检索结果-内蒙古大学图书馆

On learning the right attention point for feature enhancement

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

VCGAE++: variational collective graph autoEncoder for multi-behavior recommendation

引用

Knowledge and Information Systems 2025年 1-30页

作者： Zhuang, Yingxuan Liu, Yang Pan, Weike Ming, Zhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China Shenzhen Technology University Shenzhen China

Variational autoencoder (VAE) is known as a classic and effective method in modeling users’ homogeneous behaviors in recommender systems. In recent years, graph neural networks (GNNs) have achieved promising performance in learning users’ preferences by modeling complex relationships between users and items. However, most VAE- and GNN-based methods are for single-behavior recommendation, rather than the more prevalent counterpart in real-world applications, i.e., multi-behavior recommendation. This motivates us to leverage VAE and GNNs to address the more important and challenging problem of multi-behavior recommendation. Traditional multi-behavior recommendation models have not captured the complex transition relationships across different types of behaviors well, ignoring the varying semantic strength of different types of behaviors. In addition, most of them just construct separate behavior-specific subgraphs and learn separate collaborative filtering embeddings, overlooking the information of the global graph. Moreover, existing methods rarely explored how to deal with the sparse data under the target behavior (e.g., purchase). To tackle the above four challenges, we propose a novel multi-behavior recommendation framework named VCGAE++, which inherits the advantages of VCGAE (Variational Collective Graph AutoEncoder) to fully exploit the multi-behavior data and model the high-order relationships to improve the accuracy of the recommendations. Specifically, we design a multi-behavior contrastive learning framework to capture the complex transitions between diverse behaviors. In addition, we design a global graph information fusion network to capture the high-level relationships across different user-item interaction graphs. Extensive experiments on four real-world datasets clearly demonstrate the effectiveness of our VCGAE++ compared with the state-of-the-art methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature

关键词： Graph neural networks

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

Enhancing Arabic Cyberbullying Detection with End-to-End Transformer Model

引用

computer Modeling in engineering & sciences 2024年第11期141卷 1651-1671页

作者： Mohamed A.Mahdi Suliman Mohamed Fati Mohamed A.G.Hazber Shahanawaj Ahamad Sawsan A.Saad Information and Computer Science Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Information Systems Department College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Software Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia Computer Engineering Department College of Computer Science and EngineeringUniversity of Ha’ilHa’il55476Saudi Arabia

Cyberbullying,a critical concern for digital safety,necessitates effective linguistic analysis tools that can navigate the complexities of language use in online *** tackle this challenge,our study introduces a new approach employing Bidirectional Encoder Representations from the Transformers(BERT)base model(cased),originally pretrained in *** model is uniquely adapted to recognize the intricate nuances of Arabic online communication,a key aspect often overlooked in conventional cyberbullying detection *** model is an end-to-end solution that has been fine-tuned on a diverse dataset of Arabic social media(SM)tweets showing a notable increase in detection accuracy and sensitivity compared to existing *** results on a diverse Arabic dataset collected from the‘X platform’demonstrate a notable increase in detection accuracy and sensitivity compared to existing methods.E-BERT shows a substantial improvement in performance,evidenced by an accuracy of 98.45%,precision of 99.17%,recall of 99.10%,and an F1 score of 99.14%.The proposed E-BERT not only addresses a critical gap in cyberbullying detection in Arabic online forums but also sets a precedent for applying cross-lingual pretrained models in regional language applications,offering a scalable and effective framework for enhancing online safety across Arabic-speaking communities.

关键词： Cyberbullying offensive detection Bidirectional Encoder Representations from the Transformers(BERT) continuous bag of words Social Media natural language processing

来源：评论

学校读者我要写书评

暂无评论

Confidence-based Class Relation Embedding for Few-shot Domain Adaptation

Confidence-based Class Relation Embedding for Few-shot Domai...

引用

2024 International Symposium on Internet of Things and Smart Cities, ISITSC 2024

作者： Jia, Baoxi Chen, Junyang Wu, Yirui College of Computer Science and Software Engineering Hohai University Nanjing China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9798331505516

In visual tasks such as image classification, the presence of domain shift often renders deep neural network models trained solely on specific datasets unable to generalize to new domains. In practical applications, due to the high cost of annotating rare data, it is extremely challenging to label all source domain samples comprehensively. Moreover, existing unsupervised domain adaptation methods often lack modeling of class relationships. Therefore, we propose a few-shot unsupervised domain adaptation method based on confidence-guided class relationship embedding. This approach aims to identify high-confidence target samples corresponding to sparsely labeled source samples, forming an inter-domain cross-mixed dataset. By constructing inter-domain contrastive learning, we explicitly guide the transfer of knowledge from the source domain to the target domain, leveraging the domain invariance of class relationships. Additionally, considering the varying learning difficulties of different target samples, we have devised an intra-domain class relationship contrastive loss, which leverages easy samples to facilitate the learning of difficult-to-classify samples. Experiments demonstrate that this model contributes to enhancing the performance of domain adaptation tasks. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Digital twin driven and intelligence enabled content delivery in end-edge-cloud collaborative 5G networks

引用

Digital Communications and Networks 2024年第2期10卷 328-336页

作者： Bo Yi Jianhui Lv Xingwei Wang Lianbo Ma Min Huang College of Computer Science and Engineering Northeastern UniversityShenyang110169China Pengcheng Lab. Shenzhen518055China College of Software Northeastern UniversityShenyang110819China College of Information Science and Engineering Northeastern UniversityShenyang110819China

The rapid development of 5G/6G and AI enables an environment of Internet of Everything(IoE)which can support millions of connected mobile devices and applications to operate smoothly at high speed and low ***,these massive devices will lead to explosive traffic growth,which in turn cause great burden for the data transmission and content *** challenge can be eased by sinking some critical content from cloud to *** this case,how to determine the critical content,where to sink and how to access the content correctly and efficiently become new *** work focuses on establishing a highly efficient content delivery framework in the IoE *** particular,the IoE environment is re-constructed as an end-edge-cloud collaborative system,in which the concept of digital twin is applied to promote the *** on the digital asset obtained by digital twin from end users,a content popularity prediction scheme is firstly proposed to decide the critical content by using the Temporal Pattern Attention(TPA)enabled Long Short-Term Memory(LSTM)***,the prediction results are input for the proposed caching scheme to decide where to sink the critical content by using the Reinforce Learning(RL)***,a collaborative routing scheme is proposed to determine the way to access the content with the objective of minimizing *** experimental results indicate that the proposed schemes outperform the state-of-the-art benchmarks in terms of the caching hit rate,the average throughput,the successful content delivery rate and the average routing overhead.

关键词： Digital twin IoE Content delivery Caching Routing

来源：评论

学校读者我要写书评

暂无评论

GazeREC-Net: Advancing Gaze Restoration in Low-Light Conditions

IAENG International Journal of Computer Science

引用

IAENG International Journal of computer science 2024年第12期51卷 2034-2042页

作者： Ku, Jiayin Wang, Li School of Computer Science and software Engineering University of Science and Technology Liaoning Anshan114051 China College of Computer Science and Tech nology Liaoning Anshan114051 China

Gaze estimation technology is essential for applications such as human-computer interaction, augmented reality, and virtual reality. However, its accuracy is significantly compromised in low-light conditions due to degraded image quality. To address this, we developed GazeREC-Net, an innovative gaze restoration method. We simulated low-light conditions on the MPIIFaceGaze and ColumbiaGaze datasets, creating a specialized degraded dataset for training and testing our model. GazeREC-Net combines Fourier transform techniques with advanced image restoration algorithms, significantly enhancing image quality and optimizing gaze information recovery and extraction in low-light environments. Our evaluations using Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index (SSIM) metrics demonstrated a PSNR improvement of 7.64% and an SSIM improvement of 5.75% compared to HINet. Additionally, GazeREC-Net outperformed CFTNet and other existing gaze estimation models, including Gaze-TR, Dilated-Net, CA-Net, L2CS-Net, and MTGLS, in reducing gaze estimation error. These findings validate the effectiveness of GazeREC-Net in low-light conditions and offer new research directions for applying gaze estimation technologies in complex lighting environments. © (2024), (International Association of Engineers). All rights reserved.

关键词： Augmented reality

来源：评论

学校读者我要写书评

暂无评论

A Dual-stage Teacher-Student Representation Learning Framework for Semi-supervised Cardiac Image Segmentation

A Dual-stage Teacher-Student Representation Learning Framewo...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Yifan Zhao, Jiajun Zhao, Yang Yang, Xuan College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350386226

This study introduces a novel generative adversarial network (GAN)-based Dual-stage Teacher-Student Representation Learning (GDL) framework designed to extract effective representations from unlabeled data for cardiac image segmentation. The GDL framework employs an adversarial augmentation approach, simultaneously training a generation model to produce diverse samples and a teacher-student model to learn image representations iteratively. During the pre-training stage, a generator is trained using a diversity-enhanced contrastive loss to generate diverse augmented samples. Subsequently, in the first stage, the generator is further supervised by enforcing dissimilarity between representations produced by the teacher and student models, aiming to expand the image representation space of generated images. In the second stage, the student model is trained to transfer distilled knowledge acquired from the augmented samples to the teacher model to improve its generalization performance in the image segmentation task. Our proposed model ensures that the diverse generated samples correspond precisely to their pseudo-labels, facilitating learning semantic representations from unlabeled data. Experimental results on public cardiac MR datasets demonstrate that our model surpasses the performance of state-of-the-art semi-supervised learning networks. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

BGHR: Bridging the Gap Between HBox-Supervised and RBox-Supervised Oriented Object Detection via Adaptive Fine-Grained Sample Mining 39

BGHR: Bridging the Gap Between HBox-Supervised and RBox-Supe...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Fu, Chenlin Zhu, Yingying College of Computer Science and Software Engineering Shenzhen University China

ISBN: (纸本)157735897X

Oriented object detection is crucial for complex scenes such as aerial images and industrial inspection, providing precise delineation by minimizing background interference. Recently, the weakly-supervised detector paradigm H2RBox has demonstrated promise in learning rotated bounding box (RBox) from the more readily available horizontal bounding box (HBox), alleviating the scarcity and high cost of RBox annotations. However, these H2RBox-based methods have primarily focused on the gap in orientation information between HBox- and RBox-supervised approaches, overlooking the gap in training sample selection. In response, we propose the Adaptive Fine-grained Sample Mining (AFSM) strategy, which improves the selection of fine-grained training samples in HBox-supervised methods. AFSM assigns the best-matching prediction RBox to each ground truth (GT) HBox and selects positive samples based on these paired boxes. Furthermore, to effectively filter the best-matching prediction RBox for AFSM, we introduce the Prediction Rbox Assignment (PRA) scheme, employing Kullback-Leibler Divergence (KLD) as a localization quality metric. Additionally, we introduce an improved self-supervised branch loss (Lss*) to address the symmetry of weakly-supervised branch prediction boxes. Incorporating these core components (AFSM, PRA, and Lss*), we develop an end-to-end network architecture (BGHR) to further bridge the gap between HBox- and RBox-supervised oriented object detection. Extensive experiments on DOTA-v1.0 and DIOR-R demonstrate that BGHR achieves state-of-the-art performance compared to HBox-supervised methods without additional overhead. Even when benchmarked against fully supervised FCOS, our method still exhibits a slight performance advantage. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Modified Bat Algorithm: a newly proposed approach for solving complex and real-world problems

引用

Soft Computing 2024年第13-14期28卷 7983-7998页

作者： Umar, Shahla U. Rashid, Tarik A. Ahmed, Aram M. Hassan, Bryar A. Baker, Mohammed Rashad Department of Software College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq Computer Science and Engineering Department School of Science and Engineering University of Kurdistan Hewler KRI Erbil Iraq Department of Computer Science College of Science Charmo University Sulaimani Chamchamal46023 Iraq

Bat Algorithm (BA) is a nature-inspired metaheuristic search algorithm designed to efficiently explore complex problem spaces and find near-optimal solutions. The algorithm is inspired by the echolocation behavior of bats, which acts as a signal system to estimate the distance and hunt prey. Although the BA has proven effective for various optimization problems, it exhibits limited exploration ability and susceptibility to local optima. The algorithm updates velocities and positions based on the current global best solution, causing all agents to converge toward a specific location, potentially leading to local optima issues in optimization problems. On this premise, this paper proposes the Modified Bat Algorithm (MBA) as an enhancement to address the local optima limitation observed in the original BA. MBA incorporates the frequency and velocity of the current best solution, enhancing convergence speed to the optimal solution and preventing local optima entrapment. While the original BA faces diversity issues, both the original BA and MBA are introduced. To assess MBA’s performance, three sets of test functions (classical benchmark functions, CEC2005, and CEC2019) are employed, with results compared to those of the original BA, Particle Swarm Optimization (PSO), Genetic Algorithm (GA), and Dragonfly Algorithm (DA). The outcomes demonstrate the MBA’s significant superiority over other algorithms. In addition, MBA successfully addresses a real-world assignment problem (call center problem), traditionally solved using linear programming methods, with satisfactory results. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Swarm intelligence

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：