检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Luo, Anwei Cai, Rizhao Kong, Chenqi Ju, Yakun Kang, Xiangui Huang, Jiwu Kot, Alex C. The School of Information Technology Jiangxi University of Finance and Economics Nanchang330013 China The School of Computer Science and Engineering Sun Yat-Sen University Guangzhou510006 China Lab. School of Electrical and Electronic Engineering Nanyang Technology University Singapore The Guangdong Key Laboratory of Intelligent Information Processing National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China The China-Singapore International Joint Research Institute Singapore

With the rapid progress of generative models, the current challenge in face forgery detection is how to effectively detect realistic manipulated faces from different unseen domains. Though previous studies show that pre-trained Vision Transformer (ViT) based models can achieve some promising results after fully fine-tuning on the Deepfake dataset, their generalization performances are still unsatisfactory. One possible reason is that fully fine-tuned ViT-based models may disrupt the pre-trained features [1], [2] and overfit to some data-specific patterns [3]. To alleviate this issue, we present a Forgery-aware Adaptive Vision Transformer (FA-ViT) under the adaptive learning paradigm, where the parameters in the pre-trained ViT are kept fixed while the designed adaptive modules are optimized to capture forgery features. Specifically, a global adaptive module is designed to model long-range interactions among input tokens, which takes advantage of self-attention mechanism to mine global forgery clues. To further explore essential local forgery clues, a local adaptive module is proposed to expose local inconsistencies by enhancing the local contextual association. In addition, we introduce a fine-grained adaptive learning module that emphasizes the common compact representation of genuine faces through relationship learning in fine-grained pairs, driving these proposed adaptive modules to be aware of fine-grained forgery-aware information. Extensive experiments demonstrate that our FA-ViT achieves state-of-the-arts results in the cross-dataset evaluation, and enhances the robustness against unseen perturbations. Particularly, FA-ViT achieves 93.83% and 78.32% AUC scores on Celeb-DF and DFDC datasets in the cross-dataset evaluation. The code and trained model have been released at: https://***/LoveSiameseCat/FAViT. Copyright © 2023, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Graph convolutional network for visual question answering based on fine-grained question representation 5

Graph convolutional network for visual question answering ba...

引用

5th IEEE International Conference on data Science in Cyberspace, DSC 2020

作者： Hu, Ze Wei, Jielong Huang, Qingbao Liang, Hanyu Zhang, Xingmao Liu, Qingguang Guangxi University School of Electrical Engineering Nanning Guangxi China School of Software Engineering South China University of Technology Guangzhou Guangdong China Key Laboratory of Big Data and Intelligent Robot South China University of Technology Ministry of Education China Guangxi Arts University General Education Department Nanning Guangxi China

ISBN: (数字)9781728195582

ISBN: (纸本)9781728195582

Visual Question Answering (VQA) requires a fine-grained and simultaneous understanding of both the visual content of images and the textual content of questions. Recent research works mainly focus on the bilinear fusion methods and attention mechanism methods to explore the global features and local features, respectively. When an image exists multiple objects, the fine-grained question features can effectively identify the relationship between objects in an image. Therefore we propose a graph convolutional network based on fine-grained question representation (FQ-GCN). The object relation graph is firstly constructed. The fine-grained question features are used to explore the relations between objects in an image and prune unrelated edges between object nodes. Graph convolutional network is used to aggregate all neighborhood information of each object in an object graph. Experiments on the VQA 2.0 dataset show that the performance of our FQ-GCN model improves 2% ~ 3% than the classical methods. © 2020 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Over-sampling algorithm for imbalanced data classification

引用

Journal of Systems Engineering and Electronics 2019年第6期30卷 1182-1191页

作者： XU Xiaolong CHEN Wen SUN Yanfei Jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Big Data Research at Yancheng Nanjing University of Posts and TelecommunicationsYancheng 224000China Office of Scientific R&D Nanjing University of Posts and TelecommunicationsNanjing 210023China

For imbalanced datasets, the focus of classification is to identify samples of the minority class. The performance of current data mining algorithms is not good enough for processing imbalanced datasets. The synthetic minority over-sampling technique(SMOTE) is specifically designed for learning from imbalanced datasets, generating synthetic minority class examples by interpolating between minority class examples nearby. However, the SMOTE encounters the overgeneralization problem. The densitybased spatial clustering of applications with noise(DBSCAN) is not rigorous when dealing with the samples near the *** optimize the DBSCAN algorithm for this problem to make clustering more reasonable. This paper integrates the optimized DBSCAN and SMOTE, and proposes a density-based synthetic minority over-sampling technique(DSMOTE). First, the optimized DBSCAN is used to divide the samples of the minority class into three groups, including core samples, borderline samples and noise samples, and then the noise samples of minority class is removed to synthesize more effective samples. In order to make full use of the information of core samples and borderline samples,different strategies are used to over-sample core samples and borderline samples. Experiments show that DSMOTE can achieve better results compared with SMOTE and Borderline-SMOTE in terms of precision, recall and F-value.

关键词： imbalanced data density-based spatial clustering of applications with noise(DBSCAN) synthetic minority over sampling technique(SMOTE) over-sampling.

来源：评论

学校读者我要写书评

暂无评论

A study on orderings based on fuzzy quasi-order relations

Research Square

引用

Research Square 2021年

作者： Chai, Zhonglin College of Sciences China Jiliang University Hangzhou310018 China Key Laboratory of Intelligent Manufacturing Quality Big Data Tracing and Analysis of Zhejiang Province China Jiliang University Hangzhou310018 China

This paper further studies orderings based on fuzzy quasi-order relations using fuzzy graph. Firstly, a fuzzy relation on a finite set is represented equivalently by a fuzzy graph. Using the graph, some new results on fuzzy relations are derived. In ranking those alternatives, we usually obtain a quasi-order relation, which often has inconsistencies, so it cannot be used for orderings directly. We need to remake it into a reasonable partial order relation for orderings. This paper studies these inconsistencies, and divides them into two types: framework inconsistencies and degree inconsistencies. For the former, a reasonable and feasible method is presented to eliminate them. To eliminate the latter, the concept of complete partial order relation is presented, which is more suitable than partial order relation to rank the alternatives. A method to obtain a reasonable complete partial order relation for a quasi-order relation is given also. An example is given as well to illustrate these discussions. Lastly, the paper discusses the connection between quasi-order relations and preference relations for orderings and some other related problems. © 2021, CC BY.

关键词： Fuzzy sets

来源：评论

学校读者我要写书评

暂无评论

Prediction of Angle Deflection of Smart Car Based on Neural Network

Prediction of Angle Deflection of Smart Car Based on Neural ...

引用

第33届中国控制与决策会议

作者： Quanjin Huang Jiandong Li Chunyang Mu Xing Ma The Key Laboratory of Intelligent Information and Big Data Processing of Ningxia Province North Minzu University School of Electrical and Information Engineering North Minzu University College of Mechatronic Engineering North Minzu University

This paper designs a model based on convolutional neural network to simulate the deflection angle of a driverless car while *** model is first trained by extracting the features in the images of the training set,and then the simulated car sends the images taken by the on-board camera into the trained model,so that the driverless car can predict the direction and angle according to the real-time road *** testing,the model's judgment loss on the input road condition images during the training process is reduced to 0.3,which enables the driverless car to predict the direction in which it should deflect based on the actual road conditions in the virtual environment.

关键词： Driverless Driving Convolutional Neural Network Angle Prediction

来源：评论

学校读者我要写书评

暂无评论

Graph Regularized Nonnegative Latent Factor Analysis Model for Temporal Link Prediction in Cryptocurrency Transaction Networks

arXiv

引用

arXiv 2022年

作者： Zhou, Yue Liu, Zhigang Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The Chongqing School University of Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

With the development of blockchain technology, the cryptocurrency based on blockchain technology is becoming more and more popular. This gave birth to a huge cryptocurrency transaction network has received widespread attention. Link prediction learning structure of network is helpful to understand the mechanism of network, so it is also widely studied in cryptocurrency network. However, the dynamics of cryptocurrency transaction networks have been neglected in the past researches. We use graph regularized method to link past transaction records with future transactions. Based on this, we propose a single latent factor-dependent, non-negative, multiplicative and graph regularized-incorporated update (SLF-NMGRU) algorithm and further propose graph regularized nonnegative latent factor analysis (GrNLFA) model. Finally, experiments on a real cryptocurrency transaction network show that the proposed method improves both the accuracy and the computational efficiency. © 2022, CC BY-NC-ND.

关键词： Multivariant analysis

来源：评论

学校读者我要写书评

暂无评论

Size-Invariance Matters: Rethinking Metrics and Losses for Imbalanced Multi-object Salient Object Detection

arXiv

引用

arXiv 2024年

作者： Li, Feiran Xu, Qianqian Bao, Shilong Yang, Zhiyong Cong, Runmin Cao, Xiaochun Huang, Qingming Institute of Information Engineering Chinese Academy of Sciences Beijing China School of Cyber Security University of Chinese Academy of Sciences Beijing China Key Laboratory of Intelligent Information Processing Institute of Computing Technology Chinese Academy of Sciences Beijing China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing China Institute of Information Science Beijing Jiaotong University Beijing China School of Control Science and Engineering Shandong University Jinan China Key Laboratory of Machine Intelligence and System Control Ministry of Education Jinan China School of Cyber Science and Tech. Sun Yat-Sen University Shenzhen Campus China Key Laboratory of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing China

This paper explores the size-invariance of evaluation metrics in Salient Object Detection (SOD), especially when multiple targets of diverse sizes co-exist in the same image. We observe that current metrics are size-sensitive, where larger objects are focused, and smaller ones tend to be ignored. We argue that the evaluation should be size-invariant because bias based on size is unjustified without additional semantic information. In pursuit of this, we propose a generic approach that evaluates each salient object separately and then combines the results, effectively alleviating the imbalance. We further develop an optimization framework tailored to this goal, achieving considerable improvements in detecting objects of different sizes. Theoretically, we provide evidence supporting the validity of our new metrics and present the generalization analysis of SOD. Extensive experiments demonstrate the effectiveness of our method. The code is available at https://***/Ferry-Li/SI-SOD. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on the Zebra Crossing Behavior of Mixed Bicycles and Pedestrians

SSRN

引用

SSRN 2022年

作者： Ma, Jian Wang, Qiao Chen, Juan Jiang, Rui Song, Weiguo Li, Ruoyu Lian, Liping School of Transportation and Logistics National Engineering Laboratory of Integrated Transportation Big Data Application Technology National United Engineering Laboratory of Integrated and Intelligent Transportation Southwest Jiaotong University Chengdu610031 China Faculty of Geosciences and Environmental Engineering Southwest Jiaotong University Chengdu610031 China Key Laboratory of Transport Industry of Big Data Application Technologies for Comprehensive Transport Ministry of Transport Beijing Jiaotong University Beijing100044 China State Key Laboratory of Fire Science University of Science and Technology of China Hefei230027 China School of Urban Planning and Design Peking University Shenzhen Graduate School School of Architectural Engineering Shenzhen Polytechnic Shenzhen518055 China

Slow transportation mode, consisting of walking and cycling, plays an important role in urban traffic system. Based on the fact that bicycles and pedestrians often share the common road facility, we conducted bicycle-pedestrian mixed flow experiments to investigate the interaction effect among individuals in a 10 m-long, 3 m-wide passageway, mimicking the zebra crossing area. The goal is to explore the influence of bicycles proportion ( p ) on traffic efficiency and investigate the spatial distribution of agents in the mixed flow. Our analyses showed that the increase of bicycle proportion results in longer passing time and less travel time because of large personal space requirements of cyclists. When the bicycle proportion is small or large, the majority pedestrians (bicycles) were divided into several parts by minor bicycles (pedestrians) along the motion direction. We also recorded the following- and lateral- distance between two nearest individuals to calculate the theoretical formula of the passing time for unidirectional bicycle-pedestrian mixed flow based on the existing formula. Comparing the passing time between numerical calculation and experimental data, the effect coefficients for bicycle and pedestrian were obtained. Focusing on the overtaking bicycles, the through gap, lateral and headway distance that decide the overtaking behavior were analyzed. These findings are the first step toward the development of bicycle-pedestrian mixed flow on zebra crossing, which is contribute to provide practical implications for the planning and design of bicycle and pedestrian shared infrastructures. © 2022, The Authors. All rights reserved.

关键词： Travel time

来源：评论

学校读者我要写书评

暂无评论

Adaptive decoupled strategy for robust and efficient low-rank matrix decomposition

引用

Neurocomputing 2025年 649卷

作者： Min Gan Peng Xue Fan Zhang Xiang-Xiang Su Xin Lin Guang-Yong Chen College of Computer and Data Science Fuzhou University Fuzhou 350116 China Key Laboratory of Intelligent Metro of Universities in Fujian Fuzhou University Fuzhou 350116 China Engineering Research Center of Big Data Intelligence Ministry of Educatio Fuzhou 350116 China Inspur Zhuoshu Big Data Industry Development Co. Ltd. Wuxi 610101 China

Low-rank matrix decomposition with missing values is vital in computer vision and pattern recognition, yet it presents significant challenges. This problem can be viewed as a separable nonlinear optimization, but traditional methods often fail to account for the coupling between parameters and the impact of solution properties on visual reconstruction. We observe that such separable nonlinear problems frequently encounters narrow ravines filled with sharp minima. Classic alternating optimization methods, the Wiberg algorithm and its variants tend to linger in these regions, converging to sharp minima, thereby slowing convergence and degrading reconstruction quality. This promotes us to introduce the Adaptive Decoupled Variable Projection algorithm (ADVP), which can adaptively handle the coupling of parameters, significantly accelerate the convergence rate, and dynamically adjust the parameter search subspace, helping algorithms avoid these ravines towards flatter local minima. These flat minima exhibit robustness against missing data, noise, and outliers, enhancing the quality of visual reconstruction. Extensive experiments on synthetic and real datasets have validated the efficiency of ADVP and its superior performance in visual reconstruction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Experimental Study on the Zebra Crossing Behavior of Mixed Bicycles and Pedestrians

SSRN

引用

SSRN 2022年

关键词： Travel time

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：