074 China

Decomposition-based many-objective evolutionary algorithms decompose the objective space into multiple subregions, with the help of a set of predefined reference vectors. As subregions are fixed in every generation, their performance is highly affected by the Pareto fronts (PFs). The main issue is that the predefined reference vectors may not intersect with irregular PFs. To address this problem, this paper proposes a dynamical decomposition and selection strategy (DDS). In DDS, the predefined reference vectors are replaced by solutions themselves, which endeavors to guide the population to automatically adapt to the PFs. In the dynamical decomposition strategy, the population is firstly divided into two subpopulations according to the similarity between the selected individuals and the unselected individuals. The subpopulation with low similarity is used as the candidate solution to improve the diversity of population. Then, a promising solution will be selected as candidate set according to the dynamical selection strategy. In the early stage of evolution, a higher convergence pressure is addressed to push the population toward the PF in dynamical selection strategy. However, at the later stage of evolution, a wider diversity of the candidate solutions is concentrated. The process of dynamical decomposition and selection strategy is repeated until the termination condition is met. The proposed algorithm is compared with the state-of-the-art many-objective optimization algorithms on a number of benchmark problems with 5 to 15 objectives in evolutionary computation. The experimental results show a better performance than other algorithms in most test instances, and less sensitivity to irregularity PFs. © 2022, The Authors. All rights reserved.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

UNRAVELING THE ENIGMA OF DOUBLE DESCENT: AN IN-DEPTH ANALYSIS THROUGH THE LENS OF LEARNED FEATURE SPACE

arXiv

引用

arXiv 2023年

作者： Gu, Yufei Zheng, Xiaoqing Aste, Tomaso School of Computer Science Fudan University China Shanghai Key Laboratory of Intelligent Information Processing China Department of Computer Science University College London United Kingdom

Double descent presents a counter-intuitive aspect within the machine learning domain, and researchers have observed its manifestation in various models and tasks. While some theoretical explanations have been proposed for this phenomenon in specific contexts, an accepted theory for its occurring mechanism in deep learning remains yet to be established. In this study, we revisit the phenomenon of double descent and demonstrate that the presence of noisy data strongly influences its occurrence. By comprehensively analysing the feature space of learned representations, we unveil that double descent arises in imperfect models trained with noisy data. We argue that while small and intermediate models before the interpolation threshold follow the traditional bias-variance trade-off, over-parameterized models interpolate noisy samples among robust data thus acquiring the capability to separate the information from the noise. The source code is available at https://***/Yufei-Gu-451/double_descent_***. Copyright © 2023, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Parallel Factorization Machine Recommended Algorithm Based on MapReduce

Parallel Factorization Machine Recommended Algorithm Based o...

引用

International Conference on Semantics, Knowledge and Grid (SKG)

作者： Hanxiao Sun Wenjie Wang Zhongzhi Shi School of Computer and Control Engineering University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781479967162

Factorization Machines [1, 2] is a new factorization model that can combine the merits of SVM model with matrix factorization models. It can model all the interactive actions using factorized parameters. So it could mimic most other matrix factorization models by feature engineering. Due to the superior flexible, Factorization Machines has already been widely used in many recommended algorithm competitions and practical online recommended system. But, because of the prevalence of large dataset, there is a need to improve the scalability of computation in factorization machines model. In this paper, we propose a parallel algorithm can be used on Factorization Machines model. The experimental results show that the proposed algorithm has good speed-up and scalability on big dataset.

关键词： Frequency modulation Computational modeling Data models Computers Parallel algorithms Stochastic processes Algorithm design and analysis

来源：评论

学校读者我要写书评

暂无评论

SVM-based Hybrid pattern for New Word Discovery

SVM-based Hybrid Pattern for New Word Discovery

引用

IEEE International Conference on Natural Language processing and Knowledge Engineering (NLP-KE)

作者： Hui Yang Yue-jie Zhang Tao Zhang Department of Computer Science & Engineering Shanghai Key Laboratory of Intelligent Information processing Fudan University Shanghai China School of Information Management and Engineering Shanghai University of Finance and Economics Shanghai China

New words bring more challenges into Chinese word segmentation. This paper presents a SVM-based hybrid pattern for new word discovery, trying to integrate the advantages of the statistics-based method and the rule-based method to improve the performance of the new word discovery. In the statistics module, new words discovery is defined as a binary classification problem, in which we considered the previous new word features and proposed context information and affix information as new features, as well as constraints, which reveal the relationships among the new word candidates. Finally, some rules are introduced aimed to improve the performance. In the experiment, some new words are simulated by revising the dictionary of a Natural Language processing (NLP) system. The results show that these features and constraints are useful for new word discovery, and the F-measure is 64.62% which is 7% higher than the baseline.

关键词： Statistics Dictionaries Probability Frequency Computer science Laboratories information processing information management Finance Support vector machines

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：