检索结果-内蒙古大学图书馆

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Han, Fei Zhang, Yao Zhao, Meng Tianjin University of Technology Engineering Research Center of Learning-Based Intelligent System Ministry of Education Key Laboratory of Computer Vision and System of Ministry of Education Tianjin300384 China

ISBN: (纸本)9798350331684

As an emerging distributed machine learning paradigm, federated learning (FL) only shares model updates between clients and servers, and training data are secured on each client's device. Due to local data privacy, FL is vulnerable to poisoning attacks, which causes serious degradation in the model performance. In this paper, we analyze the targeted poisoning attacks of FL and reveal that when the data held by each client of FL is independent and identically distributed (iid), the loss of all non-poisoned models on some clean dataset agrees with a normal distribution (ND), while the loss value of the poisoned model deviates from this distribution. Based on this observation, we propose a method named ND-defense to defend FL targeted poisoning attacks. We set a small clean test dataset on the server, compute the loss of each client model on it, detect the abnormal ones with the proposed loss-value-based inspection algorithm, and then only aggregate the benign clients' models to get the global model. We conducted experiments on three benchmark datasets and compared several state-of-the-art defense methods. The results show that our NDdefense is effective in defending against targeted poisoning attacks. © 2023 IEEE.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

CACP: Covariance-Aware Cross-Domain Prototypes for Domain Adaptive Semantic Segmentation

引用

IEEE Transactions on Multimedia 2025年

作者： Xue, Yanbing Tian, Xinyu Zhang, Feifei Wen, Xianbin Gao, Zan Chen, Shengyong Tianjin University of Technology Key Laboratory of Computer Vision and System Ministry of Education Tianjin300382 China

Domain adaptive semantic segmentation aims to reduce domain shifts / discrepancies between source and target domains, improving the source domain model's generalization ability to the target domain. Recently, prototypical methods, which primarily use single-source or single-target domain prototypes as category centers to aggregate features from both domains, have achieved competitive performance in this task. However, due to large domain shifts, single-source domain prototypes have finite generalization ability and not all source domain knowledge is conducive to model generalization. Single-target domain prototypes are noisy because they are prematurely initialized with all features filtered by pseudo labels, which causes error accumulation in the prototypes. To address these issues, we proposes a covariance-aware cross-domain prototypes method (CACP) to achieve robust domain adaptation. We propose to use both domain prototypes to dynamically rectify pseudo labels in the target domain, effectively reducing the recognition difficulty of hard target domain samples and narrowing the gap between features of the same category in both domains. In addition, to further generalize the model to the target domain, we propose two modules based on covariance correlation, FSPC (Features Selection by Prototypes Covariances) and WSPC (Weighting Source by Prototypes Coefficients), to learn discriminative characteristics. FSPC selects highly correlated features to update target domain prototypes online, denoising and enhancing discriminativeness between categories. WSPC utilizes the correlation coefficients between target domain prototypes and source domain features to weight each point in the source domain, eliminating the information interference from the source domain. In particular, CACP achieves excellent performance on the GTA5 \to Cityscapes and SYNTHIA \to Cityscapes tasks with minimal computational resources and time. © 1999-2012 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

A CNN-LSTM Network for Classification of Attention Deficit Hyperactivity Disorder from EEG Data 41

A CNN-LSTM Network for Classification of Attention Deficit H...

引用

第41届中国控制会议

作者： Yaru Zhang Xiangxin Tan Yue Gu Key Laboratory of Computer Vision and System (Ministry of Education) School of Computer Science and EngineeringTianjin University of Technology Engineering Research Center of Learning-Based Intelligent system Ministry of Education

ISBN: (数字)9789887581536

ISBN: (纸本)9781665482561

Attention deficit hyperactivity disorder(ADHD) is one of the most common neuropsychiatric disorders in children,with core symptoms of inattention,impulsivity,and *** a result,early detection and treatment are *** this point,ADHD can be diagnosed using an electroencephalogram(EEG).This study proposes a model for identifying the EEG of children with *** proposed model is made up of three parts:temporal convolutional blocks,spatial convolutional blocks,and Long Short Term Memory(LSTM),and because EEG contains more temporal information than other data,we build a model that can extract more temporal *** study included 24 subjects,including 12 children with ADHD and12 normal *** experimental results show that our proposed model outperforms Support Vector Machine(SVM) and EEGNet,with our model achieving correct classification rates of 92.29%,92.76%,and 90.91% on the three backs,respectively,and 94.25% on the full data,demonstrating the model's feasibility and applicability to the ADHD recognition problem.

关键词： Attention Deficit Hyperactivity Disorder Electroencephalogram Deep learning Classification

来源：评论

学校读者我要写书评

暂无评论

Specificity-preserving RGB-D saliency detection

引用

Computational Visual Media 2023年第2期9卷 297-317页

作者： Tao Zhou Deng-Ping Fan Geng Chen Yi Zhou Huazhu Fu School of Computer Science and Engineering Nanjing University of Science and TechnologyNanjing 210094China Key Laboratory of System Control and Information Processing Ministry of EducationShanghaiChina Computer Vision Lab ETH Z¨urichZ¨urichSwitzerland School of Computer Science and Engineering Northwestern Polytechnical UniversityXi’anChina School of Computer Science and Engineering Southeast UniversityNanjingChina Inception Institute of Artificial Intelligence Abu DhabiUnited Arab Emirates

Salient object detection(SOD)in RGB and depth images has attracted increasing research *** RGB-D SOD models usually adopt fusion strategies to learn a shared representation from RGB and depth modalities,while few methods explicitly consider how to preserve modality-specific *** this study,we propose a novel framework,the specificity-preserving network(SPNet),which improves SOD performance by exploring both the shared information and modality-specific ***,we use two modality-specific networks and a shared learning network to generate individual and shared saliency prediction *** effectively fuse cross-modal features in the shared learning network,we propose a cross-enhanced integration module(CIM)and propagate the fused feature to the next layer to integrate cross-level ***,to capture rich complementary multi-modal information to boost SOD performance,we use a multi-modal feature aggregation(MFA)module to integrate the modalityspecific features from each individual decoder into the shared *** using skip connections between encoder and decoder layers,hierarchical features can be fully *** experiments demonstrate that our SPNet outperforms cutting-edge approaches on six popular RGB-D SOD and three camouflaged object detection *** project is publicly available at https://***/taozh2017/SPNet.

关键词： salient object detection(SOD) RGB-D cross-enhanced integration module(CIM) multi-modal feature aggregation(MFA)

来源：评论

学校读者我要写书评

暂无评论

A Copyright Authentication Method Balancing Watermark Robustness and Data Distortion 26

A Copyright Authentication Method Balancing Watermark Robust...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wang, Chundong Li, Yue Tianjin University of Technology Tianjin300384 China National Engineering Laboratory for Virus Prevention and Control Technology Tianjin China Key Laboratory of Computer Vision and System Ministry of Education Tianjin China

ISBN: (纸本)9798350331684

Database watermarking plays an irreplaceable role in copyright authentication and data integrity protection, but the robustness of the watermark and the resulting data distortion are a pair of contradictory objects that cannot be ignored. To solve this problem, a reversible database watermarking method, named IGADEW, is proposed to balance the relationship between them. The biggest difference from previous research is that IGADEW synthesizes the optimization objects and obtain various parameters through genetic algorithm (GA). Second, the fitness function considers the weights of robustness and distortion, aiming to find the optimal balance between the two. IGADEW uses the Hash-based Message Authentication Code (HMAC) algorithm to encrypt the experimental parameters and uses the primary key hash algorithm for data grouping, both to ensure robustness. And the data distortion is limited with the help of threshold constraints. Finally, experiments using the UCI dataset demonstrate the effectiveness of IGADEW. Experimental results show that, compared with existing methods, IGADEW is more robust against common attacks, with lower data distortion. © 2023 IEEE.

关键词： Copyrights

来源：评论

学校读者我要写书评

暂无评论

Disk based pay-as-you-go record linkage

引用

Frontiers of computer Science 2022年第4期16卷 227-229页

作者： Chenchen Sun Derong Shen Key Laboratory of Computer Vision and System(Ministry of Education) Tianjin University of TechnologyTianjin300384China College of Intelligence and Computing Tianjin UniversityTianjin300350China School of Computer Science and Engineering Northeastern UniversityShenyang110189China

1Introduction Record linkage(RL)groups_records corresponding to the same entities in datasets,and is a long-standing topic in data management and mining communities[1-2].In big data era,real-time data applications become popular,and callfor payas-you-go RL(PRL),which produces as many match pairs as possible in very limited time(much shorter than the overall RLruntime).

关键词： record linkage mining

来源：评论

学校读者我要写书评

暂无评论

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent Diffusion 38

HairDiffusion: Vivid Multi-Colored Hair Editing via Latent D...

引用

38th Conference on Neural Information Processing systems, NeurIPS 2024

作者： Zeng, Yu Zhang, Yang Liu, Jiachen Shen, Linlin Deng, Kaijun He, Weizhao Wang, Jinbao Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China Shenzhen Institute of Artificial Intelligence and Robotics for Society China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Provincial Key Laboratory of Intelligent Information Processing China

Hair editing is a critical image synthesis task that aims to edit hair color and hairstyle using text descriptions or reference images, while preserving irrelevant attributes (e.g., identity, background, cloth). Many existing methods are based on StyleGAN to address this task. However, due to the limited spatial distribution of StyleGAN, it struggles with multiple hair color editing and facial preservation. Considering the advancements in diffusion models, we utilize Latent Diffusion Models (LDMs) for hairstyle editing. Our approach introduces Multi-stage Hairstyle Blend (MHB), effectively separating control of hair color and hairstyle in diffusion latent space. Additionally, we train a warping module to align the hair color with the target region. To further enhance multi-color hairstyle editing, we fine-tuned a CLIP model using a multi-color hairstyle dataset. Our method not only tackles the complexity of multi-color hairstyles but also addresses the challenge of preserving original colors during diffusion editing. Extensive experiments showcase the superiority of our method in editing multi-color hairstyles while preserving facial attributes given textual descriptions and reference images. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Ocean Scene Video Captioning with Multimodal Pre-Training and Video-Swin-Transformer 49

Enhancing Ocean Scene Video Captioning with Multimodal Pre-T...

引用

49th Annual Conference of the IEEE Industrial Electronics Society, IECON 2023

作者： Chen, Xinyu Zhao, Meng Shi, Fan Zhang, Meng'en He, Yu Chen, Shengyong School of Computer Science and Engineering Tianjin University of Technology Laboratory of Computer Vision and System of Ministry of Education Tianjin300384 China Technology and Engineering Center for Space Utilization Chinese Academy of Sciences Key Laboratory of Space Utilization Beijing100190 China

ISBN: (纸本)9798350331820

With the success of multimodal pre-training models in the video-language field and various downstream tasks, previous multimodal models used 3DCNN networks as video feature extractors, which have limitations in interacting and fusing with text features. This paper proposes a multimodal pre-training model that utilizes a Video-Swin-Transformer-based network to encode both video and text data, to achieve better performance in video understanding. The model consists of four modules: video encoder, text encoder, interact encoder, and caption decoder to accomplish the task of ocean scene video captioning. A dataset of ocean scene videos, including various content types such as sea surfaces and shores, is also constructed. The training process is divided into two stages: pre-training and fine-tuning. Pre-training is performed on the Howto100m dataset to allow the model to learn video captions in natural scenes and complete video-language matching tasks. The fine-tuning stage is then performed on the ocean1000 dataset to better understand the events and content in ocean scene videos and generate captions that conform to ocean scene video descriptions. The model achieves satisfying results on both the public dataset YouCook2 and the proprietary dataset Ocean1000, demonstrating its ability in video-text information fusion and interaction. © 2023 IEEE.

关键词： Signal encoding

来源：评论

学校读者我要写书评

暂无评论

Pose-guided feature region-based fusion network for occluded person re-identification

Pose-guided feature region-based fusion network for occluded...

引用

作者： Xie, Gengsheng Wen, Xianbin Yuan, Liming Wang, Jianchen Guo, Changlun Jia, Yansong Li, Minghao School of Computer Science and Engineering Tianjin University of Technology Tianjin300384 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin300384 China Tianjin Key Laboratory of Intelligence Computing and Novel Software Technology Tianjin300384 China

Learning distinguishing features from training datasets while filtering features of occlusions is critical to person retrieval scenarios. Most of the current person re-identification (Re-ID) methods based on classification or deep metric representation learning tend to overlook occlusion issues on the training set. Such representations from obstacles are easily over-fitted and misleading due to being considered as a part of the human body. To alleviate the occlusion problem, we propose a pose-guided feature region-based fusion network (PFRFN), to utilize pose landmarks as guidance to guide local learning for a good property of local feature, and the representation learning risk is evaluated on each part loss separately. Compared with only using global classification loss, concurrently considering local loss and the results of robust pose estimation enable the deep network to learn the representations of the body parts that prominently displayed in the image and gain the discriminative faculties on occluded scenes. Experimental results on multiple datasets, i.e., Market-1501, DukeMTMC, CUHK03, demonstrate the effectiveness of our method in a variety of scenarios. © 2021, The Author(s), under exclusive licence to Springer-Verlag GmbH, DE part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Light field imaging based on a parallel SVM method for recognizing 2D fake pedestrians

引用

Optoelectronics Letters 2022年第1期18卷 48-53页

作者： JIA Chen ZHANG Yao SHI Fan ZHAO Meng Key Laboratory of Computer Vision and System of Ministry of Education Tianjin Key Laboratory of Intelligence Computing and Novel Software TechnologyTianjin University of TechnologyTianjin 300384China The MOE Key Laboratory of Weak-Light Nonlinear Photonics Nankai UniversityTianjin 300457China

It is novel to apply three-dimensional(3D)light field imaging technology to recognize two-dimensional(2D)fake *** this paper,we propose a parallel support vector machine(SVM)method based on 3D light field imaging(light field camera)and machine learning techniques.A light field(LF)camera with robust sensors,which is able to record rich 3D information,is used as hardware *** of oriented gradient(HOG)feature extraction algorithm and SVM classification method are used to recognize the real and 2D fake pedestrians ***,we carry out an experiment on our improved LF pedestrian *** experimental results of parameter optimization study show that in the case of 400 training samples(200 positive samples and 200 negative samples),120 to 420 testing samples,and an HOG cellsize as 8×8,the best recognition accuracy with polynomial kernel function is improved by more than 2%compared with the previous *** best accuracy is 99.17%.Otherwise,the recognition accuracy of more than 98.00%will be obtained even under other experimental conditions.

关键词： hardware field method

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：