检索结果-内蒙古大学图书馆

Akane: Perplexity-Guided Time Series data Cleaning

Proceedings of the ACM on Management of data 2024年第3期2卷 1-26页

作者： Xiaoyu Han Haoran Xiong Zhenying He Peng Wang Chen Wang X. Sean Wang School of Computer Science Fudan University Shanghai China Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China National Engineering Research Center for Big Data Software EIRI Tsinghua University Beijing China

Dirty data are prevalent in time series, such as energy consumption or stock data. Existing data cleaning algorithms present shortcomings in dirty data identification and unsatisfactory cleaning decisions. To handle these drawbacks, we leverage inherent recurrent patterns in time series, analogize them as fixed combinations in textual data, and incorporate the concept of perplexity. The cleaning problem is thus transformed to minimize the perplexity of the time series under a given cleaning cost, and we design a four-phase algorithmic framework to tackle this problem. To ensure the framework's feasibility, we also conduct a brief analysis of the impact of dirty data and devise an automatic budget selection strategy. Moreover, to make it more generic, we additionally introduce advanced solutions, including an ameliorative probability calculation method grounded in the homomorphic pattern aggregation and a greedy-based heuristic algorithm for resource savings. Experiments on 12 real-world datasets demonstrate the superiority of our methods.

关键词： data cleaning perplexity recurrent patterns time series

来源：评论

学校读者我要写书评

暂无评论

Harnessing Monotonic Neural Networks for Performance Prediction and Threshold Determination in Multichannel Detection

引用

IEEE Transactions on Signal Processing 2025年

作者： Zhou, Rui Pu, Wenqiang You, Ming-Yi Shi, Qingjiang The Chinese University of Hong Kong-Shenzhen Shenzhen Research Institute of Big Data Guangdong China National Key Laboratory of Electromagnetic Space Security Jiaxing China Tongji University School of Software Engineering Shanghai China Shenzhen Research Institute of Big Data Shenzhen China

Despite extensive research on numerous multichannel detection methods, predicting their performance remains difficult due to the high dimensionality of raw data and the complexity of the detection process. To tackle this, we introduce a special type of neural network designed to predict detection performance under specific environmental conditions. We utilize a monotonic neural network (MNN) to develop PdMonoNet, which ensures that the influence of input parameters on the output probability of detection is monotonic. This approach also facilitates the determination of thresholds. We provide a theoretical analysis of the universal approximation capabilities and prediction error of the network architectures we employ. Numerical experiments conducted on both synthetic datasets and real-world scenarios within the context of multichannel spectrum sensing demonstrate the effectiveness and robustness of PdMonoNet in predicting detection performance and determining thresholds. © 1991-2012 IEEE.

关键词： Signal detection

来源：评论

学校读者我要写书评

暂无评论

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-Preserving Talking Face Synthesis

DEGSTalk: Decomposed Per-Embedding Gaussian Fields for Hair-...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Kaijun Deng Dezhi Zheng Jindong Xie Jinbao Wang Weicheng Xie Linlin Shen Siyang Song Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Guangdong Provincial Key Laboratory of Intelligent Information Processing Department of Computer Science University of Exeter

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Accurately synthesizing talking face videos and capturing fine facial features for individuals with long hair presents a significant challenge. To tackle these challenges in existing methods, we propose a decomposed per-embedding Gaussian fields (DEGSTalk), a 3D Gaussian Splatting (3DGS)-based talking face synthesis method for generating realistic talking faces with long hairs. Our DEGSTalk employs Deformable Pre-Embedding Gaussian Fields, which dynamically adjust pre-embedding Gaussian primitives using implicit expression coefficients. This enables precise capture of dynamic facial regions and subtle expressions. Additionally, we propose a Dynamic Hair-Preserving Portrait Rendering technique to enhance the realism of long hair motions in the synthesized videos. Results show that DEGSTalk achieves improved realism and synthesis quality compared to existing approaches, particularly in handling complex facial dynamics and hair preservation. Our code is available at https://***/CVI-SZU/DEGSTalk.

关键词： Hair Training Three-dimensional displays Dynamics Signal processing Rendering (computer graphics) Noise measurement Speech processing Faces Videos

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Domain Adaption Harnessing Vision-Language Pre-training

arXiv

引用

arXiv 2024年

作者： Zhou, Wenlve Zhou, Zhiheng School of Electronic and Information Engineering South China University of Technology Guangdong Guangzhou510641 China Key Laboratory of Big Data and Intelligent Robot Ministry of Education South China University of Technology Guangzhou510641 China

This paper addresses two vital challenges in Unsupervised Domain Adaptation (UDA) with a focus on harnessing the power of Vision-Language Pre-training (VLP) models. Firstly, UDA has primarily relied on ImageNet pre-trained models. However, the potential of VLP models in UDA remains largely unexplored. The rich representation of VLP models holds significant promise for enhancing UDA tasks. To address this, we propose a novel method called Cross-Modal Knowledge Distillation (CMKD), leveraging VLP models as teacher models to guide the learning process in the target domain, resulting in state-of-the-art performance. Secondly, current UDA paradigms involve training separate models for each task, leading to significant storage overhead and impractical model deployment as the number of transfer tasks grows. To overcome this challenge, we introduce Residual Sparse Training (RST) exploiting the benefits conferred by VLP's extensive pre-training, a technique that requires minimal adjustment (approximately 0.1%∼0.5%) of VLP model parameters to achieve performance comparable to fine-tuning. Combining CMKD and RST, we present a comprehensive solution that effectively leverages VLP models for UDA tasks while reducing storage overhead for model deployment. Furthermore, CMKD can serve as a baseline in conjunction with other methods like FixMatch, enhancing the performance of UDA. Our proposed method outperforms existing techniques on standard benchmarks. Our code will be available at: https://***/Wenlve-Zhou/VLP-UDA. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Semantic-Constraint Matching Transformer for Weakly Supervised Object Localization

arXiv

引用

arXiv 2023年

作者： Cao, Yiwen Su, Yukun Wang, Wenjun Liu, Yanxia Wu, Qingyao The School of Software Engineering South China University of Technology Guangzhou510640 China The Key Laboratory of Big Data and Intelligent Robot Ministry of Education Guangzhou China The School of Computer Science and Engineering Nanyang Technological University Singapore The Pazhou Lab Guangzhou China

Weakly supervised object localization (WSOL) strives to learn to localize objects with only image-level supervision. Due to the local receptive fields generated by convolution operations, previous CNN-based methods suffer from partial activation issues, concentrating on the object's discriminative part instead of the entire entity scope. Benefiting from the capability of the self-attention mechanism to acquire long-range feature dependencies, Vision Transformer has been recently applied to alleviate the local activation drawbacks. However, since the transformer lacks the inductive localization bias that are inherent in CNNs, it may cause a divergent activation problem resulting in an uncertain distinction between foreground and background. In this work, we proposed a novel Semantic-Constraint Matching Network (SCMN) via transformer to converge on the divergent activation. Specifically, we first propose a local patch shuffle strategy to construct the image pairs, disrupting local patches while guaranteeing global consistency. The paired images that contain the common object in spatial are then fed into the Siamese network encoder. We further design a semantic-constraint matching module, which aims to mine the co-object part by matching the coarse class activation maps (CAMs) extracted from the pair images, thus implicitly guiding and calibrating the transformer network to alleviate the divergent activation. Extensive experimental results conducted on two challenging benchmarks including CUB-200-2011 and ILSVRC datasets show that our method can achieve the new state-of-the-art performance and outperform the previous method by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Chemical activation

来源：评论

学校读者我要写书评

暂无评论

RFC:a feature selection algorithm for software defect prediction

引用

Journal of Systems engineering and Electronics 2021年第2期32卷 389-398页

作者： XU Xiaolong CHEN Wen WANG Xinheng Jiangsu Key Laboratory of Big Data Security&Intelligent Processing Nanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Big Data Research at Yancheng Nanjing University of Posts and TelecommunicationsYancheng 224000China School of Computing and Engineering University of West LondonLondon W55RFUK

software defect prediction(SDP)is used to perform the statistical analysis of historical defect data to find out the distribution rule of historical defects,so as to effectively predict defects in the new ***,there are redundant and irrelevant features in the software defect datasets affecting the performance of defect *** order to identify and remove the redundant and irrelevant features in software defect datasets,we propose ReliefF-based clustering(RFC),a clusterbased feature selection ***,the correlation between features is calculated based on the symmetric *** to the correlation degree,RFC partitions features into k clusters based on the k-medoids algorithm,and finally selects the representative features from each cluster to form the final feature *** the experiments,we compare the proposed RFC with classical feature selection algorithms on nine National Aeronautics and Space Administration(NASA)software defect prediction datasets in terms of area under curve(AUC)and *** experimental results show that RFC can effectively improve the performance of SDP.

关键词： software defect prediction(SDP) feature selection cluster

来源：评论

学校读者我要写书评

暂无评论

WMFormer++: Nested Transformer for Visible Watermark Removal via Implict Joint Learning

arXiv

引用

arXiv 2023年

作者： Huo, Dongjian Zhang, Zehong Su, Hanjing Li, Guanbin Fang, Chaowei Wu, Qingyao School of Software and Engineering South China University of Technology China Key Laboratory of Big Data and Intelligent Robot Ministry of Education Peng Cheng Laboratory China Tencent Wechat Department School of Computer Science and Engineering Sun Yat-sen University China Xidian University China

Watermarking serves as a widely adopted approach to safeguard media copyright. In parallel, the research focus has extended to watermark removal techniques, offering an adversarial means to enhance watermark robustness and foster advancements in the watermarking field. Existing watermark removal methods mainly rely on UNet with task-specific decoder branches——one for watermark localization and the other for background image restoration. However, watermark localization and background restoration are not isolated tasks;precise watermark localization inherently implies regions necessitating restoration, and the background restoration process contributes to more accurate watermark localization. To holistically integrate information from both branches, we introduce an implicit joint learning paradigm. This empowers the network to autonomously navigate the flow of information between implicit branches through a gate mechanism. Furthermore, we employ cross-channel attention to facilitate local detail restoration and holistic structural comprehension, while harnessing nested structures to integrate multiscale information. Extensive experiments are conducted on various challenging benchmarks to validate the effectiveness of our proposed method. The results demonstrate our approach’s remarkable superiority, surpassing existing state-ofthe-art methods by a large margin. Copyright © 2023, The Authors. All rights reserved.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Dual Encoders for Diffusion-based Image Inpainting

Dual Encoders for Diffusion-based Image Inpainting

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Dezhi Zheng Kaijun Deng Jinbao Wang Linlin Shen Computer Vision Institute School of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Guangdong Provincial Key Laboratory of Intelligent Information Processing Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Current diffusion-based inpainting models struggle to preserve unmasked regions or generate highly coherent content. Additionally, it is hard for them to generate meaningful content for 3D inpainting. To tackle these challenges, we design a plug-and-play branch that runs through the entire generation process to enhance existing models. Specifically, we utilize dual encoders - a Convolutional Neural Network (CNN) encoder and the pre-trained Variational AutoEncoder (VAE) encoder, to encode masked images. The latent code and the feature map from the dual encoders are fed to diffusion models simultaneously. In addition, we apply Zero-padded initialization to solve the problem of mode collapse caused by this branch. Experiments on BrushBench and EditBench demonstrate that models with our plug-and-play branch can improve the coherence of inpainting, and our model achieves new state-of-the-art results.

关键词： Visualization Three-dimensional displays Codes Autoencoders Coherence Signal processing Diffusion models Decoding Convolutional neural networks Speech processing

来源：评论

学校读者我要写书评

暂无评论

Local Entropy Based Fuzzy Connectedness Segmentation for Thyroid Ultrasound Images

Local Entropy Based Fuzzy Connectedness Segmentation for Thy...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Yixuan Fu Kai Li Junying Chen Key Laboratory of Big Data and Intelligent Robot (SCUT) Ministry of Education School of Software Engineering South China University of Technology Guangzhou China Department of Ultrasound Third Affiliated Hospital of Sun Yat-sen University Guangzhou China

Although deep learning methods are popular in recent years to achieve dominant image segmentation performance, the carefully annotated training images are very difficult to obtain in clinical medicine, and the deep learning model training demands a lot of computing resources which are not always available. To overcome these difficulties, it is very necessary to investigate segmentation algorithms which do not require any training data. In this work, we improve a semi-automatic conventional segmentation algorithm, fuzzy connectedness segmentation, by introducing the local information entropy of the ultrasound image into the fuzzy affinity membership function. The proposed semi-automatic local entropy based fuzzy connectedness (LEFC) segmentation algorithm is further modified by incorporating the popular deep learning methods to make the LEFC algorithm fully automatic. The proposed semi-automatic LEFC algorithm achieves better performance than other representative fuzzy connectedness segmentation algorithms with the accuracy and IoU values increased by 5.9~14% and 5~10.5%, and achieves very close segmentation performance as compared with the best deep learning model in the experiments (0.2% lower accuracy and 0.2% lower IoU compared to CE-Net). Besides, the automatic LEFC algorithm improves the segmentation results obtained by the corresponding deep learning based coarse segmentation modules with the accuracy and IoU increased by 0.2~8% and 0.1~3.8%, respectively. Furthermore, the experiment results demonstrate that the proposed automatic LEFC algorithm obtains stably good segmentation performance even with limited training data, achieving the accuracy and IoU values (at the stable state) 23.6 % and 18.5% higher than those of the corresponding U-Net model which is trained with the samesized dataset.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Automatic Deep Active Contour Model Based on Local Image Characteristics

Automatic Deep Active Contour Model Based on Local Image Cha...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Haijun You Kai Li Junying Chen Key Laboratory of Big Data and Intelligent Robot (SCUT) Ministry of Education School of Software Engineering South China University of Technology Guangzhou China Department of Ultrasound Third Affiliated Hospital of Sun Yat-sen University Guangzhou China

In recent years, convolutional neural networks have made remarkable achievements in medical image segmentation. Unclear margins and fuzzy boundary regions are formed surrounding the thyroid gland area under the influence of artifacts and speckles, which increases the difficulty of thyroid ultrasound image segmentation. However, building an effective CNN model usually requires massive computing resources, long training time, and large amounts of carefully labeled data. In this work, we develop a fast, compact, accurate and robust image segmentation model for automatic thyroid segmentation in medical ultrasound images. We propose an automatic deep active contour (DAC) model based on local image characteristics, which utilizes the deep neural network model to obtain the initial contour and constructs external energy items based on the local image characteristics of contour points. Compared with the deep neural network model, the DAC model requires less training data, and the segmentation performance of the DAC model on a small dataset can reach that of the deep neural network model on a larger dataset. The proposed DAC model can be used for automatic thyroid segmentation in medical ultrasound images, which does not require massive computing resources, long training time, and large amounts of carefully labeled data.

关键词：

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：