检索结果-内蒙古大学图书馆

3rd IEEE International Conference on Intelligent networking and Collab.rativeSystems, INCoS 2011

作者： Fan, Kai Wang, Yue Li, Hui Ministry of Edu. Key Lab. of Computer Network and Information Security Xidian University Xi'an China Xi'an Branch Shaanxi Telecom Ltd. Xi'an China

ISBN: (纸本)9780769545790

Abuse-freeness is one of the most interesting new problems in the electronic payment security today. It is an effective supplementary for the fairness. It is confused for researchers how to get real abuse-freeness in electronic payment. An abuse-freeness electronic payment protocol for real goods is proposed in this paper. The protocol has the abuse-freeness by introducing a trusted third party and using the concurrent signature and it has prevented both sides in payment to originate and terminate protocol maliciously. At the same time fairness and security are also achieved in the proposed protocol. © 2011 IEEE.

关键词： Contracts Equations Forgery Manuals Process control Protocols Security abuse-freeness abuse-freeness electronic payment protocol concurrent signature concurrent signature digital signatures electronic money electronic payment protocol electronic payment security trusted third party trusted third party (TTP)

来源：评论

学校读者我要写书评

暂无评论

Forward secure proxy blind signature scheme

Forward secure proxy blind signature scheme

引用

3rd IEEE International Conference on Intelligent networking and Collab.rativeSystems, INCoS 2011

作者： Fan, Kai Wang, Yue Li, Hui Ministry of Edu. Key Lab. of Computer Network and Information Security Xidian University Xi'an China Xi'an Branch Shaanxi Telecom Ltd. Xi'an China

ISBN: (纸本)9780769545790

There is no forward security in any proxy blind signature schemes today. The lack of forward security will impact the system security tremendously if the key is stolen. To avoid such a security problem this paper proposes a forward secure proxy blind signature scheme which employs the key evolution mechanism in a newly proposed proxy blind signature scheme. The security of proxy blind signature and the forward security are both analyzed in the proposed scheme. Even if the current signature key is compromised, the attacker cannot forge signatures as if they had been generated before the key leakage. That is to say, signatures signed before the leakage are still valid. © 2011 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Calibration bottleneck: over-compressed representations are less calibratable 24

Calibration bottleneck: over-compressed representations are ...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Deng-Bao Wang Min-Ling Zhang School of Computer Science and Engineering Southeast University Nanjing China and Key Lab. of Computer Network and Information Integration (Southeast University) MOE China

Although deep neural networks have achieved remarkable success, they often exhibit a significant deficiency in reliable uncertainty calibration. This paper focus on model calibratability, which assesses how amenable a model is to be well recalibrated post-hoc. We find that the widely used weight decay regularizer detrimentally affects model calibratability, subsequently leading to a decline in final calibration performance after post-hoc calibration. To identify the underlying causes leading to poor calibratability, we delve into the calibratability of intermediate features across the hidden layers. We observe a U-shaped trend in the calibratability of intermediate features from the bottom to the top layers, which indicates that over-compression of the top representation layers significantly hinders model calibratability. Based on the observations, this paper introduces a weak classifier hypothesis, i.e., given a weak classification head that has not been over-trained, the representation module can be better learned to produce more calibratable features. Consequently, we propose a progressively layer-peeled training (PLP) method to exploit this hypothesis, thereby enhancing model calibratability. Our comparative experiments show the effectiveness of our method, which improves model calibration and also yields competitive predictive performance.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Age Distribution Learning for Apparent Age Estimation

Deep Age Distribution Learning for Apparent Age Estimation

引用

IEEE computer Society Conference on computer Vision and Pattern Recognition Workshops (CVPRW)

作者： Zengwei Huo Xu Yang Chao Xing Ying Zhou Peng Hou Jiaqi Lv Xin Geng Key Lab of Computer Network and Information Integration (Ministry of Education) Southeast University Nanjing China

Apparent age estimation has attracted more and more researchers since its potential applications in the real world. Apparent age estimation differs from chronological age estimation that in apparent age estimation each facial image is lab.lled by multiple individuals, the mean age is the ground truth age and the uncertainty is introduced by the standard deviation. In this paper, we propose a novel method called Deep Age Distribution Learning(DADL) to deal with such situation. According to the given mean age and the standard deviation, we generate a Gaussian age distribution for each facial image as the training target instead of the single age. DADL first detects the facial region in image and aligns the facial image. Then, it uses deep Convolutional Neural network(CNN) pre-trained based on the VGGFace and fine-tuned on the age dataset to extract the predicted age distribution. Finally it uses ensemble method to get the result. Our DADL method got a good performance in ChaLearn Looking at People 2016-Track 1: Age Estimation and ranked the 2nd place among 105 registered participants.

关键词： Estimation Training Standards Face Predictive models Uncertainty Correlation

来源：评论

学校读者我要写书评

暂无评论

Multi-layer screen-space ambient occlusion using hybrid sampling

Multi-layer screen-space ambient occlusion using hybrid samp...

引用

12th ACM SIGGRAPH International Conference on Virtual-Reality Continuum and Its Applications in Industry, VRCAI 2013

作者： Liu, Fang Song, Yunpeng Liu, Xuehui Xu, Xianchao State Key Lab. of Computer Sciences Institute of Software Chinese Academy of Sciences China SuperComputing Center Computer Network Information Center Chinese Academy of Sciences China Intel Labs. of China China

ISBN: (纸本)9781450325905

Ambient occlusion is a shading method which approximates the global illumination by taking into account attenuation of light due to occlusion[Christensen 2002;Sergey et al. 1998;Andrei et al. 2003]. Screen-space ambient occlusion is a scene-independent improvement which performs the visibility test using depth buffer on GPU in real time. Shanmugam et al. [Shanmugam et al. 2007] proposes a real-time multi-pass hardware assisted ambient occlusion method. The algorithm randomly samples the normal/depth buffer and reconstructs the surface using spheres that can be projected to screen, but has the overocclusion issue. Bavoil et al. [Bavoil et al. 2008] approximates the ambient occlusion illumination using a image-space horizon-based method. However, the scenes will also be overoccluded due to the inconsideration of the layers behind the frontmost one. Moreover, the rough approximation of the geometry occluder makes the shadows lack of rich details. In this paper we propose a new solution to approximate ambient occlusion using a hybrid sampling method of both above methods. The surfaces can be more accurately depicted using spheres and the geometry occluder under the horizon plane can be discarded to address the overocclusion issue. In addition, a multi-layer method is utilized to future alleviate overocclusion using the depth information of all the layers. Experiments show that our algorithm can generate more realistic results for complex scenes with rich details, with comparable performance. © 2013 ACM.

关键词： Interactive computer graphics

来源：评论

学校读者我要写书评

暂无评论

Video Frame Interpolation via Direct Synthesis with the Event-based Reference

Video Frame Interpolation via Direct Synthesis with the Even...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yuhan Liu Yongjian Deng Hao Chen Zhen Yang College of Computer Science Beijing University of Technology Key Lab of Computer Network and Information Integration Southeast University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Video Frame Interpolation (VFI) has witnessed a surge in popularity due to its abundant downstream applications. Event-based VFI (E-VFI) has recently propelled the ad-vancement of VFI. Thanks to the high temporal resolution benefits, event cameras can bridge the informational void present between successive video frames. Most state-of-the-art E-VFI methodologies follow the conventional VFI paradigm, which pivots on motion estimation between consecutive frames to generate intermediate frames through a process of warping and refinement. However, this reliance engenders a heavy dependency on the quality and consis-tency of keyframes, rendering these methods susceptible to challenges in extreme real-world scenarios, such as missing moving objects and severe occlusion dilemmas. This study proposes a novel E-VFI framework that directly synthesize intermediate frames leveraging event-based reference, obviating the necessity for explicit motion estimation and substantially enhancing the capacity to handle motion occlusion. Given the sparse and inher-ently noisy nature of event data, we prioritize the relia-bility of the event-based reference, leading to the development of an innovative event-aware reconstruction strategy for accurate reference generation. Besides, we implement a bi-directional event-guided alignment from keyframes to the reference using the introduced E-PCD module. Finally, a transformer-based decoder is adopted for prediction re-finement. Comprehensive experimental evaluations on both synthetic and real-world datasets underscore the superiority of our approach and its potential to execute high-quality VFI tasks.

关键词： Interpolation Motion estimation Noise Propulsion Transformers Rendering (computer graphics) Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Bridging the Gap: Learning Pace Synchronization for Open-World Semi-Supervised Learning

arXiv

引用

arXiv 2023年

作者： Ye, Bo Gan, Kai Wei, Tong Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing211189 China Key Lab. of Computer Network and Information Integration Southeast University MoE China

In open-world semi-supervised learning, a machine learning model is tasked with uncovering novel categories from unlab.led data while maintaining performance on seen categories from lab.led data. The central challenge is the substantial learning gap between seen and novel categories, as the model learns the former faster due to accurate supervisory information. Moreover, capturing the semantics of unlab.led novel category samples is also challenging due to the missing lab.l information. To address the above issues, we introduce 1) the adaptive synchronizing marginal loss which imposes class-specific negative margins to alleviate the model bias towards seen classes, and 2) the pseudo-lab.l contrastive clustering which exploits pseudo-lab.ls predicted by the model to group unlab.led data from the same category together in the output space. Extensive experiments on benchmark datasets demonstrate that previous approaches may significantly hinder novel class learning, whereas our method strikingly balances the learning pace between seen and novel classes, achieving a remarkable 3% average accuracy increase on the ImageNet dataset. Importantly, we find that fine-tuning the self-supervised pre-trained model significantly boosts the performance, which is overlooked in prior literature. Our code is availab.e at https://***/yebo0216best/LPS-main. 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

Finformer: A Static-dynamic Spatiotemporal Framework for Stock Trend Prediction

Finformer: A Static-dynamic Spatiotemporal Framework for Sto...

引用

2023 IEEE International Conference on Big Data, BigData 2023

作者： Zu, Yi Mi, Jiacong Song, Lingning Lu, Shan He, Jieyue Southeast University School of Computer Science and Engineering Key Lab of Computer Network and Information Integration MOE Nanjing China Southeast University School of Software Engineering Nanjing China Nanjing Fenghuo Tiandi Communication Technology Co. Ltd Nanjing China

ISBN: (纸本)9798350324457

The core of quantitative investment lies in predicting future trends in stock prices. The future trend of a stock is closely related to the industry it belongs to and its relationship with other stocks. Although some research has focused on stock trend prediction in recent years, most studies have only considered the stock's own time series feature, neglecting the spatial features between stocks. Some research has incorporated spatial information, but typically only considered predefined static relationships. At the same time, capturing dynamic spatial information in the market has been a long-standing challenge. Thus, we propose a spatio-temporal model, Finformer, in order to go beyond traditional time series models. We designed a sparse static-dynamic transformer to capture dynamic market spatial information as it changes over time and combined predefined relationships to extract highly correlated spatial features in the stock market. To effectively integrate spatial and temporal features, we introduced an adaptive spatio-temporal fusion module that dynamically fuses spatio-temporal features based on market conditions at different periods. Experiments on two real-world stock market datasets show that our proposed model outperforms the state-of-the-art baselines in the signal-based and portfolio-based metrics, which are widely concerned in the financial field. Ablation study and hyper-parameter study further reveal the effectiveness of each module in the model and the impact of hyper-parameters. The code will be made publicly availab.e. 1 © 2023 IEEE.

关键词： computational finance deep learning stock trend prediction transformer

来源：评论

学校读者我要写书评

暂无评论

Logistic Boosting Regression for lab.l Distribution Learning

Logistic Boosting Regression for Label Distribution Learning

引用

IEEE Conference on computer Vision and Pattern Recognition

作者： Chao Xing Xin Geng Hui Xue Key Lab of Computer Network and Information Integration (Ministry of Education) School of Computer Science and Engineering Southeast University

ISBN: (纸本)9781467388528

lab.l Distribution Learning (LDL) is a general learning framework which includes both single lab.l and multi-lab.l learning as its special cases. One of the main assumptions made in traditional LDL algorithms is the derivation of the parametric model as the maximum entropy model. While it is a reasonable assumption without additional information, there is no particular evidence supporting it in the problem of LDL. Alternatively, using a general LDL model family to approximate this parametric model can avoid the potential influence of the specific model. In order to learn this general model family, this paper uses a method called Logistic Boosting Regression (LogitBoost) which can be seen as an additive weighted function regression from the statistical viewpoint. For each step, we can fit individual weighted regression function (base learner) to realize the optimization gradually. The base learners are chosen as weighted regression tree and vector tree, which constitute two algorithms named LDLogitBoost and AOSO-LDLogitBoost in this paper. Experiments on facial expression recognition, crowd opinion prediction on movies and apparent age estimation show that LDLogitBoost and AOSO-LDLogitBoost can achieve better performance than traditional LDL algorithms as well as other LogitBoost algorithms.

关键词： Low-Density Lipoproteins Maximum entropy Regression (Psychology) Accelerated aging Cinema Boost Parametric statistics derivation extra message

来源：评论

学校读者我要写书评

暂无评论

A new abuse-free fair electronic payment protocol

A new abuse-free fair electronic payment protocol

引用

5th International Conference on information Assurance and Security, IAS 2009

作者： Fan, Kai Wang, Yue Li, Hui Ministry of Edu. Key Lab. of Computer Network and Information Security Xidian University Xi'an Shaanxi China Xi'an Branch of Shaanxi Telecom Ltd. Xi'an Shaanxi China

ISBN: (纸本)9780769537443

To solve the problem of the abuse in electronic payment protocols, a new abuse-free fair electronic payment protocol is proposed in this paper. The proposed protocol solves the problems in Parks' protocol and furthermore it solves the abuse using off-line trusted third party (TTP). The security and fairness are also possessed in the protocol. © 2009 IEEE.

关键词： Parks

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：