检索结果-内蒙古大学图书馆

Joint specular highlight detection and removal in single images via Unet-Transformer

Computational Visual Media 2023年第1期9卷 141-154页

作者： Zhongqi Wu Jianwei Guo Chuanqing Zhuang Jun Xiao Dong-Ming Yan Xiaopeng Zhang National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China The School of Artificial Intelligence University of Chinese Academy of SciencesBeijingChina

Specular highlight detection and removal is a fundamental problem in computer vision and image *** this paper,we present an efficient endto-end deep learning model for automatically detecting and removing specular highlights in a single *** particular,an encoder–decoder network is utilized to detect specular highlights,and then a novel Unet-Transformer network performs highlight removal;we append transformer modules instead of feature maps in the Unet *** also introduce a highlight detection module as a mask to guide the removal ***,these two networks can be jointly trained in an effective *** to the hierarchical and global properties of the transformer mechanism,our framework is able to establish relationships between continuous self-attention layers,making it possible to directly model the mapping between the diffuse area and the specular highlight area,and reduce indeterminacy within areas containing strong specular highlight *** on public benchmark and real-world images demonstrate that our approach outperforms state-of-the-art methods for both highlight detection and removal tasks.

关键词： specular highlight detection specular highlight removal Unet-Transformer

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaptation on Sentence Matching Through Self-Supervision

引用

Journal of Computer Science & Technology 2023年第6期38卷 1237-1249页

作者：白桂荣刘庆斌何世柱刘康赵军 National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China

Although neural approaches have yielded state-of-the-art results in the sentence matching task,their perfor-mance inevitably drops dramatically when applied to unseen *** tackle this cross-domain challenge,we address unsupervised domain adaptation on sentence matching,in which the goal is to have good performance on a target domain with only unlabeled target domain data as well as labeled source domain ***,we propose to perform self-su-pervised tasks to achieve *** from previous unsupervised domain adaptation methods,self-supervision can not on-ly flexibly suit the characteristics of sentence matching with a special design,but also be much easier to *** training,each self-supervised task is performed on both domains simultaneously in an easy-to-hard curriculum,which gradually brings the two domains closer together along the direction relevant to the *** a result,the classifier trained on the source domain is able to generalize to the unlabeled target *** total,we present three types of self-super-vised tasks and the results demonstrate their *** addition,we further study the performance of different usages of self-supervised tasks,which would inspire how to effectively utilize self-supervision for cross-domain scenarios.

关键词： unsupervised domain adaptation sentence matching self-supervision

来源：评论

学校读者我要写书评

暂无评论

Transformer: A General Framework from Machine Translation to Others

引用

Machine intelligence Research 2023年第4期20卷 514-538页

作者： Yang Zhao Jiajun Zhang Chengqing Zong National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing100190China

Machine translation is an important and challenging task that aims at automatically translating natural language sentences from one language into ***,Transformer-based neural machine translation(NMT)has achieved great break-throughs and has become a new mainstream method in both methodology and *** this article,we conduct an overview of Transformer-based NMT and its extension to other ***,we first introduce the framework of Transformer,discuss the main challenges in NMT and list the representative methods for each ***,the public resources and toolkits in NMT are ***,the extensions of Transformer in other tasks,including the other natural language processing tasks,computer vision tasks,audio tasks and multi-modal tasks,are briefly ***,possible future research directions are suggested.

关键词： Neural machine translation Transformer document neural machine translation(NMT) multimodal NMT low-resource NMT

来源：评论

学校读者我要写书评

暂无评论

CASIA-Iris-Africa:A Large-scale African Iris Image Database

引用

Machine intelligence Research 2024年第2期21卷 383-399页

作者： Jawad Muhammad Yunlong Wang Junxing Hu Kunbo Zhang Zhenan Sun School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Research on Intelligent Perception and Computing National Laboratory of Pattern RecognitionInstitute of AutomationChinese Academy of SciencesBeijing 100190China

Iris biometrics is a phenotypic biometric trait that has proven to be agnostic to human natural physiological *** on iris biometrics has progressed tremendously,partly due to publicly available iris *** databases have been available to researchers that address pressing iris biometric challenges such as constraint,mobile,multispectral,synthetics,long-distance,contact lenses,liveness detection,***,these databases mostly contain subjects of Caucasian and Asian docents with very few *** many investigative studies on racial bias in face biometrics,very few studies on iris biometrics have been published,mainly due to the lack of racially diverse large-scale databases containing sufficient iris samples of Africans in the public ***,most of these databases contain a relatively small number of subjects and labelled *** paper proposes a large-scale African database named Chinese Academy of Sciences Institute of Automation(CASIA)-Iris-Africa that can be used as a complementary database for the iris recognition community to mediate the effect of racial biases on *** database contains 28717 images of 1023 African subjects(2046 iris classes)with age,gender,and ethnicity attributes that can be useful in demographically sensitive studies of *** of specific application protocols are incorporated with the database to ensure the database’s variability and *** results of some open-source state-of-the-art(SOTA)algorithms on the database are presented,which will serve as baseline *** relatively poor performances of the baseline algorithms on the proposed database despite better performance on other databases prove that racial biases exist in these iris recognition algorithms.

关键词： African iris recognition racial bias iris image database biometrics iris recognition

来源：评论

学校读者我要写书评

暂无评论

Staged multi-target tracking and matching algorithm combined with depth estimation information

Staged multi-target tracking and matching algorithm combined...

引用

2024 International Conference on Image, Signal Processing, and pattern recognition, ISPP 2024

作者： Jia, Yunhua Zhou, Chengjiang Yunnan Normal University School of Information Kunming650500 China Pattern Recognition and Artificial Intelligence Laboratory Kunming650500 China

ISBN: (纸本)9781510680425

As the field of artificial intelligence progresses, multi-target tracking, one of the advanced visual tasks of computer vision, has developed *** present, as multi-target tracking technology gradually matures, related scientific research results are slowly appearing in our daily lives, bringing more powerful help to our ***, the precision of multi-target tracking faces significant constraints, mainly attributed to factors like occlusion and interference from the *** to reduce the constraints of occlusion and other factors on the accuracy of multi-target *** this paper, we propose a staged multi-target tracking and matching algorithm that combines depth estimation *** using the depth estimation information of targets in the scene, combined with the proposed staged matching algorithm improves the precision of the algorithm for multi-target tracking. © 2024 SPIE.

关键词： Detection and tracking algorithms Ablation Algorithm development Data modeling Computer vision technology Sensors Video

来源：评论

学校读者我要写书评

暂无评论

Scene text removal via cascaded text stroke detection and erasing

引用

Computational Visual Media 2022年第2期8卷 273-287页

作者： Xuewei Bian Chaoqun Wang Weize Quan Juntao Ye Xiaopeng Zhang Dong-Ming Yan National Laboratory of Pattern Recognition Institute of AutomationBeijing 100049China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100084China

Recent learning-based approaches show promising performance improvement for the scene text removal task but usually leave several remnants of text and provide visually unpleasant *** this work,a novel end-to-end framework is proposed based on accurate text stroke ***,the text removal problem is decoupled into text stroke detection and stroke removal;we design separate networks to solve these two subproblems,the latter being a generative *** two networks are combined as a processing unit,which is cascaded to obtain our final model for text *** results demonstrate that the proposed method substantially outperforms the state-of-the-art for locating and erasing scene text.A new large-scale real-world dataset with 12,120 images has been constructed and is being made available to facilitate research,as current publicly available datasets are mainly synthetic so cannot properly measure the performance of different methods.

关键词： scene text removal text stroke detection generative adversarial networks cascaded network design real-world dataset

来源：评论

学校读者我要写书评

暂无评论

Understanding Driving Risks via Prompt Learning

Understanding Driving Risks via Prompt Learning

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Chang, Yubo Lyu, Fan Zhang, Zhang Wang, Liang School of Artificial Intelligence University of Chinese Academy of Sciences Beijing China Institute of Automation Chinese Academy of Sciences New Laboratory of Pattern Recognition State Key Laboratory of Multimodal Artificial Intelligence Systems Beijing China

ISBN: (纸本)9781665410205

Understanding driving risks is crucial for enhancing driving safety. It is a challenging task to evaluate driving risks in various complex driving scenarios. Inspired by prompt-based learning, we propose an end-to-end approach for identifying the highest-risk object in the current driving scenario based on a learnable risk pool. Specifically, a method based on key-value pair matching is designed to build a memory system for learning a collection of risk prototypes. Extensive experiments on the DRAMA dataset show that the proposed method achieves an improvement of 18.6% in Mean-IOU and 3.0% in B4 score compared to the state-of-the-art (SOTA) methods, which indicates that our method can effectively localize risky objects and accurately describe the driving scenes. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Mining High Quality patterns Using Multi-Objective Evolutionary Algorithm (Extended Abstract) 39

Mining High Quality Patterns Using Multi-Objective Evolution...

引用

39th IEEE International Conference on Data Engineering, ICDE 2023

作者： Fang, Wei Zhang, Qiang Sun, Jun Wu, Xiaojun Jiangnan University International Joint Laboratory on Artificial Intelligence of Jiangsu Province Jiangsu Provincial Engineering Laboratory of Pattern Recognition and Computational Intelligence Wuxi China

ISBN: (纸本)9798350322279

Most studies on pattern mining have considered only one pattern, such as frequent pattern or high-utility pattern, which is difficult to meet the increasingly diverse needs of users. In this paper, a novel multi-objective problem model for high quality pattern mining (HQPM) is proposed, where the objectives are support, occupancy, and utility. In order to solve the proposed three-objective problem efficiently, an improved multi-objective evolutionary algorithm for HQPM (MOEA-PM) is proposed with two kinds of population initialization strategies and an auxiliary tool. Experimental results on real-world datasets show that the proposed three-objective problem model with the MOEA-PM algorithm can discover patterns that are both frequently occurring and has a high utility in the transaction datasets, while at the same time being relatively complete. The proposed algorithm outperforms the state-of-the-art in terms of efficiency, quality, and convergence speed. © 2023 IEEE.

关键词： Evolutionary algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep unfolding multi-scale regularizer network for image denoising

引用

Computational Visual Media 2023年第2期9卷 335-350页

作者： Jingzhao Xu Mengke Yuan Dong-Ming Yan Tieru Wu School of Mathematics Jilin UniversityChangchun 130012China National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China.

Existing deep unfolding methods unroll an optimization algorithm with a fixed number of steps,and utilize convolutional neural networks(CNNs)to learn data-driven ***,their performance is limited for two main ***,priors learned in deep feature space need to be converted to the image space at each iteration step,which limits the depth of CNNs and prevents CNNs from exploiting contextual ***,existing methods only learn deep priors at the single full-resolution scale,so ignore the benefits of multi-scale context in dealing with high level *** address these issues,we explicitly consider the image denoising process in the deep feature space and propose the deep unfolding multi-scale regularizer network(DUMRN)for image *** core of DUMRN is the feature-based denoising module(FDM)that directly removes noise in the deep feature *** each FDM,we construct a multi-scale regularizer block to learn deep prior information from multi-resolution *** build the DUMRN by stacking a sequence of FDMs and train it in an end-to-end *** results on synthetic and real-world benchmarks demonstrate that DUMRN performs favorably compared to state-of-theart methods.

关键词： image denoising deep unfolding network multi-scale regularizer deep learning

来源：评论

学校读者我要写书评

暂无评论

Multimodal Fusion of Brain Imaging Data: Methods and Applications

引用

Machine intelligence Research 2024年第1期21卷 136-152页

作者： Na Luo Weiyang Shi Zhengyi Yang Ming Song Tianzi Jiang Brainnetome Center and National Laboratory of Pattern Recognition Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China Center for Excellence in Brain Science and Intelligence Technology Institute of AutomationChinese Academy of SciencesBeijing 100190China Research Center for Augmented Intelligence Zhejiang LaboratoryHangzhou 311100China

Neuroimaging data typically include multiple modalities,such as structural or functional magnetic resonance imaging,dif-fusion tensor imaging,and positron emission tomography,which provide multiple views for observing and analyzing the *** lever-age the complementary representations of different modalities,multimodal fusion is consequently needed to dig out both inter-modality and intra-modality *** the exploited rich information,it is becoming popular to combine multiple modality data to ex-plore the structural and functional characteristics of the brain in both health and disease *** this paper,we first review a wide spectrum of advanced machine learning methodologies for fusing multimodal brain imaging data,broadly categorized into unsupervised and supervised learning *** by this,some representative applications are discussed,including how they help to under-stand the brain arealization,how they improve the prediction of behavioral phenotypes and brain aging,and how they accelerate the biomarker exploration of brain ***,we discuss some exciting emerging trends and important future ***,we intend to offer a comprehensive overview of brain imaging fusion methods and their successful applications,along with the chal-lenges imposed by multi-scale and big data,which arises an urgent demand on developing new models and platforms.

关键词： Multimodal fusion supervised learning unsupervised learning brain atlas cognition brain disorders

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：