检索结果-内蒙古大学图书馆

2021 IEEE/CIC International Conference on Communications in China, ICCC Workshops 2021

作者： Lin, Rongfu Zhao, Tiesong Chen, Weiling Zheng, Yannan Wei, Hongan Fuzhou University Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou China

ISBN: (纸本)9781665439442

Marine biosphere monitoring is one of the crucial links to the understanding and protection of the marine environment. Moreover, underwater images play an important role in marine biosphere monitoring. Since the capture and transmission conditions are extremely poor in complicated underwater environments, images will suffer typical types of distortions significantly. Pre-evaluation of the image quality to facilitate subsequent processing becomes particularly important. Traditional Image Quality Assessment (IQA) methods are normally developed based on perceptual quality. Nevertheless, images are captured for understanding and analysis to achieve the purpose of intelligent monitoring. There are barriers between traditional IQA and IQA in marine biosphere monitoring. To address this issue, this paper focused on the fish detection task which is a vital task in marine biosphere monitoring. An Underwater Image quality database for Fish Detection (UIFD) is proposed based on the characteristics of the underwater environment. This database can be utilized as a benchmark to develop and evaluate underwater IQA. In addition, it can also be used to provide guidance for improving the performance of underwater fish detection algorithms. © 2021 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

Robust Model Aggregation for Federated Learning with Heterogeneous Clients 7

Robust Model Aggregation for Federated Learning with Heterog...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Xu, Ruiting Feng, Xinxin Zheng, Haifeng Fuzhou University Fujian Key Lab For Intelligent Processing and Wireless Transmission of Media Information Fuzhou China

ISBN: (纸本)9781665409506

This Federated learning has received extensive attention in recent years due to its potential in mitigating risks of intruding privacy. However, most of existing methods don't provide adequate consideration to the heterogeneity of client. Therefore these parameters are treated equally and aggregated with the same weight. As a result, the overall performance may be degraded because of straggling clients. In this paper, we propose an aggregation algorithm considering the accuracy of local model of heterogeneous clients. The server evaluates the accuracy of the uploaded local model with a benchmark dataset, and then updates model parameters according to the accuracy ratio. Experimental results show the model accuracy of our proposed method performs better than existing methods. At the same time, in the presence of noisy users, it can eliminate their effect by assigning lower aggregation weights to them. © 2021 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Surface Material Classification Based On Tapping Sound Characteristics 7

Surface Material Classification Based On Tapping Sound Chara...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Wang, Kai Zeng, Hongji Feng, Weize Zheng, Quanfei Fang, Ying Fuzhou University Fujian Key Lab For Intelligent Processing and Wireless Transmission of Media Information Fuzhou China

ISBN: (纸本)9781665409506

Target material recognition is of great significance for robot grasping and manipulation. Humans can easily recognize objects through a combination of multiple senses. However, it is difficult to distinguish objects with the same shape but completely different internal materials for a vision-only robot. This paper proposes, for the first time a surface material classification based on tapping sound features to make up for the lack of machine vision. The algorithm includes audio data collection, data preprocessing and category judgment, etc. To evaluate the performance of the algorithm, we performed two tasks: distinguishing the category of objects based on the audio and judging whether the two audios are from the same category of objects. Experimental results show that the accuracy of the two tasks reaches 87% and 98%, respectively. This is enough to prove the feasibility of the algorithm in this paper. © 2021 IEEE.

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

Deep Motion Vector Prediction for Versatile Video Coding 7

Deep Motion Vector Prediction for Versatile Video Coding

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Li, Lanlan Wu, Kexin Wei, Hongan Liu, Jiaqi Fang, Ying Zheng, Haifeng Fujian Key Lab For Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China

ISBN: (纸本)9781665409506

Versatile video coding (VVC) has made significant progress in the compression efficiency of video coding. It achieves better performance and halves bitrate compared to the high efficiency video coding (HEVC) under the same visual quality. However, the complexity of VVC has also been significantly increased, especially in inter prediction. This paper proposes an improved motion vector prediction method based on neural networks for motion estimation (ME). Firstly, dynamic weights are proposed in the process of selecting the best MVP for advanced motion vector prediction (AMVP);secondly, we build the motion vector prediction model based on the deep neural network;finally, the model is embedded in VVC to acquire a more accurate MVP and reduce the encoding complexity of ME. Experimental results show that the proposed algorithm can reduce the encoding time of motion estimation under the premise of guaranteeing video quality. © 2021 IEEE.

关键词： Motion estimation

来源：评论

学校读者我要写书评

暂无评论

Physics-Environment Interaction Network for Dense Crowd Behavior Recognition

SSRN

引用

SSRN 2024年

作者： Yu, Jiaqi Zhou, Yanshan Pan, Renjie Lai, Pingrui Yang, Hua Institute of Image Communication and Network Engineering Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University Shanghai200240 China

The analysis of large-scale crowd behavior plays a crucial role in public safety. However, intelligent systems face three major challenges in analyzing dense crowd behavior: the severe occlusion between individuals, the variability in behavior patterns, and the complexity of behavioral evolution. To address these challenges, we propose the Physics-Environment Interaction Network (PEIN), which directly models the motion characteristics of a group with its physics attributes. Specifically, our method consists of two streams. The first stream is the physics-informed crowd property stream, which leverages on the similarity between dense crowd motion and fluid dynamics, using the Navier-Stokes (N-S) equation from fluid mechanics as the modeling framework to describe crowd motion. Considering the inherent relationship between the terms in the N-S equation and various crowd properties (collectiveness, conflict, uniformity and stability), we model these terms with operators and neural networks guided by these crowd properties, enabling the modeling of crowd motion characteristic without relying on the extraction of individual motion information. The second stream is the environment perception stream. Considering that the physics-informed crowd property stream mainly focuses on instantaneous information and that scenes with dense crowd behavior have variability, we introduce a 3D network to enhance the model's robustness. This stream can extract global spatiotemporal information from input video frames, providing a comprehensive perception of the surrounding crowd environment. Since the two streams process different data sources, we design a dual cross-attention mechanism to to enable between features from different modalities, resulting in a joint learnable representation for the final crowd behavior recognition. By incorporating physical laws as constraints, we design a physics-informed loss function combined with a crowd behavior loss function to optimize the model. Consi

关键词： Navier Stokes equations

来源：评论

学校读者我要写书评

暂无评论

Semantic segmentation of pyramidal neuron skeletons using geometric deep learning

引用

Journal of Innovative Optical Health Sciences 2023年第6期16卷 69-76页

作者： Lanlan Li Jing Qi Yi Geng Jingpeng Wu Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University FuzhouFujian 350116P.R.China Center for Computational Neuroscience Flatiron Institute New York 10010USA

Neurons can be abstractly represented as skeletons due to the filament nature of *** the rapid development of imaging and image analysis techniques,an increasing amount of neuron skeleton data is being *** some scienti fic studies,it is necessary to dissect the axons and dendrites,which is typically done manually and is both tedious and *** automate this process,we have developed a method that relies solely on neuronal skeletons using Geometric Deep Learning(GDL).We demonstrate the effectiveness of this method using pyramidal neurons in mammalian brains,and the results are promising for its application in neuroscience studies.

关键词： Pyramidal neuron geometric deep learning neuron skeleton semantic segmentation point cloud.

来源：评论

学校读者我要写书评

暂无评论

Personalized Federated Learning with Neighbor Aggregation for Traffic Flow Prediction

Personalized Federated Learning with Neighbor Aggregation fo...

引用

International Conference on Computer and Communications (ICCC)

作者： Junxin Guo Xinxin Feng Haifeng Zheng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou China

As an important part of Intelligent Transportation System (ITS), traffic flow prediction has attracted more and more attention from academia and industry. However, since traffic flow data are distributed among different organizations, traditional centralized learning methods are no longer applicable, thus federated learning has begun to play an important role in traffic flow prediction tasks. In this paper, we design an improved traffic flow prediction model based on federated learning. At the same time, we consider the interaction of topology and feature space between traffic data owned by different organizations, and propose a method named Federated Neighbor Aggregation (FedNe). The server update the model parameters with both the physical connectivity and similarity relationships between the organizations, and finally generate a personalized model for each organization. Experimental results on real-world dataset show that our proposed method has the lowest average MAE and average RMSE. Finally, based on our method, when new clients participate, they can also quickly obtain their personalized models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Target Parameter Estimation with Deep Unfolding Networks for MIMO-OFDM Based Integrated Sensing and Communication Systems

Target Parameter Estimation with Deep Unfolding Networks for...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Jingcai Lin Haifeng Zheng Xinxin Feng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou China

The multiple-input multiple-output orthogonal frequency division multiplexing (MIMO-OFDM) technology shows great potential in integrated sensing and communication (ISAC) systems. To address the challenges posed by the high computational complexity and low estimation accuracy of traditional target parameter estimation methods in a MIMO-OFDM based ISAC system, this paper introduces a compressed sensing based approach for target parameter estimation. We first derive the channel model within the MIMO-OFDM system, and then reformulate the problem of target parameter estimation as a least absolute shrinkage and selection operator (LASSO) problem. Furthermore, we propose a model-driven network, termed FISTA-Net, which deeply unfolds the fast iterative shrinkage thresholding algorithm (FISTA) into a deep neural network to solve the LASSO problem. Experimental results show that the proposed FISTA-Net algorithm outperforms the existing methods in terms of estimation accuracy and computation efficiency for MIMO-OFDM based target parameter estimation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Background Clustering Pre-Training for Few-Shot Segmentation

Background Clustering Pre-Training for Few-Shot Segmentation

引用

IEEE International Conference on Image processing

作者： Zhimiao Yu Tiancheng Lin Yi Xu Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University Chongqing Research Institute of Shanghai Jiao Tong University

Recent few-shot segmentation (FSS) methods introduce an extra pre-training stage before meta-training to obtain a stronger backbone, which has become a standard step in few-shot learning. Despite the effectiveness, current pre-training scheme suffers from the merged background problem: only base classes are labelled as foregrounds, making it hard to distinguish between novel classes and actual background. In this paper, we propose a new pre-training scheme for FSS via decoupling the novel classes from background, called Background Clustering Pre-Training (BCPT). Specifically, we adopt online clustering to the pixel embeddings of merged background to explore the underlying semantic structures, bridging the gap between pre-training and adaptation to novel classes. Given the clustering results, we further propose the background mining loss and leverage base classes to guide the clustering process, improving the quality and stability of clustering results. Experiments on PASCAL-5 i and COCO-20 i show that BCPT yields advanced performance. Code will be available at https://***/Carboxy/BCPT.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Traffic Flow Prediction Based on Stream Tensor Analysis 2021

Traffic Flow Prediction Based on Stream Tensor Analysis

引用

2021 The 9th International Conference on Information Technology: IoT and Smart City

作者： Haitao Zhang Xinxin Feng Lingchao He Haifeng Zheng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University China

ISBN: (纸本)9781450384971

In intelligent transportation system (ITS), traffic flow prediction can provide data support for route planning, traffic management and public safety. Prediction algorithms based on machine learning or deep learning usually need a large number of unabridged historical data to conduct parameter training. However, data will be missing and abnormal in practice, which will affect the accuracy of prediction. In this paper, we propose the stream tensor analysis (STA) algorithm for traffic flow prediction. First, dynamic tensor stream of four dimensions of space, time, day and week is constructed to better mine the multi-mode correlation between traffic flow data. Second, the first few columns with the largest norm are selected to update the projection matrix by the tracking projection matrix algorithm. The experimental results show that the STA algorithm has low complexity, and also achieve good prediction performance in random missing and extreme missing patterns.

关键词： Traffic Flow Prediction Tensor Analysis Projection Matrix

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：