检索结果-内蒙古大学图书馆

Data Compression Conference (DCC)

作者： Zhengang Li Jingchi Zhang Yonghua Wang Xing Zeng Zhen Zhang Yunlin Long Menghu Jia Ning Wang State Key Laboratory of Mobile Network and Mobile Multimedia Technology ZTE Corporation

ISBN: (数字)9798350385878

ISBN: (纸本)9798350385885

This paper presents a video coding scheme that combines traditional optimization methods with deep learning methods based on the Enhanced Compression Model (ECM). In order to achieve better subjective quality, we adjust the quantization parameter (QP) of every coding tree unit (CTU) adaptively according to the spatial-temporal perception information and block importance. In addition, the QP of key frame is individually adjusted according to the video content characteristics. Meanwhile, the deep learning methods propose a convolutional neural network-based loop filter (CNNLF), which is turned on/off based on the rate-distortion optimization at the CTU and frame level. Besides, intra-prediction using neural networks (NN-intra) is proposed to further improve compression quality, where 8 neural networks are used for predicting blocks of different sizes. On the validation set of the Challenge for Learning Image Compression (CLIC), the proposed method achieves remarkable higher compression quality than the conventional ECM 3.0 in terms of PSNR and subjective evaluation.

关键词： Video coding Deep learning Adaptation models Image coding Quantization (signal) Rate-distortion Optimization methods

来源：评论

学校读者我要写书评

暂无评论

Intra-Vehicle Optical networks 22

Intra-Vehicle Optical Networks

引用

22nd International Conference on Optical communications and networks, ICOCN 2024

作者： Liang, Qin Liu, Gordon Ning School of Electronic and Information Engineering Soochow University Jiangsu Suzhou215006 China Suzhou Key Laboratory of Advanced Optical Communication Network Technology Soochow University Suzhou China

Intelligent connected vehicles require high bandwidth due to the increased sensors and improved architectures. Optical communications provide several advantages over copper cables in intra-vehicle networks, but face m... 详细信息

ISBN: (纸本)9798350367652

关键词： Vehicle-to-grid

来源：评论

学校读者我要写书评

暂无评论

A method of flavors and fragrances identification based on hybrid neural network

A method of flavors and fragrances identification based on h...

引用

2023 International Conference on Computer Application and Information Security, ICCAIS 2023

作者： Zou, Yun Chen, Yan Zhou, Xiao Liang, Hailing China Tobacco Guangxi Industrial Co. Ltd. Guangxi Nanning530001 China School of Computer and Electronic Information Guangxi University Guangxi Nanning530004 China Guangxi Key Laboratory of Multimedia Communication and Network Technology Guangxi University Guangxi Nanning530004 China

ISBN: (纸本)9781510675032

Traditional spices quality testing methods face problems such as long testing latency, high testing cost, complicated testing process, environment-dependent inconsistency and great influence of human factors on the testing results. In order to solve these problems, this paper proposes a hybrid model based on Shuffled Frog Leaping Algorithm (Shuffled Frog Leaping Algorithm, SFLA) and Back Propagation (Back Propagation, BP) neural network, namely SFLA-BP. The model first obtains the weights and biases as initial parameters through the BP neural network, then uses the SFLA to optimize the parameters, and finally feeds the optimized parameters back into the BP neural network for model training. Experiments show that the hybrid neural network model can effectively improve the accuracy of identifying fragrances and flavors, and reduce the interference of environmental and subjective factors, which has significant practical application value. © 2024 SPIE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

From single- to multi-modal remote sensing imagery interpretation: a survey and taxonomy

引用

Science China(Information Sciences) 2023年第4期66卷 5-32页

作者： Xian SUN Yu TIAN Wanxuan LU Peijin WANG Ruigang NIU Hongfeng YU Kun FU Aerospace Information Research Institute Chinese Academy of Sciences Key Laboratory of Network Information System Technology(NIST) Aerospace Information Research Institute Chinese Academy of Sciences University of Chinese Academy of Sciences School of Electronic Electrical and Communication Engineering University of Chinese Academy of Sciences

Modality is a source or form of information. Through various modal information, humans can perceive the world from multiple perspectives. Simultaneously, the observation of remote sensing(RS) is multimodal. We observe the world macroscopically through panchromatic, Lidar, and other modal *** observation of remote sensing has become an active area, which is beneficial for urban planning,monitoring, and other applications. Despite numerous advancements in this area, there has still not been a comprehensive assessment that provides a systematic overview with a unified evaluation. Accordingly, in this survey paper, we first highlight the key differences between single-and multimodal RS imagery interpretation,then use these differences to guide our research survey of multimodal RS imagery interpretation in a cascaded structure. Finally, some potential future research directions are explored and outlined. We hope that this survey will serve as a starting point for researchers to review state-of-the-art developments and work on multimodal research.

关键词： multimodal remote sensing image interpretation feature fusion co-learning

来源：评论

学校读者我要写书评

暂无评论

JNMR: Joint Non-Linear Motion Regression for Video Frame Interpolation

引用

IEEE Transactions on Image Processing 2023年 32卷 5283-5295页

作者： Liu, Meiqin Xu, Chenming Yao, Chao Lin, Chunyu Zhao, Yao Beijing Jiaotong University Institute of Information Science Beijing100044 China Beijing Key Laboratory of Advanced Information Science and Network Technology Beijing100044 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China

Video frame interpolation (VFI) aims to generate predictive frames by motion-warping from bidirectional references. Most examples of VFI utilize spatiotemporal semantic information to realize motion estimation and interpolation. However, due to variable acceleration, irregular movement trajectories, and camera movement in real-world cases, they can not be sufficient to deal with non-linear middle frame estimation. In this paper, we present a reformulation of the VFI as a joint non-linear motion regression (JNMR) strategy to model the complicated inter-frame motions. Specifically, the motion trajectory between the target frame and multiple reference frames is regressed by a temporal concatenation of multi-stage quadratic models. Then, a comprehensive joint distribution is constructed to connect all temporal motions. Moreover, to reserve more contextual details for joint regression, the feature learning network is devised to explore clarified feature expressions with dense skip-connection. Later, a coarse-to-fine synthesis enhancement module is utilized to learn visual dynamics at different resolutions with multi-scale textures. The experimental VFI results show the effectiveness and significant improvement of joint motion regression over the state-of-the-art methods. The code is available at https://***/ruhig6/JNMR. © 1992-2012 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

A review on GaN HEMTs:nonlinear mechanisms and improvement methods

引用

Journal of Semiconductors 2023年第12期44卷 31-46页

作者： Chenglin Du Ran Ye Xiaolong Cai Xiangyang Duan Haijun Liu Yu Zhang Gang Qiu Minhan Mi State Key Laboratory of Mobile Network and Mobile Multimedia Technology Shenzhen 518055China Wireless Product Planning Department ZTE CorporationShenzhen 518055China School of Microelectronics Xidian UniversityXi’an 710071China

The GaN HEMT is a potential candidate for RF applications due to the high frequency and large power handling *** ensure the quality of the communication signal,linearity is a key parameter during the system ***,the GaN HEMT usually suffers from the nonlinearity problems induced by the nonlinear parasitic capacitance,transconductance,channel transconductance *** them,the transconductance reduction is the main contributor for the nonlinearity and is mostly attributed to the scattering effect,the increasing resistance of access region,the self-heating effect and the trapping *** on the mechanisms,device-level improvement methods of transconductance including the trapping suppression,the nanowire channel,the graded channel,the double channel,the transconductance compensation and the new material structures have been proposed *** features of each method are reviewed and compared to provide an overview perspective on the linearity of the GaN HEMT at the device level.

关键词： GaN HEMT linearity improvement transconductance reduction transconductance compensation nanowire channel graded channel

来源：评论

学校读者我要写书评

暂无评论

Research on Non-uniform Grid Map Building and Object Detection technology Based on LiDAR 8th

Research on Non-uniform Grid Map Building and Object Detecti...

引用

8th International Conference on Computing, Control and Industrial Engineering, CCIE 2024

作者： Yang, Yufeng Meng, Rui Lei, Ning Hu, Zhehao Tong, Haojing School of Automation and Information Engineering Xi’an University of Technology Xi’an China Xi’an Key Laboratory of Wireless Optical Communication and Network Research Xi’an University of Technology Xi’an China Shaanxi Civil-Military Integration Key Laboratory of Intelligence Collaborative Networks Xi’an University of Technology Xi’an China

ISBN: (纸本)9789819769339

Occupancy grid is a practical method for environment map building. A drawback of occupancy grid is the high computational cost, the smaller cell size the higher map accuracy, but the overall number of cells increase quadratically, meaning that the rising computational cost, thus a trade-off between the grid map accuracy and the computational cost is required. To address this issue the non-uniform occupancy grid is used for environment modeling and object detection in this paper, which not only reduces the number of cells but also achieves high accuracy grid in the vicinity of ego vehicle. Then, according to the distribution characteristic of the non-uniform grid, the obstacle is extracted with the distance-based cluster algorithm. Finally to fit the obstacle with a 3D bounding box. Experiment show that the memory usage of improved method reduces by about 81% and 86% respectively, the time consumption for building the grid map reduces by about 72.37% and 73.72% respectively. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

Transferring fashion to surveillance with weak labels

引用

Neural Computing and Applications 2023年第18期35卷 13021-13035页

作者： Zheng, Qi He, Zheng Liang, Chao Chen, Jun Lin, Chia-Wen Tao, Dapeng National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University Wuhan430072 China Collaborative Innovation Center of Geospatial Technology Wuhan430079 China Department of Electrical Engineering National Tsing Hua University Hsinchu Taiwan School of Information Science and Engineering Yunnan University Yunnan Kunming650504 China

In this paper, we address the problem of automatic clothing parsing in surveillance images using the information from user-generated tags, such as "jeans" and "T-shirt." Although clothing parsing has achieved great success in the fashion domain, it is quite challenging to parse target under practical surveillance conditions due to the presence of complex environmental interference, such as that from low resolution, viewpoint variations and lighting changes. Our method is developed to capture target information from the fashion domain and apply this information to a surveillance domain by weakly supervised transfer learning. Most target tags convey strong location information (e.g., "T-shirt" is always shown in the upper region), which can be used as weak labels for our transfer method. Both quantitative and qualitative experiments conducted on practical surveillance datasets demonstrate the effectiveness of the proposed surveillance data enhancing method. © 2020, Springer-Verlag London Ltd., part of Springer Nature.

关键词： Monitoring

来源：评论

学校读者我要写书评

暂无评论

Centralized Wi-Fi Access networks over OFDM-PON with Joint System Load-based Resource Scheduling

Centralized Wi-Fi Access Networks over OFDM-PON with Joint S...

引用

2023 Opto-Electronics and communications Conference, OECC 2023

作者： Chen, Yuxuan Li, Jun Wang, Xiang Chang, Tianhai Shen, Gangxiang School of Electronic and Information Engineering Jiangsu Engineering Research Center of Novel Optical Fiber Technology and Communication Network Suzhou Key Laboratory of Advanced Optical Communication Network Technology Suzhou China Huawei Technologies Co. Ltd. China

We propose centralized Wi-Fi access networks over orthogonal frequency division multiplexing (OFDM) passive optical network, in which optical and wireless resources are jointly scheduled based on system load to improv... 详细信息

ISBN: (纸本)9781665462136

关键词： Wi-Fi

来源：评论

学校读者我要写书评

暂无评论

MCFTNet: Multimodal Cross-Layer Fusion Transformer network for Hyperspectral and LiDAR Data Classification

引用

IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing 2025年 18卷 12803-12818页

作者： Huang, Wei Wu, Tianren Zhang, Xueyu Li, Liangliang Lv, Ming Jia, Zhenhong Zhao, Xiaobin Ma, Hongbing Vivone, Gemine Xinjiang University School of Computer Science and Technology Urumqi830017 China Xinjiang University Key Laboratory of Signal Detection and Processing Urumqi830017 China Guangxi University School of Computer and Electronic Information Nanning530004 China Guangxi University Guangxi Key Laboratory of Multimedia Communications and Network Technology Nanning530004 China Beijing Institute of Technology School of Information and Electronics Beijing100081 China University of Science and Technology Beijing School of Computer and Communication Engineering Beijing100083 China Tsinghua University Department of Electronic Engineering Beijing100084 China National Research Council Tito85050 Italy National Biodiversity Future Center NBFC Palermo90133 Italy

Remote sensing image classification is a popular yet challenging field. Many researchers have combined convolutional neural networks (CNNs) and Transformers for hyperspectral imaging (HSI) classification tasks. However, in traditional Transformers, shallow-level information does not propagate well to deeper layers, which can lead to spatial variations and overfitting. Moreover, traditional Transformer models use an external classification token (CLS token) that is randomly initialized and often struggles to generalize effectively. In this article, we combine the strengths of HSI and light detection and ranging (LiDAR) data, using LiDAR as an external CLS token, which significantly enhances classification accuracy and reliability. We propose a new multimodal cross-layer fusion transformer network (MCFTNet), integrating CNNs with the latest Transformer networks. It includes a CNN for extracting spatial features and a hybrid cross-patch attention mechanism for land cover classification, leveraging LiDAR data to generate CLS and HSI patch tokens. More importantly, to reduce the loss of valuable information during the layer-by-layer propagation, we designed cross-layer skip connections. Through adaptive learning, these cross-layer fusions help address the gradient vanishing problem in deep networks while preserving early-layer features. This enables the model to better integrate information from different layers, enhancing both its stability and performance. We carried out in-depth experiments on commonly used benchmark datasets, specifically, the University of Houston dataset, the Trento dataset, and the University of Southern Mississippi Gulf Park dataset. We compared the results of the proposed MCFTNet model with those obtained from state-of-the-art Transformer models, classical CNNs, and traditional classifiers. As a result, the MCFTNet model outshones them all in terms of performance. © 2008-2012 IEEE.

关键词： Convolutional neural networks

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：