检索结果-内蒙古大学图书馆

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Pan, Wenwen Shi, Haonan Zhao, Zhou Zhu, Jieming He, Xiuqiang Pan, Zhigeng Gao, Lianli Yu, Jun Wu, Fei Tian, Qi Zhejiang Univ Hangzhou Peoples R China Huawei Noahs Ark Lab Hong Kong Peoples R China Hangzhou Normal Univ Hangzhou Peoples R China Univ Elect Sci & Technol China Chengdu Peoples R China Hangzhou Dianzi Univ Hangzhou Peoples R China Zhejiang Univ Shanghai Inst Adv Study Hangzhou Peoples R China Huawei Cloud & AI Shenzhen Peoples R China

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Audio-Guided video object segmentation is a challenging problem in visual analysis and editing, which automatically separates foreground objects from the background in a video sequence according to the referring audio expressions. However, existing referring video object segmentation works mainly focus on the guidance of text-based referring expressions, due to the lack of modeling the semantic representations of audio-video interaction contents. In this paper, we consider the problem of audio-guided video semantic segmentation from the viewpoint of end-to-end denoising encoder-decoder network learning. We propose the wavelet-based encoder network to learn the cross-modal representations of the video contents with audio form queries. Specifically, we adopt the multi-head cross-modal attention layers to explore the potential relations of video and query contents. A 2-dimension discrete wavelet transform is merged into the transformer encoder to decompose the audio-video features. Next, we maximize mutual information between the encoded features and multi-modal features after cross-modal attention layers to enhance the audio guidance. Then, a self attention free decoder network is developed to generate the target masks with frequency-domain transforms. In addition, we construct the first large-scale audio-guided video semantic segmentation dataset. The extensive experiments show the effectiveness of our method(1).

关键词： visualization Frequency-domain analysis Semantics Noise reduction Video sequences Object segmentation Wavelet analysis

来源：评论

学校读者我要写书评

暂无评论

Audio-Visual Based Online Multi-Source Separation

引用

ieee-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 2022年 30卷 1219-1234页

作者： Ong, Jonah Vo, Ba Tuong Nordholm, Sven Vo, Ba-Ngu Moratuwage, Diluka Shim, Changbeom Curtin Univ Dept Elect & Comp Engn Bentley WA 6102 Australia

Meeting or conference assistance is a popular application that typically requires compact configurations of co-located audio and visual sensors. This paper proposes a novel solution for online separation of an unknown and time-varying number of moving sources using only a single microphone array co-located with a single visual device. The approach exploits the complementary nature of simultaneous audio and visual measurements, accomplished by a model-centric 3-stage process of detection, tracking, and (spatial) filtering, which performs separation in a block-wise or recursive fashion. Fusing the measurements requires solving the multi-modal space-time permutation problem, since the audio and visual measurements reside in different observation spaces, but also are unidentified or unlabeled (with respect to the unknown and time-varying number of sources), and are subject to noise, extraneous measurements and missing measurements. A labeled random finite set tracking filter is applied to resolve the permutation problem and recursively estimate the source identities and trajectories. A time-varying set of generalized side-lobe cancellers is constructed based on the tracking estimates to perform online separation. Evaluations are undertaken with live human speakers.

关键词： visualization Noise measurement Sensors Radio frequency Position measurement Music Training Audio-visual source separation spatial filtering labeled random finite sets generalized labeled multi-Bernoulli

来源：评论

学校读者我要写书评

暂无评论

Introduction to Special Issue on visualization Applied to Software Engineering

引用

information AND SOFTWARE TECHNOLOGY 2023年 155卷

作者： Leger, Paul Bergel, Alexandre Alcocer, Juan Pablo Sandoval Merino, Leonel Univ Catolica Norte Escuela Ingn Coquimbo Chile RelationalAI Zug Switzerland Pontificia Univ Catolica Chile Sch Engn DCC Santiago Chile Pontificia Univ Catolica Chile Sch Design DILAB Santiago Chile Pontificia Univ Catolica Chile Sch Engn Santiago Chile

Software visualization is a broad research area whose general goal is to enhance and promote the theory, realization, and evaluation of approaches to visually encode and analyze software systems, including software development practices, evolution, structure, and software runtime behavior. Software visualization is inherently interdisciplinary, drawing on theories and techniques from information visualization and computer graphics and applying these in the software engineering domain. This special issue on software visualization aims to bring together a community of researchers from software engineering, information visualization, computer graphics, human-computer interaction, and data science to discuss theoretical foundations, algorithms, techniques, tools, and applications related to software visualization. The special issue received 17 submissions of which 6 were accepted for publication (i.e., acceptance rate of 35.3%). Amongst the accepted papers, three correspond to extended versions of papers published in the ieee Working conference on Software visualization (VISSOFT) 2021.

关键词： Software visualization Software evolution Software comprehension User studies

来源：评论

学校读者我要写书评

暂无评论

GIS for Assessing Road Transport Complex Impact on Urban Air Pollution

GIS for Assessing Road Transport Complex Impact on Urban Air...

引用

2022 conference of Russian Young Researchers in Electrical and Electronic Engineering, ElConRus 2022

作者： Myshko, Roman. A. Kurakina, Natalia I. Saint Petersburg Electrotechnical University 'LETI' Dept. Information Measuring System and Technologies Saint Petersburg Russia

ISBN: (纸本)9781665409933

The paper describes creation of a road transport urban air pollution modelling geographic information system. It is noted that the road transport is the main factor of air pollution in large cities. The necessity of taking into account the particulate matter impact besides of exhaust gas components is shown. An atmospheric air pollution modelling algorithm taking into account roads spatial data and climatic conditions was developed. A software implementation of the developed algorithm using Python with subsequent visualization in the ArcGIS for Desktop environment was also carried out. Vsevolozhsk road transport air pollution modeling was carried out with displaying the result on the map. © 2022 ieee.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

Adaptive Feature Consolidation Network for Burst Super-Resolution

Adaptive Feature Consolidation Network for Burst Super-Resol...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Mehta, Nancy Dudhane, Akshay Murala, Subrahmanyam Zamir, Syed Waqas Khan, Salman Khan, Fahad Shahbaz Indian Inst Technol Ropar CVPR Lab Bara Phool Punjab India Mohamed bin Zayed Univ AI Abu Dhabi U Arab Emirates Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates Australian Natl Univ Canberra ACT Australia Linkoping Univ Linkoping Sweden

ISBN: (数字)9781665487399

ISBN: (纸本)9781665487399

Modern digital cameras generally count on image signal processing (ISP) pipelines for producing naturalistic RGB images. Nevertheless, in comparison to DSLR cameras, low-quality images are generally output from portable mobile devices due to their physical limitations. The synthesized low-quality images usually have multiple degradations - low-resolution owing to small camera sensors, mosaic patterns on account of camera filter array and subpixel shifts due to camera motion. Such degradation usually restrain the performance of single image super-resolution methodologies for retrieving high-resolution (HR) image from a single low-resolution (LR) image. Burst image super-resolution aims at restoring a photo-realistic HR image by capturing the abundant information from multiple LR images. Lately, the soaring popularity of burst photography has made multi-frame processing an attractive solution for overcoming the limitations of single image processing. In our work, we thus aim to propose a generic architecture, adaptive feature consolidation network (AFCNet) for multi-frame processing. To alleviate the challenge of effectively modelling the long-range dependency problem, that multi-frame approaches struggle to solve, we utilize encoder-decoder based transformer backbone which learns multi-scale local-global representations. We propose feature alignment module to align LR burst frame features. Further, the aligned features are fused and reconstructed by abridged pseudo-burst fusion module and adaptive group upsampling modules, respectively. Our proposed approach clearly outperforms the other existing state-of-the-art techniques on benchmark datasets. The experimental results illustrate the effectiveness and generality of our proposed framework in upgrading the visual quality of HR images.

关键词： Degradation visualization Adaptive systems Superresolution Signal processing Feature extraction Transformers

来源：评论

学校读者我要写书评

暂无评论

New Way of News Dissemination Based on Big Data Analysis and visualization Technology 2

New Way of News Dissemination Based on Big Data Analysis and...

引用

2nd ieee International conference on Artificial Intelligence of Things and Crowdsensing, AIoTCs 2022

作者： Li, Jingyuan Qilu Institute of Technology Shandong Jinan250200 China

ISBN: (纸本)9798350334104

With the advent of the wave of the Internet big data era, in view of the continuous rapid and high growth of Internet information volume, how to effectively and reasonably use Internet big data analysis, through scientific, effective and scientific information data mining, classification and classification expression, Changing the generation and methods of traditional information dissemination to better meet the various information needs of human life in the future has gradually become the key point of information dissemination and reform and development in the era of Internet big data. This research adopts the research method of questionnaire survey to support the development of this research. Based on the theoretical basis of the existing relationship research between China and foreign countries, combined with practical cases, this paper examines the status of the media industry's extensive use of the Internet in news production activities, and uses the concept of media information communication to analyze the impact of the new Internet technology on the way of media work. The experimental results show that 26% of new media practitioners in newspapers and 34% of new media practitioners in websites are using new visual charts such as data maps and timelines. The visual reporting of data news conforms to the development trend of the digital age and is the future journalism industry important direction of development. © 2022 ieee.

关键词： Big data

来源：评论

学校读者我要写书评

暂无评论

Cross-modal Clinical Graph Transformer for Ophthalmic Report Generation

Cross-modal Clinical Graph Transformer for Ophthalmic Report...

引用

ieee/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Mingjie Cai, Wenjia Verspoor, Karin Pan, Shirui Liang, Xiaodan Chang, Xiaojun Monash Univ Dept Data Sci & Artificial Intelligence Clayton Vic Australia Sun Yat Sen Univ Zhongshan Ophthalm Ctr State Key Lab Ophthalmol Guangzhou Peoples R China RMIT Univ Sch Comp Technol Melbourne Vic Australia Sun Yat Sen Univ Sch ISE Peng Cheng Natl Lab Guangzhou Peoples R China Univ Technol Sydney AAII ReLER Sydney NSW Australia

ISBN: (数字)9781665469463

ISBN: (纸本)9781665469463

Automatic generation of ophthalmic reports using data-driven neural networks has great potential in clinical practice. When writing a report, ophthalmologists make inferences with prior clinical knowledge. This knowledge has been neglected in prior medical report generation methods. To endow models with the capability of incorporating expert knowledge, we propose a Cross-modal clinical Graph Transformer (CGT) for ophthalmic report generation (ORG), in which clinical relation triples are injected into the visual features as prior knowledge to drive the decoding procedure. However, two major common Knowledge Noise (KN) issues may affect models' effectiveness. 1) Existing general biomedical knowledge bases such as the UMLS may not align meaningfully to the specific context and language of the report, limiting their utility for knowledge injection. 2) Incorporating too much knowledge may divert the visual features from their correct meaning. To overcome these limitations, we design an automatic information extraction scheme based on natural language processing to obtain clinical entities and relations directly from in-domain training reports. Given a set of ophthalmic images, our CGT first restores a sub-graph from the clinical graph and injects the restored triples into visual features. Then visible matrix is employed during the encoding procedure to limit the impact of knowledge. Finally, reports are predicted by the encoded cross-modal features via a Transformer decoder. Extensive experiments on the large-scale FFA-IR benchmark demonstrate that the proposed CGT is able to outperform previous benchmark methods and achieve state-of-the-art performances.

关键词： Training visualization Unified modeling language Benchmark testing Writing Transformers Image restoration

来源：评论

学校读者我要写书评

暂无评论

Auxiliary System of Red Tourism Resource visualization for the Construction of Educational Integration Platform Under the Background of Mobile Image Collection 4

Auxiliary System of Red Tourism Resource Visualization for t...

引用

4th International conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Guo, Yajun School of Marxism China West Normal University Sichuan Nanchong637002 China

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

Using the moving image acquisition background method combined with the motion history map to detect the dynamic target, and study the background modeling, introduce several methods of background extraction, so as to achieve a small amount of calculation, improve the real-time performance, and strengthen the effectiveness. In order to reduce the system cost Research and development costs, enhance practicality, on the basis of being able to obtain qualified fabric images. Based on red tourism resources and college education, the two are organically coupled. Based on this, some suggestions are put forward, such as mining the depth of red resources, innovating the university education platform, and integrating red resources with the university education system. © 2022 ieee.

关键词： visualization

来源：评论

学校读者我要写书评

暂无评论

Exploring Multiview Interactive visualization for Chinese Historical Texts Using Knowledge Aggregation

Exploring Multiview Interactive Visualization for Chinese Hi...

引用

ieee/ACM Joint conference on Digital Libraries(JCDL)

作者： Chengxi Yan Shaojian Li School of Information Resource Management Renmin University of China Beijing China

Textual knowledge extraction and visual analysis technology bring new technical methodology to traditional qualitative research in the historical domain. However, there is still some difficulty impeding the semantic understanding and presentation for knowledge in historical texts. To address it, we propose a novel solution that integrates the semantic aggregation of different types of textual knowledge units in multiple technical pathways and hybrid strategies-based visual display for supporting smooth interactive functionalities with different groups of users. A visualization system is also developed, which can provide various digital tools to reveal the knowledge clues and patterns in both macro and micro level and support deep exploration of implicit knowledge around historical research. The user evaluation shows the effectiveness of our system and design solution. It is believed our preliminary research can promote knowledge organization and visualization of Chinese historical texts and a future extension to other domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Scalable Fiducial Tag Localization on a 3D Prior Map via Graph-Theoretic Global Tag-Map Registration

Scalable Fiducial Tag Localization on a 3D Prior Map via Gra...

引用

ieee/RSJ International conference on Intelligent Robots and Systems (IROS)

作者： Koide, Kenji Oishi, Shuji Yokozuka, Masashi Banno, Atsuhiko Natl Inst Adv Ind Sci & Technol Dept Informat Technol & Human Factors Umezono 1-1-1 Tsukuba Ibaraki 3050061 Japan

ISBN: (数字)9781665479271

ISBN: (纸本)9781665479271

This paper presents an accurate and scalable method for fiducial tag localization on a 3D prior environmental map. The proposed method comprises three steps: 1) visual odometry-based landmark SLAM for estimating the relative poses between fiducial tags, 2) geometrical matching-based global tag-map registration via maximum clique finding, and 3) tag pose refinement based on direct camera-map alignment with normalized information distance. Through simulationbased evaluations, the proposed method achieved a 98 % global tag-map registration success rate and an average tag pose estimation accuracy of a few centimeters. Experimental results in a real environment demonstrated that it enables to localize over 110 fiducial tags placed in an environment in 25 minutes for data recording and post-processing.

关键词： Location awareness Measurement visualization Three-dimensional displays Simultaneous localization and mapping Pose estimation Cameras

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：