检索结果-南通市图书馆

Controllable multi-domain semantic artwork synthesis

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computational Visual Media 2024年第2期10卷 355-373页

作者： Yuantian Huang Satoshi Iizuka Edgar Simo-Serra Kazuhiro Fukui Department of computer science University of TsukubaTsukuba 305-8577Japan Department of computer science and engineering Waseda UniversityTokyo 169-8050Japan

We present a novel framework for the multidomain synthesis of artworks from semantic *** of the main limitations of this challenging task is the lack of publicly available segmentation datasets for art *** address this problem,we propose a dataset called ArtSem that contains 40,000 images of artwork from four different domains,with their corresponding semantic label *** first extracted semantic maps from landscape photography and used a conditional generative adversarial network(GAN)-based approach for generating high-quality artwork from semantic maps without requiring paired training ***,we propose an artwork-synthesis model using domain-dependent variational encoders for high-quality multi-domain ***,the model was improved and complemented with a simple but effective normalization method based on jointly normalizing semantics and style,which we call spatially style-adaptive normalization(SSTAN).Compared to the previous methods,which only take semantic layout as the input,our model jointly learns style and semantic information representation,improving the generation quality of artistic *** results indicate that our model learned to separate the domains in the latent ***,we can perform fine-grained control of the synthesized artwork by identifying hyperplanes that separate the different ***,by combining the proposed dataset and approach,we generated user-controllable artworks of higher quality than that of existing approaches,as corroborated by quantitative metrics and a user study.

关键词： semantic artwork synthesis generative adversarial network(GAN) datasets non-photorealistic rendering

Meta label associated loss for fine-grained visual recognition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第6期67卷 230-247页

作者： Yanchao LI Fu XIAO Hao LI Qun LI Shui YU School of computer science Nanjing University of Posts and Telecommunications School of Network engineering Zhoukou Normal University School of computer science University of Technology Sydney

Recently, intensive attempts have been made to design robust models for fine-grained visual recognition, most notably are the impressive gains for training with noisy labels by incorporating a reweighting strategy into a meta-learning framework. However, it is limited to up or downweighting the contribution of an instance for label reweighting approaches in the learning process. To solve this issue, a novel noise-tolerant method with auxiliary web data is proposed. Specifically, first, the associations made from embeddings of well-labeled data with those of web data and back at the same class are measured. Next, its association probability is employed as a weighting fusion strategy into angular margin-based loss, which makes the trained model robust to noisy datasets. To reduce the influence of the gap between the well-labeled and noisy web data, a bridge schema is proposed via the corresponding loss that encourages the learned embeddings to be coherent. Lastly, the formulation is encapsulated into the meta-learning framework, which can reduce the overfitting of models and learn the network parameters to be noise-tolerant. Extensive experiments are performed on benchmark datasets, and the results clearly show the superiority of the proposed method over existing state-of-the-art approaches.

关键词： label associated loss weighting noisy samples fine-grained visual recognition noise-tolerant learning meta-learning

ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 771-781页

作者： Ho Yin Au Jie Chen Junkun Jiang Yike Guo Department of computer science Hong Kong Baptist UniversityHong Kong 999077China Department of computer science and engineering The Hong Kong University of Science and EngineeringHong Kong 999077China

To generate dance that temporally and aesthetically matches the music is a challenging problem in three ***,the generated motion should be beats-aligned to the local musical ***,the global aesthetic style should be matched between motion and *** third,the generated motion should be diverse and *** address these challenges,we propose ReChoreoNet,which re-choreographs high-quality dance motion for a given piece of music.A data-driven learning strategy is proposed to efficiently correlate the temporal connections between music and motion in a progressively learned cross-modality embedding *** beats-aligned content motion will be subsequently used as autoregressive context and control signal to control a normalizing-flow model,which transfers the style of a prototype motion to the final generated *** addition,we present an aesthetically labelled music-dance repertoire(MDR)for both efficient learning of the cross-modality embedding,and understanding of the aesthetic connections between music and *** demonstrate that our repertoire-based framework is robustly extensible in both content and *** quantitative and qualitative experiments have been carried out to validate the efficiency of our proposed model.

关键词： Generative model cross-modality learning normalizing flow tempo synchronization style transfer.

Multi-scale persistent spatiotemporal transformer for long-term urban traffic flow prediction

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Electronic science and Technology 2024年第1期22卷 53-69页

作者： Jia-Jun Zhong Yong Ma Xin-Zheng Niu Philippe Fournier-Viger Bing Wang Zu-kuan Wei School of computer science and engineering University of Electronic Science and Technology of ChinaChengdu611731China College of computer science&Software engineering Shenzhen UniversityShenzhen518060China School of computer science Southwest Petroleum UniversityChengdu610500China

Long-term urban traffic flow prediction is an important task in the field of intelligent transportation,as it can help optimize traffic management and improve travel *** improve prediction accuracy,a crucial issue is how to model spatiotemporal dependency in urban traffic *** recent years,many studies have adopted spatiotemporal neural networks to extract key information from traffic ***,most models ignore the semantic spatial similarity between long-distance areas when mining spatial *** also ignore the impact of predicted time steps on the next unpredicted time step for making long-term ***,these models lack a comprehensive data embedding process to represent complex spatiotemporal *** paper proposes a multi-scale persistent spatiotemporal transformer(MSPSTT)model to perform accurate long-term traffic flow prediction in *** adopts an encoder-decoder structure and incorporates temporal,periodic,and spatial features to fully embed urban traffic data to address these *** model consists of a spatiotemporal encoder and a spatiotemporal decoder,which rely on temporal,geospatial,and semantic space multi-head attention modules to dynamically extract temporal,geospatial,and semantic *** spatiotemporal decoder combines the context information provided by the encoder,integrates the predicted time step information,and is iteratively updated to learn the correlation between different time steps in the broader time range to improve the model’s accuracy for long-term *** on four public transportation datasets demonstrate that MSPSTT outperforms the existing models by up to 9.5%on three common metrics.

关键词： Graph neural network Multi-head attention mechanism Spatio-temporal dependency Traffic flow prediction

Dynamic Hand Gesture-Based Person Identification Using Leap Motion and Machine Learning Approaches

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第4期79卷 1205-1222页

作者： Jungpil Shin Md.AlMehedi Hasan Md.Maniruzzaman Taiki Watanabe Issei Jozume School of computer science and engineering The University of AizuAizuwakamatsuFukushima965-8580Japan Department of computer science&engineering Rajshahi University of Engineering&TechnologyRajshahi6204Bangladesh

Person identification is one of the most vital tasks for network security. People are more concerned about theirsecurity due to traditional passwords becoming weaker or leaking in various attacks. In recent decades, fingerprintsand faces have been widely used for person identification, which has the risk of information leakage as a resultof reproducing fingers or faces by taking a snapshot. Recently, people have focused on creating an identifiablepattern, which will not be reproducible falsely by capturing psychological and behavioral information of a personusing vision and sensor-based techniques. In existing studies, most of the researchers used very complex patternsin this direction, which need special training and attention to remember the patterns and failed to capturethe psychological and behavioral information of a person properly. To overcome these problems, this researchdevised a novel dynamic hand gesture-based person identification system using a Leap Motion sensor. Thisstudy developed two hand gesture-based pattern datasets for performing the experiments, which contained morethan 500 samples, collected from 25 subjects. Various static and dynamic features were extracted from the handgeometry. Randomforest was used to measure feature importance using the Gini Index. Finally, the support vectormachinewas implemented for person identification and evaluate its performance using identification accuracy. Theexperimental results showed that the proposed system produced an identification accuracy of 99.8% for arbitraryhand gesture-based patterns and 99.6% for the same dynamic hand gesture-based patterns. This result indicatedthat the proposed system can be used for person identification in the field of security.

关键词： Person identification leap motion hand gesture random forest support vector machine

Local saliency consistency-based label inference for weakly supervised salient object detection using scribble annotations

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 239-249页

作者： Shuo Zhao Peng Cui Jing Shen Haibo Liu School of computer science and Technology Harbin University of Science and TechnologyHarbinChina School of computer science and Technology Harbin Engineering UniversityHarbinChina

Recently,weak supervision has received growing attention in the field of salient object detection due to the convenience of ***,there is a large performance gap between weakly supervised and fully supervised salient object detectors because the scribble annotation can only provide very limited foreground/background ***,an intuitive idea is to infer annotations that cover more complete object and background regions for *** this end,a label inference strategy is proposed based on the assumption that pixels with similar colours and close positions should have consistent ***,k-means clustering algorithm was first performed on both colours and coordinates of original annotations,and then assigned the same labels to points having similar colours with colour cluster centres and near coordinate cluster ***,the same annotations for pixels with similar colours within each kernel neighbourhood was set *** experiments on six benchmarks demonstrate that our method can significantly improve the performance and achieve the state-of-the-art results.

关键词： label inference salient object detection weak supervision

A blockchain based privacy-preserving federated learning scheme for Internet of Vehicles

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Digital Communications and Networks 2024年第1期10卷 126-134页

作者： Naiyu Wang Wenti Yang Xiaodong Wang Longfei Wu Zhitao Guan Xiaojiang Du Mohsen Guizani School of Control and computer engineering North China Electric Power UniversityChina Department of Mathematics&computer science Fayetteville State UniversityFayettevilleNCUSA Department of Electrical and computer engineering Stevens Institute of TechnologyHobokenNJ07030USA Department of computer science and engineering Qatar UniversityDohaQatar

The application of artificial intelligence technology in Internet of Vehicles(lov)has attracted great research interests with the goal of enabling smart transportation and traffic ***,concerns have been raised over the security and privacy of the tons of traffic and vehicle *** this regard,Federated Learning(FL)with privacy protection features is considered a highly promising ***,in the FL process,the server side may take advantage of its dominant role in model aggregation to steal sensitive information of users,while the client side may also upload malicious data to compromise the training of the global *** existing privacy-preserving FL schemes in IoV fail to deal with threats from both of these two sides at the same *** this paper,we propose a Blockchain based Privacy-preserving Federated Learning scheme named BPFL,which uses blockchain as the underlying distributed framework of *** improve the Multi-Krum technology and combine it with the homomorphic encryption to achieve ciphertext-level model aggregation and model filtering,which can enable the verifiability of the local models while achieving ***,we develop a reputation-based incentive mechanism to encourage users in IoV to actively participate in the federated learning and to practice *** security analysis and performance evaluations are conducted to show that the proposed scheme can meet the security requirements and improve the performance of the FL model.

关键词： Federated learning Blockchain Privacy-preservation Homomorphic encryption Internetof vehicles

Early Detection of Colletotrichum Kahawae Disease in Coffee Cherry Based on computer Vision Techniques

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computer Modeling in engineering & sciences 2024年第4期139卷 759-782页

作者： Raveena Selvanarayanan Surendran Rajendran Youseef Alotaibi Department of computer science and engineering Saveetha School of EngineeringSaveetha Institute of Medical and Technical ScienceChennai602105India Department of computer science College of Computer and Information SystemsUmm Al-Qura UniversityMakkah21955Saudi Arabia

Colletotrichum kahawae(Coffee Berry Disease)spreads through spores that can be carried by wind,rain,and insects affecting coffee plantations,and causes 80%yield losses and poor-quality coffee *** deadly disease is hard to control because wind,rain,and insects carry *** researchers utilized a deep learning system to identify CBD in coffee cherries at three growth stages and classify photographs of infected and uninfected cherries with 93%accuracy using a random forest *** the dataset is too small and noisy,the algorithm may not learn data patterns and generate accurate *** overcome the existing challenge,early detection of Colletotrichum Kahawae disease in coffee cherries requires automated processes,prompt recognition,and accurate *** proposed methodology selects CBD image datasets through four different stages for training and *** to train a model on datasets of coffee berries,with each image labeled as healthy or *** themodel is trained,SHAP algorithmto figure out which features were essential formaking predictions with the proposed *** of these characteristics were the cherry’s colour,whether it had spots or other damage,and how big the Lesions *** inception is important for classification to virtualize the relationship between the colour of the berry is correlated with the presence of *** evaluate themodel’s performance andmitigate excess fitting,a 10-fold cross-validation approach is *** involves partitioning the dataset into ten subsets,training the model on each subset,and evaluating its *** comparison to other contemporary methodologies,the model put forth achieved an accuracy of 98.56%.

关键词： computer vision coffee berry disease colletotrichum kahawae XG boost shapley additive explanations

A Gaussian Noise-Based Algorithm for Enhancing Backdoor Attacks

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

computers, Materials & Continua 2024年第7期80卷 361-387页

作者： Hong Huang Yunfei Wang Guotao Yuan Xin Li School of computer science and engineering Sichuan University of Science&EngineeringYibin644000China

Deep Neural Networks(DNNs)are integral to various aspects of modern life,enhancing work ***-less,their susceptibility to diverse attack methods,including backdoor attacks,raises security *** aim to investigate backdoor attack methods for image categorization tasks,to promote the development of DNN towards higher *** on backdoor attacks currently faces significant challenges due to the distinct and abnormal data patterns of malicious samples,and the meticulous data screening by developers,hindering practical attack *** overcome these challenges,this study proposes a Gaussian Noise-Targeted Universal Adversarial Perturbation(GN-TUAP)*** approach restricts the direction of perturbations and normalizes abnormal pixel values,ensuring that perturbations progress as much as possible in a direction perpendicular to the decision hyperplane in linear *** limits anomalies within the perturbations improves their visual stealthiness,and makes them more challenging for defense methods to *** verify the effectiveness,stealthiness,and robustness of GN-TUAP,we proposed a comprehensive threat *** on this model,extensive experiments were conducted using the CIFAR-10,CIFAR-100,GTSRB,and MNIST datasets,comparing our method with existing state-of-the-art attack *** also tested our perturbation triggers using various defense methods and further experimented on the robustness of the triggers against noise filtering *** experimental outcomes demonstrate that backdoor attacks leveraging perturbations generated via our algorithm exhibit cross-model attack effectiveness and superior ***,they possess robust anti-detection capabilities and maintain commendable performance when subjected to noise-filtering methods.

关键词： Image classification model backdoor attack gaussian distribution Artificial Intelligence(AI)security