检索结果-内蒙古大学图书馆

17th International Forum on Digital TV and Wireless Multimedia Communication, IFTC 2020

作者： Xu, Yiwen Huang, Jingquan Liu, Wei Chen, Weiling Zhao, Tiesong Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information College of Physics and Information Engineering Fuzhou University Fuzhou China

ISBN: (纸本)9789811611933

The measurements of Quality of Experience (QoE) are essential to research for better analysis and optimization of Multi-View and 3D (MV/3D) videos. However, there is a lack of systematic description of QoE mechanism in MV/3D videos yet. This paper aims to give a comprehensive account of QoE assessment and management for MV/3D video services. We first conclude distinctive QoE influencing factors (IFs) in MV/3D videos by dividing them into immersion and interaction related IFs. Then the methods of QoE assessment in MV/3D video services (including subjective assessment and objective assessment) are presented. Finally, we summarize QoE management for improving immersion and interaction. We hope our work is capable of providing a useful guideline on the related issues and the future research directions in MV/3D video services. © 2021, Springer Nature Singapore Pte Ltd.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

A Region of Interest Extraction Algorithm for Underwater Surveillance Video

A Region of Interest Extraction Algorithm for Underwater Sur...

引用

International Conference on Information, Communication and Networks (ICICN)

作者： Nian He Jingquan Huang Tiesong Zhao Yiwen Xu Zhicheng College Fuzhou University Fuzhou China Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China

Underwater Surveillance Video (USV) plays important role in the research and development of marine resources. The harsh underwater environment means that USV can only be transmitted over hydroacoustic channel with narrow bandwidth. Region of Interest (ROI)-based rate control algorithm, which automatically adjusts the code rate to accommodate bandwidth changes based on user’s interest. So the ROI Extraction Algorithm (ROI-EA) is a key process. But the existing ROI-EA is mainly aimed at conventional video. It does not take into account the characteristics of USV. Thus, there is still room for improvement in its performance. Therefore, an ROI-EA for USV is proposed in this paper. The characteristics of USV was explored first. Then a underwater image enhancement algorithm based on improved gamma-corrected was proposed. Finally, the proposed ROI-EA, according to the characteristics of USV, was demonstrated. We also compared the performance of our method with existing ROI-EAs. The results show the superiority of our algorithm.

关键词：

来源：评论

学校读者我要写书评

暂无评论

引用

International Conference on Acoustics, Speech, and Signal processing (ICASSP)

作者： Jinhai Yang Hua Yang Institution of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission Shanghai China

Few-shot learning aims for rapid adaptation with few samples. Recently, cross-granularity few-shot learning has emerged as a promising research area, where models observe coarse labels but target fine-grained recognition among novel classes. As coarse supervision tends to eliminate feature discrimination among underlying sub-classes, existing methods commonly utilize self-supervision as a complement to explore intra-class variation. However, current methods suffer from an intrinsic conflict between contrastive learning and coarse supervision. In this paper, we locate the root cause of the intrinsic conflict. Then, we resolve it by exploiting the similarity among augmented views while ignoring the unreasonable constraint between negative pairs. Besides, we decouple contrastive learning and coarse supervision into parallel branches to better regularize the latent space. Albeit simple, our approach consistently outperforms state-of-the-art methods across different benchmarks.

关键词： Adaptation models Target recognition Semantics Signal processing Performance gain Benchmark testing Acoustics

来源：评论

学校读者我要写书评

暂无评论

Application-Based Cooperative Content Caching via Tensor Domain Adaptation Networks

Application-Based Cooperative Content Caching via Tensor Dom...

引用

International Conference on Wireless Communications and Signal processing (WCSP)

作者： Yanlong Wang Youjia Chen Pingping Chen Jinsong Hu Haifeng Zheng Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China

ISBN: (纸本)9781665450867

The proliferation of smart devices has accelerated the development of mobile applications (Apps). Traffic generated by Apps accounts for the vast majority of cellular traffic, resulting in significant transmission delay. Caching popular App content can effectively reduce duplicate data transmission. In this paper, we design an App-based cooperative content caching scheme through Apps' traffic prediction. In detail, a tensor domain adaptation network model for Apps' traffic prediction is proposed, where cross-domain spatio-temporal features are transferred from the source domain to the target domain by learning a shared tensor subspace. Furthermore, a cooperative content caching strategy is proposed to minimize the service delay. The cache decision problem is solved by GA-PSO which jointly uses a genetic algorithm and a particle swarm optimization. Experiment results show the proposed prediction model outperforms existing models in terms of prediction accuracy, and the performance impact of different caching modes and storage sizes is also Investigated.

关键词： Adaptation models Tensors Simulation Signal processing algorithms Predictive models Signal processing Prediction algorithms

来源：评论

学校读者我要写书评

暂无评论

A Review of Deep Learning Applications in Lesion Detection Research

A Review of Deep Learning Applications in Lesion Detection R...

引用

IEEE International Symposium on Information (IT) in Medicine and Education, ITME

作者： Tao Chen Yi Geng Lanlan Li Hongan Wei College of Physics and Information Engineering Fuzhou University China Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China

As a powerful machine learning technique, deep learning has been widely applied to lesion detection in medical image processing. This review summarizes the research progress of deep learning applications in lesion detection. Firstly, the characteristics of medical image data are introduced, and the datasets and evaluation metrics of lesion detection are summarized. Then, the main contents of deep learning, including Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), Generative Adversarial Networks (GAN), YOLO algorithm, and SAM, have demonstrated good performance in medical image processing. Meanwhile, the applications of lesion detection in different medical image modalities are discussed, and the advantages of deep learning in different lesion types are highlighted, such as high automation, good performance, and transferability. In addition, some challenges of deep learning in lesion detection are discussed, such as sample scarcity, interpretability, and reliability. Finally, the future development directions of deep learning in lesion detection are discussed, such as multimodal fusion, transfer learning, and labeled data. This review provides a comprehensive overview of the research progress of deep learning in the field of lesion detection, which offers guidance and reference for related research and applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model

arXiv

引用

arXiv 2024年

作者： Dong, Jihao Pan, Renjie Yang, Hua Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

Human-Object Interaction (HOI) detection aims to localize human-object pairs and comprehend their interactions. Recently, two-stage transformer-based methods have demonstrated competitive performance. However, these methods frequently focus on object appearance features and ignore global contextual information. Besides, vision-language model CLIP which effectively aligns visual and text embeddings has shown great potential in zero-shot HOI detection. Based on the former facts, We introduce a novel HOI detector named ISA-HOI, which extensively leverages knowledge from CLIP, aligning interactive semantics between visual and textual features. We first extract global context of image and local features of object to Improve interaction Features in images (IF). On the other hand, we propose a Verb Semantic Improvement (VSI) module to enhance textual features of verb labels via cross-modal fusion. Ultimately, our method achieves competitive results on the HICO-DET and V-COCO benchmarks with much fewer training epochs, and outperforms the state-of-the-art under zero-shot settings. © 2024, CC BY.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Exploring Interactive Semantic Alignment for Efficient HOI Detection with Vision-language Model

Exploring Interactive Semantic Alignment for Efficient HOI D...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Jihao Dong Hua Yang Renjie Pan Institute of Image Communication and Network Engineering Shanghai Jiao Tong University China Shanghai Key Lab of Digital Media Processing and Transmission China China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

关键词： Training visualization Target recognition Semantics Detectors Benchmark testing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

SSIM-Variation-Based Complexity Optimization for Versatile Video Coding

arXiv

引用

arXiv 2022年

作者： Lin, Jielian Lin, Hongbin Zhang, Zhichen Xu, Yiwen Zhao, Tiesong Fujian Key Lab for Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fujian Fuzhou350116 China

To date, Versatile Video Coding (VVC) has a more magnificent overall performance than High Efficiency Video Coding (HEVC). The Quadtree with Nested Multi-Type Tree (QTMT) coding block structure can substantially enhance video coding quality in VVC. However, the coding gain also leads to a greater coding complexity. Therefore, this letter proposes a Fast Decision Scheme Based on Structural Similarity Index Metric Variation (FDS-SSIMV) to solve this problem. Firstly, the Structural Similarity Index Metric Variation (SSIMV) characteristic among the sub coding units of the spit mode is illustrated. Next, to evaluate the SSIMV value, SSIMV measure strategies are designed for different split modes in this letter. Then, the desired split modes are selected by the SSIMV values. Experimental results show that the proposed method achieves 64.74% average encoding Time Saving (TS) with a 2.79% Bjøntegaard Delta Bit Rate (BDBR), outperforming the benchmarks. Copyright © 2022, The Authors. All rights reserved.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Compressed Video Quality Metric Based on Just-Noticeable-Difference and Saliency-aware Blocking Detection 7

Compressed Video Quality Metric Based on Just-Noticeable-Dif...

引用

7th International Conference on Computer and Communications, ICCC 2021

作者： Wang, Zheng Liao, Guodong Wu, Yuxuan Lin, Liqun Yang, Jing Zheng, Haifeng Fujian Key Lab For Intelligent Processing and Wireless Transmission of Media Information Fuzhou University Fuzhou China Huawei Technologies Co.Ltd. Guangdong Shenzhen China

ISBN: (纸本)9781665409506

Block-based prediction-quantization hybrid coding framework is widely used in video compression, which results in visually annoying artifacts, i.e., blocking artifacts, on encoded videos. They significantly degrade the Quality-of-Experience (QoE). To improve the QoE, it is crucial to develop Video Quality Assessment (VQA) methods that can identify and quantify various artifacts, among which the negative effect introduced by blocking artifacts is of guiding significance. To evaluate and monitor video quality effectively, a novel Blocking-based Compressed Video Quality Assessment (BCVQA) is proposed in this paper. The key idea of the BCVQA method is a blocking detection model based on Just-Noticeable-Difference (JND) mechanism, which is aimed to improve detection performance, since it only focuses on the observable blocking artifacts. Furthermore, the saliency model is utilized in quality prediction procedure after blocking detection, considering the visual attention mechanism. With the fusion of the above two visual mechanisms, quality prediction of compressed videos becomes more effective, since the useful information is refined in our framework. Experimental results show that the proposed BCVQA is consistent with perceived quality and can effectively evaluate video quality. © 2021 IEEE.

关键词： Image compression

来源：评论

学校读者我要写书评

暂无评论

Interventional Bag Multi-Instance Learning On Whole-Slide Pathological Images

Interventional Bag Multi-Instance Learning On Whole-Slide Pa...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Tiancheng Lin Zhimiao Yu Hongyu Hu Yi Xu Chang Wen Chen Shanghai Key Lab of Digital Media Processing and Transmission Shanghai Jiao Tong University MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University The Hong Kong Polytechnic University Hong Kong China

Multi-instance learning (MIL) is an effective paradigm for whole-slide pathological images (WSIs) classification to handle the gigapixel resolution and slide-level label. Prevailing MIL methods primarily focus on improving the feature extractor and aggregator. However, one deficiency of these methods is that the bag contextual prior may trick the model into capturing spurious correlations between bags and labels. This deficiency is a confounder that limits the performance of existing MIL methods. In this paper, we propose a novel scheme, Interventional Bag Multi-Instance Learning (IBMIL), to achieve deconfounded bag-level prediction. Unlike traditional likelihood-based strategies, the proposed scheme is based on the backdoor adjustment to achieve the interventional training, thus is capable of suppressing the bias caused by the bag contextual prior. Note that the principle of IBMIL is orthogonal to existing bag MIL methods. Therefore, IBMIL is able to bring consistent performance boosting to existing schemes, achieving new state-of-the-art performance. Code is available at https://***/HHHedo/IBMIL.

关键词：

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：