检索结果-内蒙古大学图书馆

17th Asian Conference on computer Vision, ACCV 2024

作者： Xu, Meng Lin, Mingying Ren, Qi Jia, Sen College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9789819609109

Transformer-based methods have improved the quality of hyperspectral images (HSIs) reconstructed from RGB by effectively capturing their remote relationships. The self-attention mechanisms in existing Transformer models have not fully considered the spatial sparsity and spectral continuity characteristics of HSIs and fail to effectively filter out significant features, resulting in lower-quality reconstruction results. This paper proposes a sparse spectral transformer model for HSI reconstruction (SSTHyper) to address this limitation, adaptively preserving crucial features. The network consists of an encoder-decoder structure capable of learning shallow and deep spatial-spectral priors, primarily composed of sparse spectral self-attention groups. Introducing a sparse spectral self-attention mechanism allows adaptive masking of non-significant details, enhancing reconstruction accuracy. Meanwhile, a lightweight cross-level fusion network is proposed to reduce model parameters and computational costs to enhance spatial-spectral feature extraction. Experimental results on two benchmark datasets demonstrate the outstanding performance of the proposed method. The code will be released at SSTHyper. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

CLIP-Based Cross-Level Semantic Interaction and Recombination Network for Composed Image Retrieval 27

CLIP-Based Cross-Level Semantic Interaction and Recombinatio...

引用

27th European Conference on Artificial Intelligence, ECAI 2024

作者： Liu, Zhihang Huang, Qiang Zhu, Yingying College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9781643685489

Composed image retrieval seeks to retrieve a target image that fulfills both modalities based on the user's query, which comprises a modified text and a reference image. Although existing studies introduce novel multi-modal feature fusion techniques at the global or local level, they ignore exploring the cross-level semantic correspondence and recombining the original and target features in the reference image and the modified text, and the problems of modal inconsistency. To address these issues, we propose a CLIP-based Cross-Level Semantic Interaction and Recombination Network (SeIR). Specifically, we first resort the image and text encoders of the CLIP pre-trained model to narrow the modal gap between image and text, and extract both global and local features. We also introduce a cross-modal attention mechanism to screen out original and target features by exploring the semantic correlation between the cross-level image and text features. Subsequently, to alleviate the modal difference between the generated composed query representation and the target image, we utilize an affine transformation technique to recombine the original and target features from the image and text. Extensive experiments on the FashionIQ and CIRR benchmark datasets demonstrate the competitive performance of the proposed SeIR compared to the state-of-the-art methods. © 2024 The Authors.

关键词： Affine transforms

来源：评论

学校读者我要写书评

暂无评论

Expensive Optimization Based on Evolutionary Multi-Tasking and Hybrid Restart Strategy 13

Expensive Optimization Based on Evolutionary Multi-Tasking a...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Li, Zhenyuan Ma, Xiaoliang Zhu, Zexuan Li, Yueyue College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)9798350308365

Evolutionary Algorithms (EAs) can not handle expensive optimization problems (EOPs) well due to the limited function evaluations in EOPs. To address this challenge, surrogate-assisted evolutionary algorithms (SAEAs) have been widely used and obtained good performance. With the problem dimension increases, SAEAs encounter some challenges in relatively high complexity on the training time and prediction time. To address this, this article proposes a novel expensive optimization algorithm with evolutionary multi-tasking and hybrid restart strategy (HRS-EMT). In the surrogate model construct, two radial basis function (RBF) models with different kernel functions are trained on all evaluated data to provide diversity and then are solved by a multi-tasking optimizer to a better optimization performance. In the surrogate model management, HRS-EMT combines multiple RBF models into an ensemble RBF (ERBF) model, strategically applied in the initial population pre-selection of surrogate model. Based on the prediction of ERBF surrogate model, HRS-EMT can obtain a better initial population in high dimensions. HRS-EMT is validated on twelve benchmark functions and compared with other state-of-the-art SAEAs. Experimental studies have shown the superior or comparable performance to other popular SAEAs in addressing EOPs. © 2024 IEEE.

关键词： evolutionary multitasking Expensive optimization infill criteria surrogate-assisted optimization

来源：评论

学校读者我要写书评

暂无评论

CLIP-Flow:Decoding images encoded in CLIP space

引用

Computational Visual Media 2024年第6期10卷 1157-1168页

作者： Hao Ma Ming Li Jingyuan Yang Or Patashnik Dani Lischinski Daniel Cohen-Or Hui Huang Visual Computing Research Center College of Computer Science and Software EngineeringShenzhen UniversityShenzhen 518060China Department of Computer Science Tel Aviv UniversityTel Aviv 6997801Israel School of Computer Science and Engineering the Hebrew University of JerusalemJerusalem 91904Israel

This study introduces CLIP-Flow,a novel network for generating images from a given image or *** effectively utilize the rich semantics contained in both modalities,we designed a semantics-guided methodology for image-and text-to-image *** particular,we adopted Contrastive Language-Image Pretraining(CLIP)as an encoder to extract semantics and StyleGAN as a decoder to generate images from such ***,to bridge the embedding space of CLIP and latent space of StyleGAN,real NVP is employed and modified with activation normalization and invertible *** the images and text in CLIP share the same representation space,text prompts can be fed directly into CLIP-Flow to achieve text-to-image *** conducted extensive experiments on several datasets to validate the effectiveness of the proposed image-to-image synthesis *** addition,we tested on the public dataset Multi-Modal CelebA-HQ,for text-to-image *** validated that our approach can generate high-quality text-matching images,and is comparable with state-of-the-art methods,both qualitatively and quantitatively.

关键词： image-to-image text-to-image contrastive language-image pretraining(CLIP) flow StyleGAN

来源：评论

学校读者我要写书评

暂无评论

Classification of Fetal Cardiac Arrhythmia Using Heart Rate Variability and Machine Learning 5

Classification of Fetal Cardiac Arrhythmia Using Heart Rate ...

引用

5th International Conference on Advancements in Computational Sciences, ICACS 2024

作者： Shahid, Muhammad Arslan Shaukat, Arslan Akram, Muhammad Usman Butt, Wasi Haider College of Electrical and Mechanical Engineering Department of Computer and Software Engineering Islamabad Pakistan

ISBN: (纸本)9798350394764

Fetal arrhythmias can lead to cardiac failure or death;thus, early detection is crucial but challenged by noise and artifacts. This paper investigates fetal arrhythmia detection using time, frequency, and non-linear Heart Rate Variability (HRV) features extracted from fetal ECG signals in the NIFEEG dataset. Machine learning classifiers including Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Decision Tree, XGBoost, Naive Bayes, and Convolutional Neural Network (CNN) are evaluated. The HRV features provide insights into fetal heart rate patterns. While SVM, KNN, Decision Tree, and XGBoost show promise, CNN demonstrates the highest performance with 98.16% accuracy, 100% sensitivity, 96.15% specificity, and 98.11% F1-score. This highlights CNN's potential for early and reliable fetal arrhythmia detection. Statistical analysis supports the significance of HRV features, paving the way for improved prenatal monitoring. To further improve model generalizability, future work should focus on expanding the dataset size, exploring advanced deep neural network architectures such as LSTMs, and integrating supplementary physiological inputs like uterine contractions. Overall, this study demonstrates the capabilities of HRV-based machine learning approaches, especially CNNs, for robust fetal arrhythmia detection, offering valuable clinical implications for early diagnosis and management. © 2024 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

GTE: learning code AST representation efficiently and effectively

引用

Science China(Information Sciences) 2025年第3期68卷 393-394页

作者： Yihao QIN Shangwen WANG Bo LIN Kang YANG Xiaoguang MAO College of Computer Science and Technology National University of Defense Technology Key Laboratory of Software Engineering for Complex Systems National University of Defense Technology

With the development of deep learning in recent years, code representation learning techniques have become the foundation of many software engineering tasks such as program classification [1] and defect detection. Earlier approaches treat the code as token sequences and use CNN, RNN, and the Transformer models to learn code representations.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A novel thermally-stable single-phase phosphor Ca_(2)InTaO_(6):Dy^(3+)for NUV-excited white LEDs

引用

Journal of Rare Earths 2024年第10期42卷 1855-1864页

作者： Jian Hu Ruirui Cui Jun Zhang Peng Linghu Youzhen Shi Xiang Guo Key Laboratory of Micro-Nano-Electronics and Software Technology of Guizhou Province College of Big Data and Information EngineeringGuizhou UniversityGuiyang550025China College of Computer and Information Engineering Guizhou University of CommerceGuiyang550014China

The work focuses on the utilization of the conventional solid-state sintering procedure to synthesize white phosphors Ca_(2)InTaO_(6):xDy^(3+)(0.02≤x≤0.12).Utilizing X-ray diffraction,the phase structure of samples was examined,and the crystal structure was refined using the Rietveld method.A scanning electron microscope was used to analyze the microstructure of ***-principles calculations confirm that the indirect bandgap of Ca_(2)InTaO_(6)is 3.786 eV,The luminous properties and energy transfer mechanism of Ca_(2)InTaO_(6):xDy^(3+)were studied using photoluminescence ***^(4)F_(9/2)→^(6)H_(13/2)transition of Dy^(3+)ions is responsible for the greatest emission peak,which was measured at 575 *** to research,the lifespan falls as the concentration of Dy^(3+)doping amount rises because of frequent interaction and ene rgy transfer between Dy^(3+)*** correlated color temperature of the WLEDs packaged with Ca_(2)InTaO_(6):0.08Dy^(3+)is 4677 K and CIE 1931 chromaticity coordinates are(0.3578,0.3831).Meantime,the phosphor also shows outstanding te mperature stability property,which maintains 83.8%of its initial emission intensity at 450 K(activation energy of 0.1467 eV).The W-LEDs retain their performance for 100 min when powered at 3.4 V voltage and 600 mA current,demonstrating the packed W-LEDs'sustaine d operation at high temperatures.

关键词： Ca_(2)InTaO_(6):Dy^(3+)phosphors Thermal stability Photoluminescence W-LEDs Thermal imaging Rare earths

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Energy Optimization:Efficient Path Selection in Wireless Sensor Networks with Hybrid ANN

引用

computers, Materials & Continua 2024年第5期79卷 2945-2970页

作者： Muhammad Salman Qamar Ihsan ulHaq Amil Daraz Atif MAlamri Salman A.AlQahtani Muhammad Fahad Munir Department of Electrical and Computer Engineering International Islamic UniversityIslamabad44000Pakistan School of Information Science and Engineering NingboTech UniversityNingbo315100China Software Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11495Saudi Arabia Computer Engineering Department College of Computer and Information SciencesKing Saud UniversityRiyadh11495Saudi Arabia

In pursuit of enhancing the Wireless Sensor Networks(WSNs)energy efficiency and operational lifespan,this paper delves into the domain of energy-efficient routing ***,the limited energy resources of Sensor Nodes(SNs)are a big challenge for ensuring their efficient and reliable *** data gathering involves the utilization of a mobile sink(MS)to mitigate the energy consumption problem through periodic network *** mobile sink(MS)strategy minimizes energy consumption and latency by visiting the fewest nodes or predetermined locations called rendezvous points(RPs)instead of all cluster heads(CHs).CHs subsequently transmit packets to neighboring *** unique determination of this study is the shortest path to reach *** the mobile sink(MS)concept has emerged as a promising solution to the energy consumption problem in WSNs,caused by multi-hop data collection with static *** this study,we proposed two novel hybrid algorithms,namely“ Reduced k-means based on Artificial Neural Network”(RkM-ANN)and“Delay Bound Reduced kmeans with ANN”(DBRkM-ANN)for designing a fast,efficient,and most proficient MS path depending upon rendezvous points(RPs).The first algorithm optimizes the MS’s latency,while the second considers the designing of delay-bound paths,also defined as the number of paths with delay over bound for the *** methods use a weight function and k-means clustering to choose RPs in a way that maximizes efficiency and guarantees network-wide *** addition,a method of using MS scheduling for efficient data collection is *** simulations and comparisons to several existing algorithms have shown the effectiveness of the suggested methodologies over a wide range of performance indicators.

关键词： Wireless Sensor Networks(WSNs) mobile sink(MS) rendezvous point(RP) machine learning Artificial Neural Networks(ANNs)

来源：评论

学校读者我要写书评

暂无评论

On learning the right attention point for feature enhancement

引用

Science China(Information Sciences) 2023年第1期66卷 131-143页

作者： Liqiang LIN Pengdi HUANG Chi-Wing FU Kai XU Hao ZHANG Hui HUANG College of Computer Science and Software Engineering Shenzhen University Department of Computer Science and Engineering The Chinese University of Hong Kong School of Computer Science National University of Defense Technology School of Computing Science Simon Fraser University

We present a novel attention-based mechanism to learn enhanced point features for point cloud processing tasks, e.g., classification and segmentation. Unlike prior studies, which were trained to optimize the weights of a pre-selected set of attention points, our approach learns to locate the best attention points to maximize the performance of a specific task, e.g., point cloud classification. Importantly, we advocate the use of single attention point to facilitate semantic understanding in point feature learning. Specifically,we formulate a new and simple convolution, which combines convolutional features from an input point and its corresponding learned attention point(LAP). Our attention mechanism can be easily incorporated into state-of-the-art point cloud classification and segmentation networks. Extensive experiments on common benchmarks, such as Model Net40, Shape Net Part, and S3DIS, all demonstrate that our LAP-enabled networks consistently outperform the respective original networks, as well as other competitive alternatives, which employ multiple attention points, either pre-selected or learned under our LAP framework.

关键词： point convolution feature enhancement attention point deep neural network

来源：评论

学校读者我要写书评

暂无评论

Active self-training for weakly supervised 3D scene semantic segmentation

引用

Computational Visual Media 2024年第3期10卷 425-438页

作者： Gengxin Liu Oliver van Kaick Hui Huang Ruizhen Hu College of Computer Science&Software Engineering Shenzhen UniversityShenzhen 518060China School of Computer Science Carleton UniversityOttawa K1S 5B6Canada

Since the preparation of labeled datafor training semantic segmentation networks of pointclouds is a time-consuming process, weakly supervisedapproaches have been introduced to learn fromonly a small fraction of data. These methods aretypically based on learning with contrastive losses whileautomatically deriving per-point pseudo-labels from asparse set of user-annotated labels. In this paper, ourkey observation is that the selection of which samplesto annotate is as important as how these samplesare used for training. Thus, we introduce a methodfor weakly supervised segmentation of 3D scenes thatcombines self-training with active learning. Activelearning selects points for annotation that are likelyto result in improvements to the trained model, whileself-training makes efficient use of the user-providedlabels for learning the model. We demonstrate thatour approach leads to an effective method that providesimprovements in scene segmentation over previouswork and baselines, while requiring only a few userannotations.

关键词： semantic segmentation weakly supervised self-training active learning

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：