检索结果-内蒙古大学图书馆

Learning a Detail-Oriented Transformer for Image Denoising 1

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Long, Xuan Liu, Mei-Qin Yao, Chao Jin, Shuo Lin, Chun-Yu Zhao, Yao Institute of Information Science Beijing Jiaotong University Beijing100044 China School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China

ISBN: (数字)9789819906055

ISBN: (纸本)9789819906048

CNN-based methods have achieved significant success in image denoising with powerful and generous local priors. However, these methods are not good at exploring non-local self-similarity which is also an effective prior for image denoising. To overcome this weakness, we propose a detail-oriented transformer with Dense Network for Image Denoising (DDNet), exploiting global and local self-similarity for better reconstruction quality. Specifically, DDNet consists of a global feature extraction branch and a detail-maintained graph attentive branch. The global feature extraction branch utilizes a number of densely connected transformer blocks for contextual information. The detail-maintained graph attentive branch employs a dynamic graph attentive network to distinguish the image structure and noises for retaining the texture details. Numerous experiments show the superiority of DDNet on real image denoising, synthetic image denoising, and image deraining. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Image denoising

来源：评论

学校读者我要写书评

暂无评论

A survey on graph neural network-based next POI recommendation for smart cities

引用

Journal of Reliable Intelligent Environments 2024年第3期10卷 299-318页

作者： Yu, Jian Guo, Lucas Zhang, Jiayu Wang, Guiling Department of Computer Science and Soft Engineering Auckland University of Technology Auckland New Zealand School of Information Science and Technology Beijing Key Laboratory on Integration and Analysis of Large-Scale Stream Data North China University of Technology Beijing China

Amid the rise of mobile technologies and Location-Based Social Networks (LBSNs), there’s an escalating demand for personalized Point-of-Interest (POI) recommendations. Especially pivotal in smart cities, these systems aim to enhance user experiences by offering location recommendations tailored to past check-ins and visited POIs. Distinguishing itself from traditional POI recommendations, the next POI approach emphasizes predicting the immediate subsequent location, factoring in both geographical attributes and temporal patterns. This approach, while promising, faces with challenges like capturing evolving user preferences and navigating data biases. The introduction of Graph Neural Networks (GNNs) brings forth a transformative solution, particularly in their ability to capture high-order dependencies between POIs, understanding deeper relationships and patterns beyond immediate connections. This survey presents a comprehensive exploration of GNN-based next POI recommendation approaches, delving into their unique characteristics, inherent challenges, and potential avenues for future research. © The Author(s) 2024.

关键词： Location based services

来源：评论

学校读者我要写书评

暂无评论

SIGVIC: Spatial Importance Guided Variable-Rate Image Compression 48

SIGVIC: Spatial Importance Guided Variable-Rate Image Compre...

引用

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Liang, Jiaming Liu, Meiqin Yao, Chao Lin, Chunyu Zhao, Yao Beijing Jiaotong University Institute of Information Science Beijing100044 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

ISBN: (纸本)9781728163277

Variable-rate mechanism has improved the flexibility and efficiency of learning-based image compression that trains multiple models for different rate-distortion tradeoffs. One of the most common approaches for variable-rate is to channel- wisely or spatial-uniformly scale the internal features. However, the diversity of spatial importance is instructive for bit allocation of image compression. In this paper, we introduce a Spatial Importance Guided Variable-rate Image Compression (SigVIC), in which a spatial gating unit (SGU) is designed for adaptively learning a spatial importance mask. Then, a spatial scaling network (SSN) takes the spatial importance mask to guide the feature scaling and bit allocation for variablerate. Moreover, to improve the quality of decoded image, Top-K shallow features are selected to refine the decoded features through a shallow feature fusion module (SFFM). Experiments show that our method outperforms other learning- based methods (whether variable-rate or not) and traditional codecs, with storage saving and high flexibility. © 2023 IEEE.

关键词： image compression scale factor shallow feature spatial importance variable-rate

来源：评论

学校读者我要写书评

暂无评论

Multi-frame Correlated Representation Network for Video Super-Resolution

Multi-frame Correlated Representation Network for Video Supe...

引用

2023 IEEE International Conference on computer, Information, and Telecommunication Systems, CITS 2023

作者： Jin, Shuo Liu, Meiqin Guo, Yu Yao, Chao Obaidat, Mohammad S. Institute of Information Science Beijing Jiaotong University Beijing China School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China King Abdullah Ii School of Information Technology The University of Jordan Amman11942 Jordan School of Computer and Communication Engineering University of Science and Technology Beijing Beijing100083 China The Amity University UP Noida201301 India

ISBN: (纸本)9798350336092

Video super-resolution aims to reconstruct the high-resolution video from its degraded observation. Existing methods primarily utilize explicit alignment strategies, including optical flow and motion compensation, and implicit alignment strategies, including deformable convolution and non-local attention, to model the temporal information. However, these alignment strategies with motion estimation and motion compensation (MEMC) introduce inaccurate inter-frame information to some extent, which largely affects the reconstruction performance. To avoid the error compensation information, we propose to model the temporal information from the perspective of the self-similarity between frames and design a multi-frame correlated representation network (MCRNet) for video super-resolution. To address the issue of temporal information distortion caused by large-scale pixel displacement and object occlusion, MCRNet extracts temporal information through similar regions on multiple frames, which are aggregated with allocated weights for information compensation. Moreover, we design a multi-scale non-local information fusion module for non-local correlation matching of spatio-temporal features in the multi-scale space, which maintains the scale consistency of spatio-temporal features. Experimental results indicate that MCRNet achieves promising gains over other competing methods which employ explicit and implicit alignment strategies on different datasets. © 2023 IEEE.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Physics-based fuid simulation in computer graphics: Survey, research trends, and challenges

引用

Computational Visual Media 2024年第5期10卷 803-858页

作者： Xiaokun Wang Yanrui Xu Sinuo Liu Bo Ren Jiri Kosinka Alexandru C.Telea Jiamin Wang Chongming Song Jian Chang Chenfeng Li Jian Jun Zhang Xiaojuan Ban Beijing Advanced Innovation Center for Materials Genome Engineering and School of Intelligence Science and Technologyand Shunde Innovation School University of Science and Technology BeijingBeijing 100083China National Center for Computer Animation Faculty of Media and CommunicationBournemouth UniversityPoole BH125BBUK. Bernoulli Institute University of GroningenGroningen 9700 AKthe Netherlands School of Computer Science Peking UniversityBeijing 100871China. TMCC College of Computer ScienceNankai UniversityTianjin 300350China Department of Information and Computing Sciences Utrecht UniversityUtrecht 3584 CCthe Netherlands. Zienkiewicz Institute for Modelling Data and AISwansea UniversitySwansea SA18ENUK. Institute of Materials Intelligent Technology Liaoning Academy of MaterialsShenyang 110004China.

Physics-based fluid simulation has played an increasingly important role in the computer graphics *** methods in this area have greatly improved the generation of complex visual effects and its computational *** techniques have emerged to deal with complex boundaries,multiphase fluids,gas-liquid interfaces,and fine *** parallel use of machine learning,image processing,and fluid control technologies has brought many interesting and novel research *** this survey,we provide an introduction to theoretical concepts underpinning physics-based fuid simulation and their practical implementation,with the aim for it to serve as a guide for both newcomers and seasoned researchers to explore the field of physics-based fuid simulation,with a focus on developments in the last *** by the distribution of recent publications in the field,we structure our survey to cover physical background;discretization approaches;computational methods that address scalability;fuid interactions with other materials and interfaces;and methods for expressive aspects of surface detail and *** a practical perspective,we give an overview of existing implementations available for the above methods.

关键词： computer graphics physical simulation fluid simulation fluid coupling

来源：评论

学校读者我要写书评

暂无评论

A straightforward spectral emissivity estimating method based on constructing random rough surfaces

引用

Light(science & Applications) 2023年第12期12卷 2577-2588页

作者： Zezhan Zhang Mengchao Chen Lichuan Zhang Hongzu Li Hairui Huang Zilong Zhang Peifeng Yu Yi Niu Shan Gao Chao Wang Jing Jiang Clean Energy Materials and Engineering Center School of Integrated Circuit Science and EngineeringUniversity of Electronic Science and Technology of ChinaChengduChina College of Information and Communication Engineering Harbin Engineering UniversityHarbinChina Department of Precision Instrument Tsinghua UniversityBeijingChina

Spectral emissivity is an essential and sensitive parameter to characterize the radiative capacity of the solid surface in scientific and engineering applications,which would be non-negligibly affected by surface ***,there is a lack of assessment of the effect of roughness on emissivity and a straightforward method for estimating the emissivity of rough *** paper established an estimating method based on constructing random rough surfaces to predict rough surface(Geometric region)emissivity for metal *** on this method,the emissivity of ideal gray and non-gray body surfaces was calculated and *** calculated and measured spectral emissivities of GH3044,K465,DD6,and TC4 alloys with different roughness were *** results show that the emissivity increases with the roughness degree,and the enhancement effect weakens with the increase of roughness or emissivity due to the existing limit(emissivityε=1.0).At the same time,the roughness would not change the overall spectral distribution characteristics but may attenuate the local features of the spectral *** estimated results are in good agreement with the experimental data for the above alloys'rough *** study provides a new reliable approach to obtaining the spectral emissivity of rough *** approach is especially beneficial for measuring objects in extreme environments where emissivity is difficult to ***,this study promotes an understanding of surface morphology's effect mechanism on emissivity.

关键词： alloys roughness estimating

来源：评论

学校读者我要写书评

暂无评论

Towards Open-Vocabulary Video Semantic Segmentation

引用

IEEE Transactions on Multimedia 2025年 27卷 2924-2934页

作者： Li, Xinhao Liu, Yun Sun, Guolei Wu, Min Zhang, Le Zhu, Ce University of Electronic Science and Technology of China School of Information and Communication Engineering Chengdu611731 China Nankai University College of Computer Science Tianjin300350 China ETH Zurich Computer Vision Lab Zurich8092 Switzerland 138632 Singapore

Semantic segmentation in videos has been a focal point of recent research. However, existing models encounter challenges when faced with unfamiliar categories. To address this, we introduce the Open Vocabulary Video Semantic Segmentation (OV-VSS) task, designed to accurately segment every pixel across a wide range of open-vocabulary categories, including those that are novel or previously unexplored. To enhance OV-VSS performance, we propose a robust baseline, OV2VSS, which integrates a spatial-temporal fusion module, allowing the model to utilize temporal relationships across consecutive frames. Additionally, we incorporate a random frame enhancement module, broadening the model's understanding of semantic context throughout the entire video sequence. Our approach also includes video text encoding, which strengthens the model's capability to interpret textual information within the video context. Comprehensive evaluations on benchmark datasets such as VSPW and Cityscapes highlight OV-VSS's zero-shot generalization capabilities, especially in handling novel categories. The results validate OV2VSS's effectiveness, demonstrating improved performance in semantic segmentation tasks across diverse video datasets. © 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

Efficient communication in Wireless Sensor Networks Using Optimized Energy Efficient Engroove Leach Clustering Protocol

引用

Tsinghua science and technology 2024年第4期29卷 985-1001页

作者： N.Meenakshi Sultan Ahmad A.V.Prabu J.Nageswara Rao Nashwan Adnan Othman Hikmat A.M.Abdeljaber R.Sekar Jabeen Nazeer SRM Institute of Science and Technology KattankulathurChennai 603203India Department of Computer Science College of Computer Engineering and SciencesPrince Sattam Bin Abdulaziz UniversityAlkharj 11942Saudi Arabia University Center for Research and Development(UCRD) Department of Computer Science and EngineeringChandigarh UniversityGharuanMohali 140413India Department of ECE Koneru Lakshmaiah Education FoundationVaddeswaramGuntur 522502India Department of Computer Science and Engineering Lakireddy Balireddy College of Engineering(A)NTR District 521230India Department of Computer Engineering College of EngineeringKnowledge UniversityErbil 44001Iraq Department of Computer Science Faculty of Information TechnologyApplied Science Private UniversityAmman 11937Jordan Department of Electronics and Communication Engineering(ECE) School of EngineeringPresidency UniversityBangalore 834001India

The Wireless Sensor Network(WSN)is a network that is constructed in regions that are inaccessible to human *** widespread deployment of wireless micro sensors will make it possible to conduct accurate environmental monitoring for a use in both civil and military *** make use of these data to monitor and keep track of the physical data of the surrounding environment in order to ensure the sustainability of the *** data have to be picked up by the sensor,and then sent to the sink node where they may be *** nodes of the WSNs are powered by batteries,therefore they eventually run out of *** energy restriction has an effect on the network life span and environmental *** objective of this study is to further improve the Engroove Leach(EL)protocol’s energy efficiency so that the network can operate for a very long time while consuming the least amount of *** lifespan of WSNs is being extended often using clustering and routing *** Meta Inspired Hawks Fragment Optimization(MIHFO)system,which is based on passive clustering,is used in this study to do *** cluster head is chosen based on the nodes’residual energy,distance to neighbors,distance to base station,node degree,and node *** on distance,residual energy,and node degree,an algorithm known as Heuristic Wing Antfly Optimization(HWAFO)selects the optimum path between the cluster head and Base Station(BS).They examine the number of nodes that are active,their energy consumption,and the number of data packets that the BS *** overall experimentation is carried out under the MATLAB *** the analysis,it has been discovered that the suggested approach yields noticeably superior outcomes in terms of throughput,packet delivery and drop ratio,and average energy consumption.

关键词： wireless sensor networks energy efficient engroove leach protocol meta inspired Hawks fragment optimization heuristic wing antfly optimization

来源：评论

学校读者我要写书评

暂无评论

Classification with ensembles and case study on functional magnetic resonance imaging

引用

Digital communications and Networks 2022年第1期8卷 80-86页

作者： Adnan OM.Abuassba Zhang Dezheng Hazrat Ali Fan Zhang Khan Ali Department of Computer Science Arab Open University-PalestineRamallahPalestine Department of Computer Science and Communication Engineering University of Science and Technology BeijingChina and Beijing Key Laboratory of Knowledge Engineering for Materials ScienceBeijing100083China Department of Electrical and Computer Engineering COMSATS University IslamabadAbbottabad CampusAbbottabadPakistan

The ensemble is a technique that strategically combines basic models to achieve better accuracy ***,combination methods,and selection topology are the main factors determining ensemble ***,it is a challenging task to design an efficient ensemble *** though numerous paradigms have been proposed to classify ensemble schemes,there is still much room for *** paper proposes a general framework for creating ensembles in the context of ***,the ensemble framework consists of four stages:objectives,data preparing,model training,and model *** is comprehensive to design diverse *** proposed ensemble approach can be used for a wide variety of machine learning *** validate our approach on real-world *** experimental results show the efficiency of the proposed approach.

关键词： Classification Ensemble learning Extreme learning machine

来源：评论

学校读者我要写书评

暂无评论

A transformer generative adversarial network for multi-track music generation

引用

CAAI Transactions on Intelligence technology 2022年第3期7卷 369-380页

作者： Cong Jin Tao Wang Xiaobing Li Chu Jie Jiessie Tie Yun Tie Shan Liu Ming Yan Yongzhi Li Junxian Wang Shenze Huang School of Information and Communication Engineering Communication University of ChinaBeijingChina School of Information and Engineering Zhengzhou UniversityZhengzhouChina Central Conservatory of Music BeijingChina Department of computer Science University of TorontoTorontoCanada School of Data Science and Media Intelligence Communication University of ChinaBeijingChina School of Light Industry and Engineering South China University of TechnologyGuangzhouChina School of Animation and Digital Arts Communication University of ChinaBeijingChina

This study proposes a new generation network based on transformers and guided by the music theory to produce high-quality music *** this study,the decoding block of the transformer is used to learn the internal information of single-track music,and cross-track transformers are used to learn the information amongst the tracks of different musical instruments.A reward network based on the music theory is proposed,which optimizes the global and local loss objective functions while training and discriminating the network so that the reward network can provide a reliable adjustment method for the generation of the *** method of combining the reward network and cross entropy loss is used to guide the training of the generator and produce high-quality music *** with other multi-track music generation models,the experimental results verify the validity of the model.

关键词： artificial intelligence deep learning multimedia

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：