检索结果-内蒙古大学图书馆

Frontiers Technology of Information and Computer (ICFTIC), IEEE International Conference on

作者： Haonan Xu Wenfang Xue Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China

Recently, quantitative investment has become a new way of investment finance, which combines the model with the computer to predict the investment stock trend more efficiently and accurately. Stock trend forecasting is one of the difficult and important tasks in modern quantitative investment systems. With the development of artificial intelligence technology, many deep learning models have emerged. The application of deep learning in the stock market not only reduces the difficulty of stock analysis and trend prediction, but also introduces new investment methods and ideas for investors. However, most of the models are based on volume and price data, and the consideration of stock relationships are relatively simple, so we propose a Spatial-Temporal Graph Neural Network model fusing Barra factors (BSTGNN), which integrates factor knowledge, mines potential inter-stock relationships, and fully consider the heterogeneity of the relationship. The experiments conducted on the real-world stock market dataset prove that BSTGNN perform better than the baseline methods.

关键词： Deep learning Solid modeling Computational modeling Time series analysis Market research Graph neural networks Data models

来源：评论

学校读者我要写书评

暂无评论

An end-to-end autofocus camera for iris on the move

arXiv

引用

arXiv 2021年

作者： Wang, Leyuan Zhang, Kunbo Wang, Yunlong Sun, Zhenan School of Artificial Intelligence UCAS Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition CASIA

For distant iris recognition, a long focal length lens is generally used to ensure the resolution of iris images, which reduces the depth of field and leads to potential defocus blur. To accommodate users at different distances, it is necessary to control focus quickly and accurately. While for users in motion, it is expected to maintain the correct focus on the iris area continuously. In this paper, we introduced a novel rapid autofocus camera for active refocusing of the iris area of the moving objects using a focus-tunable lens. Our end-to-end computational algorithm can predict the best focus position from one single blurred image and generate a lens diopter control signal automatically. This scene-based active manipulation method enables real-time focus tracking of the iris area of a moving object. We built a testing bench to collect real-world focal stacks for evaluation of the autofocus methods. Our camera has reached an autofocus speed of over 50 fps. The results demonstrate the advantages of our proposed camera for biometric perception in static and dynamic scenes. The code is available at https://***/Debatrix/AquulaCam. © 2021, CC BY-SA.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Hard Patches Mining for Masked Image Modeling

Hard Patches Mining for Masked Image Modeling

引用

Conference on Computer Vision and pattern recognition (CVPR)

作者： Haochen Wang Kaiyou Song Junsong Fan Yuxi Wang Jin Xie Zhaoxiang Zhang Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences University of Chinese Academy of Sciences Megvii Technology Centre for Artificial Intelligence and Robotics Hong Kong Institute of Science & Innovation Chinese Academy of Science

Masked image modeling (MIM) has attracted much research attention due to its promising potential for learning scalable visual representations. In typical approaches, models usually focus on predicting specific contents of masked patches, and their performances are highly related to pre-defined mask strategies. Intuitively, this procedure can be considered as training a student (the model) on solving given problems (predict masked patches). However, we argue that the model should not only focus on solving given problems, but also stand in the shoes of a teacher to produce a more challenging problem by itself. To this end, we propose Hard Patches Mining (HPM), a brand-new framework for MIM pre-training. We observe that the reconstruction loss can naturally be the metric of the difficulty of the pretraining task. Therefore, we introduce an auxiliary loss predictor, predicting patch-wise losses first and deciding where to mask next. It adopts a relative relationship learning strategy to prevent overfitting to exact reconstruction loss values. Experiments under various settings demonstrate the effectiveness of HPM in constructing masked images. Furthermore, we empirically find that solely introducing the loss prediction objective leads to powerful representations, verifying the efficacy of the ability to be aware of where is hard to reconstruct. 1 1 Code: https://***/Haochen-wang409/HPM

关键词：

来源：评论

学校读者我要写书评

暂无评论

research on integrated test and evaluation of information system equipment

Research on integrated test and evaluation of information sy...

引用

2021 Guangdong-Hong Kong-Macao Greater Bay Area Artificial Intelligence and Big Data Forum, AIBDF 2021

作者： Ma, Jing Wang, Ruihua Wang, Jiajia Yang, Zhou Li, Na Beijing Jinghang Research Institute of Computing and Communication Beijing China PLA Academy of Military Science Beijing China Applied Mathematics Research Center of China Aerospace Science and Industry Group Beijing China Innovation Center for Intelligent System on Recognition and Decision Beijing China

The integrated test of weapons and equipment is an urgent need for the development of weapons and equipment under the contemporary information conditions, because it can reduce the resource requirements, test cost and risk, as well as improve the test efficiency and the degree of confidence. This paper based on the objective requirements of integrated evaluation of information system equipment test, aims at performance test for information system equipment. For the same equipment testing, test means to analysis the factors that affect *** implementation is based on prior knowledge and expert experience response parameters, including regression model building, and the credibility of the weighted multi-source data fusion evaluation method research. It provides technical and theoretical support for the integrated test evaluation of information system equipment multi-source test. © 2021 Institute of Physics Publishing. All rights reserved.

关键词： Information systems

来源：评论

学校读者我要写书评

暂无评论

Audio-Driven Dubbing for User Generated Contents via Style-Aware Semi-Parametric Synthesis

arXiv

引用

arXiv 2023年

作者： Song, Linsen Wu, Wayne Fu, Chaoyou Loy, Chen Change He, Ran The National Laboratory of Pattern Recognition CASIA Center for Research on Intelligent Perception and Computing CASIA Center for Excellence in Brain Science and Intelligence Technology CAS The School of Artificial Intelligence University of Chinese Academy of Sciences Beijing100190 China SenseTime Research Beijing100080 China The S-Laboratory Nanyang Technological University Singapore639798 Singapore

Existing automated dubbing methods are usually designed for Professionally Generated Content (PGC) production, which requires massive training data and training time to learn a person-specific audio-video mapping. In this paper, we investigate an audio-driven dubbing method that is more feasible for User Generated Content (UGC) production. There are two unique challenges to design a method for UGC: 1) the appearances of speakers are diverse and arbitrary as the method needs to generalize across users;2) the available video data of one speaker are very limited. In order to tackle the above challenges, we first introduce a new Style Translation Network to integrate the speaking style of the target and the speaking content of the source via a cross-modal AdaIN module. It enables our model to quickly adapt to a new speaker. Then, we further develop a semi-parametric video renderer, which takes full advantage of the limited training data of the unseen speaker via a video-level retrieve-warp-refine pipeline. Finally, we propose a temporal regularization for the semi-parametric renderer, generating more continuous videos. Extensive experiments show that our method generates videos that accurately preserve various speaking styles, yet with considerably lower amount of training data and training time in comparison to existing methods. Besides, our method achieves a faster testing speed than most recent methods. © 2023, CC BY-NC-SA.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

An Empirical Study of Graph Contrastive Learning 35

An Empirical Study of Graph Contrastive Learning

引用

35th Conference on Neural Information Processing systems - Track on Datasets and Benchmarks, NeurIPS Datasets and Benchmarks 2021

作者： Zhu, Yanqiao Xu, Yichen Liu, Qiang Wu, Shu Center for Research on Intelligent Perception and Computing National Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China School of Computer Science Beijing University of Posts and Telecommunications China

Graph Contrastive Learning (GCL) establishes a new paradigm for learning graph representations without human annotations. Although remarkable progress has been witnessed recently, the success behind GCL is still left somewhat mysterious. In this work, we first identify several critical design considerations within a general GCL paradigm, including augmentation functions, contrasting modes, contrastive objectives, and negative mining strategies. Then, to understand the interplay of different GCL components, we conduct comprehensive, controlled experiments over benchmark tasks on datasets across various domains. Our empirical studies suggest a set of general receipts for effective GCL, e.g., simple topology augmentations that produce sparse graph views bring promising performance improvements;contrasting modes should be aligned with the granularities of end tasks. In addition, to foster future research and ease the implementation of GCL algorithms, we develop an easy-to-use library PyGCL, featuring modularized CL components, standardized evaluation, and experiment management. We envision this work to provide useful empirical evidence of effective GCL algorithms and offer several insights for future research. © 2021 Neural information processing systems foundation. 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

IEEE T-BIOM Editorial Board Changes

IEEE Transactions on Biometrics, Behavior, and Identity Scie...

引用

IEEE Transactions on Biometrics, Behavior, and Identity Science 2024年第1期7卷 1-2页

作者： Naser Damer Weihong Deng Jianjiang Feng Vishal M. Patel Ajita Rattani Mark Nixon Smart Living & Biometric Technologies Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Germany Pattern Recognition and Intelligent System Laboratory Beijing University of Posts and Telecommunications Beijing China Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering Johns Hopkins University Baltimore MD USA Department of Computer Science and Engineering College of Engineering University of North Texas Denton TX USA

来源：评论

学校读者我要写书评

暂无评论

Vehicle Routing Problem with Time Windows using Hybrid Metaheuristic Dragonfly Algorithm and Variable Neighborhood Search: Work on Progress

Vehicle Routing Problem with Time Windows using Hybrid Metah...

引用

International Conference on Electrical Engineering, Computer Science and Informatics (EECSI)

作者： Yunita Yunita Deris Stiawan Dian Palupi Rini Doctoral Student at Faculty of Computer Science Sriwijaya University Intelligent System Research Group Faculty of Computer Science Sriwijaya University Palembang South Sumatera Communication Network and Information Security Research Group Faculty of Computer Science Sriwijaya University Palembang South Sumatera Image Processing dan Pattern Recognition Laboratory Group Faculty of Computer Science Sriwijaya University Palembang South Sumatera

ISBN: (数字)9798350355314

ISBN: (纸本)9798350355321

One of the problems with Smart Transportation is the problem of cost and travel time. This problem is known as the Variable Routing Problem (VRP). In some real cases, in addition to considering route selection, there are limitations on the capacity and time period for the vehicle to serve each customer known as Time Windows, so VRP has developed into Variable Routing Problem with Time Windows (VRPTW). One way to solve VRPTW is to use metaheuristic methods. However, the metaheuristic method has a weakness, which are it can get stuck in local optimums and fail to find better global solutions. To overcome this, a combination with other methods or known as hybrid is needed. The formulation of this research problem is how to develop a Smart transportation model using a metaheuristic hybrid algorithm. The purpose of this study is to develop a Smart transportation model using a metaheuristic hybrid algorithm. The method used is to combine two metaheuristic algorithms, which are the Dragonfly Algorithm (DA) and the Variable Neighborhood Search (VNS). The result of this research is a new algorithm model which is a hybrid between DA and VNS. Through a combination of global exploration using DA and local exploitation using VNS, this algorithm is expected to be able to find a better solution and faster convergence in solving VRPTW problems

关键词： Electrical engineering Computer science Costs Metaheuristics Vehicle routing Routing Search problems Smart transportation Informatics Convergence

来源：评论

学校读者我要写书评

暂无评论

An Anti-Poisoning Attack Method for Distributed AI system

An Anti-Poisoning Attack Method for Distributed AI System

引用

作者： Xuezhu Xin Yang Bai Haixin Wang Yunzhen Mou Jian Tan Innovation Center for Intelligent System on Recognition and Decision Beijing Jinghang Research Institute of Computing and Communication School of Digital Media and Art Design Beijing University of Posts and Telecommunications

In distributed AI system, the models trained on data from potentially unreliable sources can be attacked by manipulating the training data distribution by inserting carefully crafted samples into the training set, which is known as Data *** will to change the model behavior and reduce model *** paper proposes an algorithm that gives an improvement of both efficiency and security for data poisoning in a distributed AI *** past methods of active defense often have a large number of invalid checks, which slows down the operation efficiency of the whole *** passive defense also has problems of missing data and slow detection of error *** proposed algorithm establishes the suspect hypothesis level to test and extend the verification of data packets and estimates the risk of terminal *** can enhance the health degree of a distributed AI system by preventing the occurrence of poisoning attack and ensuring the efficiency and safety of the system operation.

关键词： Data Poisoning Distributed AI system Credit Probability Mechanism Inspection Module Suspect Hypothesis Level

来源：评论

学校读者我要写书评

暂无评论

Lightweight Vision Transformer with Bidirectional Interaction

arXiv

引用

arXiv 2023年

作者： Fan, Qihang Huang, Huaibo Zhou, Xiaoqiang He, Ran Center for Research on Intelligent Perception and Computing CASIA Beijing China National Laboratory of Pattern Recognition CASIA Beijing China School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Tsinghua University China University of Science and Technology of China Hefei China

Recent advancements in vision backbones have significantly improved their performance by simultaneously modeling images’ local and global contexts. However, the bidirectional interaction between these two contexts has not been well explored and exploited, which is important in the human visual system. This paper proposes a Fully Adaptive Self-Attention (FASA) mechanism for vision transformer to model the local and global information as well as the bidirectional interaction between them in context-aware ways. Specifically, FASA employs self-modulated convolutions to adaptively extract local representation while utilizing self-attention in down-sampled space to extract global representation. Subsequently, it conducts a bidirectional adaptation process between local and global representation to model their interaction. In addition, we introduce a fine-grained downsampling strategy to enhance the down-sampled self-attention mechanism for finer-grained global perception capability. Based on FASA, we develop a family of lightweight vision backbones, Fully Adaptive Transformer (FAT) family. Extensive experiments on multiple vision tasks demonstrate that FAT achieves impressive performance. Notably, FAT accomplishes a 77.6% accuracy on ImageNet-1K using only 4.5M parameters and 0.7G FLOPs, which surpasses the most advanced ConvNets and Transformers with similar model size and computational costs. Moreover, our model exhibits faster speed on modern GPU compared to other models. Code will be available at https://***/qhfan/FAT. Copyright © 2023, The Authors. All rights reserved.

关键词： Image enhancement

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：