检索结果-内蒙古大学图书馆

arXiv 2020年

作者： Hong, Xin Lan, Yanyan Pang, Liang Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China Institute for AI Industry Research Tsinghua University Beijing China

This paper defines a new visual reasoning paradigm by introducing an important factor, i.e. transformation. The motivation comes from the fact that most existing visual reasoning tasks, such as CLEVR in VQA, are solely defined to test how well the machine understands the concepts and relations within static settings, like one image. We argue that this kind of state driven visual reasoning approach has limitations in reflecting whether the machine has the ability to infer the dynamics between different states, which has been shown as important as state-level reasoning for human cognition in Piaget’s theory. To tackle this problem, we propose a novel transformation driven visual reasoning task. Given both the initial and final states, the target is to infer the corresponding single-step or multi-step transformation, represented as a triplet (object, attribute, value) or a sequence of triplets, respectively. Following this definition, a new dataset namely TRANCE is constructed on the basis of CLEVR, including three levels of settings, i.e. Basic (single-step transformation), Event (multi-step transformation), and View (multi-step transformation with variant views). Experimental results show that the state-of-the-art visual reasoning models perform well on Basic, but are still far from human-level intelligence on Event and View. We believe the proposed new paradigm will boost the development of machine visual reasoning. More advanced methods and real data need to be investigated in this direction. The resource of TVR is available at https://***/TVR. Copyright © 2020, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Video Anomaly Detection Using Open data Filter and Domain Adaptation

Video Anomaly Detection Using Open Data Filter and Domain Ad...

引用

IEEE Visual Communications and Image Processing (VCIP)

作者： Chen Zhang Guorong Li Li Su Weigang Zhang Qingming Huang School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Harbin Institute of Technology Weihai China Key Lab of Intelligent Information Processing ICT CAS Beijing China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

Video anomaly detection is a very challenging task because of the rarity, openness, and the definition of the anomalies. Researchers pay more attention to the characteristics of anomalies and have proposed a variety of anomaly detection models. However, most existing methods only use normal events to construct anomaly detection models and ignore the diversity and openness of normal events. Actually, because real-world video data often have an open-ended distribution, some normal patterns hardly ever appeared in the training data. In addition, analogous to human experience in identifying anomalies, rare abnormal events can play a certain role in the detection of similar abnormal events in the dataset. Therefore, assuming that a small number of abnormal events are known, we propose a novel supervised anomaly detection model which explicitly detects open normal events and open abnormal events in the dataset and treats open data and seen data with different classifiers. First, we use the training video to train an imbalanced classifier as the seen data classifier. Then, during the testing phase, an open data filter module isused to divide the test data into seen data and open data. Finally, we directly use the seen data classifier to generate anomaly scores for the seen test data. For the open test data, we adopt a domain adaptation method to reduce the distribution difference between it and the training data and train a new classifier to score for it. Extensive experimental results prove the effectiveness of our model.

关键词： Training Training data Anomaly detection Feature extraction data models Testing Adaptation models

来源：评论

学校读者我要写书评

暂无评论

Pattern mining, semantic label identification and movement prediction using mobile phone data

Pattern mining, semantic label identification and movement p...

引用

8th International Conference on Advanced data Mining and Applications, ADMA 2012

作者： Xie, Rong Luo, Jun Yue, Yang Li, Qingquan Zou, Xiaoqing International School of Software Wuhan University Wuhan 430079 China Shenzhen Institutes of Advanced Technology CAS Shenzhen 518055 China Shenzhen Key Laboratory of High Performance Data Mining Shenzhen 518055 China Shenzhen University Shenzhen China State Key Lab. of Information Engineering in Surveying Mapping and Remote Sensing Wuhan University Wuhan 430079 China Faculty of Land Resource Engineering Kunming University of Science and Technology Kunming China

ISBN: (纸本)9783642355264

data collected from mobile phones have potential knowledge to provide with important behavior patterns of individuals. In this paper, we present approaches to discovering personal mobility and characteristics based on mobile phone location information and semantic analysis. We discuss three aspects related to very common mobile phone-related applications such as pattern mining, semantic label identification and movement prediction. We use real mobile phone data to perform functions of discovering these behavior patterns and demonstrate effectiveness of our approaches. © Springer-Verlag 2012.

关键词： Cellular telephones

来源：评论

学校读者我要写书评

暂无评论

Boosting Connectivity in Retinal Vessel Segmentation via a Recursive Semantics-Guided network 23rd

Boosting Connectivity in Retinal Vessel Segmentation via a R...

引用

23rd International Conference on Medical Image Computing and Computer-Assisted Intervention, MICCAI 2020

作者： Xu, Rui Liu, Tiantian Ye, Xinchen Lin, Lin Chen, Yen-Wei DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China DUT-RU Co-Research Center of Advanced ICT for Active Life Dalian China Key Laboratory for Ubiquitous Network and Service Software of Liaoning Province Dalian China College of Software Dalian University of Technology Dalian China College of Information Science and Engineering Ritsumeikan University Kusatsu Japan Research Center of Healthcare Data Science Zhejiang Lab Hangzhou China

ISBN: (纸本)9783030597214

Many deep learning based methods have been proposed for retinal vessel segmentation, however few of them focus on the connectivity of segmented vessels, which is quite important for a practical computer-aided diagnosis system on retinal images. In this paper, we propose an efficient network to address this problem. A U-shape network is enhanced by introducing a semantics-guided module, which integrates the enriched semantics information to shallow layers for guiding the network to explore more powerful features. Besides, a recursive refinement iteratively applies the same network over the previous segmentation results for progressively boosting the performance while increasing no extra network parameters. The carefully designed recursive semantics-guided network has been extensively evaluated on several public datasets. Experimental results have shown the efficiency of the proposed method. © 2020, Springer Nature Switzerland AG.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Exploration of the Influence on Training Deep Learning Models by Watermarked Image dataset

Exploration of the Influence on Training Deep Learning Model...

引用

IEEE International Conference on Big data and Cloud Computing (BdCloud)

作者： Shiqin Liu Shiyuan Feng Jinxia Wu Wei Ren Weiqi Wang Wenwen Zheng School of Computer Science China University of Geosciences Wuhan China Key Laboratory of Network Assessment Technology CAS Chinese Academy of Sciences Beijing China Guizhou Provincial Key Laboratory of Public Big Data Guizhou University Guiyang China

Deep learning has achieved great success in various applications with the help of a large scale of datasets. As a result, sharing the valuable big data that can be applied to training deep learning models is of essential importance currently. However, how to claim ownership and protect the copyright of image big data during the sharing process is still a vital issue that should be addressed. The application of digital watermarks can protect the copyright of image data, at the same time, it also degrades the image quality at the same time. As for invisible digital watermarks, the higher the watermark embedding intensity causes the greater the host image changes. Therefore, the performance of deep learning models may decline due to using the watermarked training set. In this paper, we evaluate the influences of different embedding intensities of various watermarking algorithms on several mainstream models and conclude how the watermarking intensity affects the model training. Besides, referring to watermarking algorithms that have been proposed, we proposed a novel discrete Fourier transform-based watermarking algorithm that can achieve image copyright protection yet maintain the utility of models.

关键词： Training Deep learning Image quality Fourier transforms Watermarking Big data Copyright protection

来源：评论

学校读者我要写书评

暂无评论

Reverse Perspective network for Perspective-Aware Object Counting

Reverse Perspective Network for Perspective-Aware Object Cou...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yifan Yang Guorong Li Zhe Wu Li Su Qingming Huang Nicu Sebe School of Computer Science and Technology UCAS Beijing China Key Lab of Big Data Mining and Knowledge Management UCAS Beijing China Key Lab of Intelligent Information Processing Institute of Computing Technology CAS Beijing China University of Trento Trento Italy

ISBN: (数字)9781728171685

ISBN: (纸本)9781728171692

One of the critical challenges of object counting is the dramatic scale variations, which is introduced by arbitrary perspectives. We propose a reverse perspective network to solve the scale variations of input images, instead of generating perspective maps to smooth final outputs. The reverse perspective network explicitly evaluates the perspective distortions, and efficiently corrects the distortions by uniformly warping the input images. Then the proposed network delivers images with similar instance scales to the regressor. Thus the regression network doesn't need multi-scale receptive fields to match the various scales. Besides, to further solve the scale problem of more congested areas, we enhance the corresponding regions of ground-truth with the evaluation errors. Then we force the regressor to learn from the augmented ground-truth via an adversarial process. Furthermore, to verify the proposed model, we collected a vehicle counting dataset based on Unmanned Aerial Vehicles (UAVs). The proposed dataset has fierce scale variations. Extensive experimental results on four benchmark datasets show the improvements of our method against the state-of-the-arts.

关键词： Distortion Training Feature extraction Estimation Convolution Kernel Adaptation models

来源：评论

学校读者我要写书评

暂无评论

A Hierarchy Method Based on LDA and SVM for News Classification

A Hierarchy Method Based on LDA and SVM for News Classificat...

引用

IEEE International Conference on data Mining Workshops (ICDM Workshops)

作者： Limeng Cui Fan Meng Yong Shi Minqiang Li An Liu Research Center on Fictitious Economy & Data Science Key Research Lab on Big Data Mining and Knowledge Management Beijing CAS China School of Managemt Tianjin University Tianjin China School of Computer Science & Technology Soochow University Suzhou China

ISBN: (纸本)9781479942732

He growth of the online data provides the user a access to information on the Internet but also creates the challenges to obtain the valuable knowledge. In this paper we focus on news text classification, which is meaningful for information provider to organize and display the news but also for the users to reach the valuable information easily. A hierarchy method based on LDA and SVM is proposed to accomplish this task and several experiments are conducted to evaluate our method. The results show that our method is promising in text classification problems.

关键词： Support vector machines Classification algorithms Text categorization Runtime Kernel Computational modeling

来源：评论

学校读者我要写书评

暂无评论

Adversarial Learning data Augmentation for Graph Contrastive Learning in Recommendation

arXiv

引用

arXiv 2023年

作者： Huang, Junjie Cao, Qi Xie, Ruobing Zhang, Shaoliang Xia, Feng Shen, Huawei Cheng, Xueqi Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Beijing China University of Chinese Academy of Sciences Beijing China WeChat Tencent Beijing China CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences Beijing China

Recently, Graph Neural networks (GNNs) achieve remarkable success in Recommendation. To reduce the influence of data sparsity, Graph Contrastive Learning (GCL) is adopted in GNN-based CF methods for enhancing performance. Most GCL methods consist of data augmentation and contrastive loss (e.g., InfoNCE). GCL methods construct the contrastive pairs by hand-crafted graph augmentations and maximize the agreement between different views of the same node compared to that of other nodes, which is known as the InfoMax principle. However, improper data augmentation will hinder the performance of GCL. InfoMin principle, that the good set of views shares minimal information and gives guidelines to design better data augmentation. In this paper, we first propose a new data augmentation (i.e., edge-operating including edge-adding and edge-dropping). Then, guided by InfoMin principle, we propose a novel theoretical guiding contrastive learning framework, named Learnable data Augmentation for Graph Contrastive Learning (LDA-GCL). Our methods include data augmentation learning and graph contrastive learning, which follow the InfoMin and InfoMax principles, respectively. In implementation, our methods optimize the adversarial loss function to learn data augmentation and effective representations of users and items. Extensive experiments on four public benchmark datasets demonstrate the effectiveness of LDA-GCL. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Uncertainty calibration for ensemble-based debiasing methods

arXiv

引用

arXiv 2021年

作者： Xiong, Ruibin Chen, Yimeng Pang, Liang Cheng, Xueqi Ma, Zhiming Lan, Yanyan CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Baidu Inc Academy of Mathematics and Systems Science Chinese Academy of Sciences Data Intelligence System Research Center Institute of Computing Technology Chinese Academy of Sciences Institute for AI Industry Research Tsinghua University

Ensemble-based debiasing methods have been shown effective in mitigating the reliance of classifiers on specific dataset bias, by exploiting the output of a bias-only model to adjust the learning target. In this paper, we focus on the bias-only model in these ensemble-based methods, which plays an important role but has not gained much attention in the existing literature. Theoretically, we prove that the debiasing performance can be damaged by inaccurate uncertainty estimations of the bias-only model. Empirically, we show that existing bias-only models fall short in producing accurate uncertainty estimations. Motivated by these findings, we propose to conduct calibration on the bias-only model, thus achieving a three-stage ensemble-based debiasing framework, including bias modeling, model calibrating, and debiasing. Experimental results on NLI and fact verification tasks show that our proposed three-stage debiasing framework consistently outperforms the traditional two-stage one in out-of-distribution accuracy. Copyright © 2021, The Authors. All rights reserved.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

ProtoEM: A Prototype-Enhanced Matching Framework for Event Relation Extraction

arXiv

引用

arXiv 2023年

作者： Hu, Zhilei Li, Zixuan Xu, Daozhu Bai, Long Jin, Cheng Jin, Xiaolong Guo, Jiafeng Cheng, Xueqi CAS Key Laboratory of Network Data Science and Technology Institute of Computing Technology Chinese Academy of Sciences China School of Computer Science and Technology University of Chinese Academy of Sciences China State Key Laboratory of Geo-Information Engineering Xi’an710054 China Xi’an Research Institute of Surveying and Mapping Xi’an710054 China

Event Relation Extraction (ERE) aims to extract multiple kinds of relations among events in texts. However, existing methods singly categorize event relations as different classes, which are inadequately capturing the intrinsic semantics of these relations. To comprehensively understand their intrinsic semantics, in this paper, we obtain prototype representations for each type of event relation and propose a Prototype-Enhanced Matching (ProtoEM) framework for the joint extraction of multiple kinds of event relations. Specifically, ProtoEM extracts event relations in a two-step manner, i.e., prototype representing and prototype matching. In the first step, to capture the connotations of different event relations, ProtoEM utilizes examples to represent the prototypes corresponding to these relations. Subsequently, to capture the interdependence among event relations, it constructs a dependency graph for the prototypes corresponding to these relations and utilized a Graph Neural network (GNN)-based module for modeling. In the second step, it obtains the representations of new event pairs and calculates their similarity with those prototypes obtained in the first step to evaluate which types of event relations they belong to. Experimental results on the MAVEN-ERE dataset demonstrate that the proposed ProtoEM framework can effectively represent the prototypes of event relations and further obtain a significant improvement over baseline models. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

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：