检索结果-内蒙古大学图书馆

ieee Annual Computing and Communication Workshop and conference (CCWC)

作者： Victor A. Okpanachi Ifeoma Adaji University of British Columbia Okanagan Canada

ISBN: (数字)9798331507695

ISBN: (纸本)9798331507701

The rise of diet-related health issues among African international students in Western countries necessitates innovative interventions to promote healthy eating. Food Villain, a serious game designed to address this challenge, combines educational content with engaging gameplay to encourage better nutritional choices. The current paper extends previous work on the development of Food Villain. In the current paper, we present the evaluation of the game with a focus on metrics such as ease of use, perceived usefulness, engagement, quality of information, and aesthetics. Developed through a literature review of persuasive strategies and serious game design, Food Villain incorporates elements like points, levels, feedback, rewards, and authority to educate and motivate players. The game spans four levels, featuring activities like adventure missions, quizzes, food categorization tasks, and recipe creation. The evaluation involved 24 African international students, assessing key metrics via a survey. Our results indicated that participants found the game useful and informative, with suggestions on improving the user interface and interactivity. These findings provide valuable insights for future iterations, highlighting the importance of ongoing user feedback.

关键词： Surveys Measurement visualization Refining Education Games User interfaces User experience Serious games Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Influence of Ball Reception on Visual Tracking Performance of Soccer Players in a Virtual Reality Multiple-Player-Tracking Task

Influence of Ball Reception on Visual Tracking Performance o...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), ieee conference on

作者： Alexandre Vu Anthony Sorel Benoit Bideau Richard Kulpa Univ Rennes 2 Inria M2S Rennes France

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

The multitasking aspect of soccer is rarely considered to study the relationship between expertise and visual attention. This study examined the ability of 24 soccer players to visually track teammates and opponents in simulated game situations within a CAVE, with or without the requirement to intercept a virtual ball. No significant decrease in visual tracking performance was observed when an actual motor interception was required. Additionally, no significant differences were found between participants competing at the national level and those at lower levels. Further research is needed to better understand how visual attention contributes to expertise in soccer.

关键词： visualization Three-dimensional displays Tracking Virtual reality Games User interfaces Motors Multitasking Monitoring Sports

来源：评论

学校读者我要写书评

暂无评论

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-Shot Classification

ViSeNet: A Visual-Semantic Fusion Network for Enhancing Few-...

引用

ieee International conference on Consumer Electronics (ICCE)

作者： Dongheon Lee Sangwoo Yun Joonki Paik Image Processing and Intelligent & System Laboratory Graduate School of Artificial Intelligence Chung-Ang University Seoul Korea Image Processing and Intelligent & System Laboratory Graduate School of Advanced & Imaging Science Multimedia and Film Chung-Ang University Seoul Korea

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

Few-shot learning addresses the challenge of recognizing novel classes with only a few labeled examples, a critical issue in limited data scenarios. This paper proposes a multi-modal Visual and Semantic Network (ViSeNet), which enhances few-shot classification by mining linguistic features and fusing weighted vectors. ViSeNet generates enriched class prototypes by leveraging both visual and semantic information. The linguistic feature mining process utilizes image-to-text models to produce class-specific textual descriptions, which are then transformed into representative semantic embeddings. For visual feature extraction, we employ a pretrained Swin Transformer, while text embeddings are integrated for each class using weighted factors. By combining these modalities, ViSeNet constructs class prototypes that capture both visual and semantic characteristics. Experimental results on benchmark datasets, particularly CIFAR-FS, demonstrate that ViSeNet achieves performance comparable to state-of-the-art approaches.

关键词： visualization Semantics Prototypes Linguistics Transformers Feature extraction Vectors Data mining Few shot learning Consumer electronics

来源：评论

学校读者我要写书评

暂无评论

A Singing Melody Extraction Network Via Self-Distillation and Multi-Level Supervision

A Singing Melody Extraction Network Via Self-Distillation an...

引用

International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ying Hu Jiabo Jing Fan Li Lijun He Li Lin Wenzhong Yang Key Laboratory of Signal Detection and Processing Urumqi China School of Computer Science and Technology Xinjiang University Urumqi China School of Information and Communications Engineering Xi’an Jiaotong University Xi’an China Xinjiang Institute of Electronics Research Shares Co. Ltd Urumgi China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Extracting singing melody from polyphonic music is an important topic in the field of music information retrieval. In this paper, we propose a singing melody extraction network consisting of five stacked multi-scale feature time-frequency aggregation (MF-TFA) modules. In the same network, deeper layers generally contain more contextual information than shallower layers. To help the shallower layers enhance the ability of task-relevant feature extraction, we propose a self-distillation and multi-level supervision (SD-MS) method, which leverages the feature distillation from the deepest layer to the shallower one and multi-level supervision to guide network training. visualization analysis shows that by introducing SD-MS, the same-level layer in the network can obtain a clearer representation of fundamental frequency components, while the shallower layers can even learn more task-relevant semantic information. Ablation study results indicate that SD-MS applies to existing melody extraction models and can consistently improve performance. Experimental results show that our proposed method, MF-TFA with SD-MS, outperforms six compared state-of-the-art methods, achieving overall accuracy (OA) scores of 87.1%, 89.9%, and 76.6% on the ADC 2004, MIREX 05, and MEDLEY DB datasets, respectively. The main code will be available at https://***/SmoothJing/MF-TFA_SD-MS.

关键词： Training visualization Time-frequency analysis Semantics Signal processing Feature extraction Multiple signal classification Data mining Speech processing Music information retrieval

来源：评论

学校读者我要写书评

暂无评论

Differential Analysis and Prediction Based on Independent T-Test and Linear Regression-Stacking Ensemble Algorithm

Differential Analysis and Prediction Based on Independent T-...

引用

Electronics, Energy Systems and Power Engineering (EESPE), ieee International conference on

作者： Xiangtong Li Yingying Huang School of Economic and Management Tianjin University of Science and Technology Tianjin China College of Food Engineering and Biotechnology Tianjin University of Science and Technology Tianjin China

ISBN: (数字)9798350389579

ISBN: (纸本)9798350389586

This paper presents a comprehensive analysis of the differences between experimental and theoretically calculated yield values, employing the Independent T-test to assess statistical significance. By examining the resulting p-values, we determine whether significant discrepancies exist between experimental and theoretical yields. Visual representations of these comparisons are also provided to facilitate subgroup analysis and pinpoint specific mixing ratios where differences are most evident. Furthermore, we develop a predictive model for product yields using a hybrid approach that combines linear regression with a stacking ensemble algorithm. This integrated model, which leverages the strengths of both methodologies through weighted fusion, demonstrates improved predictive performance based on the experimental data.

关键词： visualization Accuracy Computational modeling Stacking Linear regression Predictive models Prediction algorithms Data models Robustness Testing

来源：评论

学校读者我要写书评

暂无评论

Digital “Double Hatters”: Augmenting Audiovisual Creative Work with a Generative Text-to-Video Workflow 58

Digital “Double Hatters”: Augmenting Audiovisual Creative ...

引用

58th Hawaii International conference on System Sciences, HICSS 2025

作者： Liu, Vivian Long, Tao Ma, Jenny Raw, Nathan Yang, Jiaxin Tang, Claudia Wang, Lulu Yang, Yumo Chilton, Lydia Columbia University United States Rochester Institute of Technology United States

ISBN: (纸本)9780998133188

Generative AI is transforming work for creative professionals. Text-to-image and text-to-video tools provide alternative methods for visual content creation, circumventing the traditional workflows creative professionals have developed. This transformation raises the pressing question of whether these new generative workflows will augment or supplant creative work. To investigate this question, we introduce Generative Disco, a text-to-video system for music visualization, and use it as a technology probe for creative professionals who freelance audiovisual work. In a mixed-methods study (n=12), we observe that professionals found Generative Disco easy to use, highly expressive, and capable of supporting many professional use cases. Its generative workflow enabled professionals to become digital “double hatters”, expanding their creative range into adjacent domains. We conclude on how creatives can benefit from this new means of skill mobility. © 2025 ieee Computer Society. All rights reserved.

关键词： creative work creativity support generative AI workflows large language models music visualization social media text-to-image

来源：评论

学校读者我要写书评

暂无评论

VIS30K: A Collection of Figures and Tables From ieee visualization conference Publications

引用

ieee TRANSACTIONS ON visualization AND COMPUTER GRAPHICS 2021年第9期27卷 3826-3833页

作者： Chen, Jian Ling, Meng Li, Rui Isenberg, Petra Isenberg, Tobias Sedlmair, Michael Moeller, Torsten Laramee, Robert S. Shen, Han-Wei Wuensche, Katharina Wang, Qiru Ohio State Univ Columbus OH 43210 USA Univ Paris Saclay CNRS INRIA LISN F-91190 St Aubin France Univ Stuttgart D-70174 Stuttgart Germany Univ Vienna A-1010 Vienna Austria Univ Nottingham Nottingham NG7 2RD England

We present the VIS30K dataset, a collection of 29,689 images that represents 30 years of figures and tables from each track of the ieee visualization conference series (Vis, SciVis, InfoVis, VAST). VIS30K's comprehensive coverage of the scientific literature in visualization not only reflects the progress of the field but also enables researchers to study the evolution of the state-of-the-art and to find relevant work based on graphical content. We describe the dataset and our semi-automatic collection process, which couples convolutional neural networks (CNN) with curation. Extracting figures and tables semi-automatically allows us to verify that no images are overlooked or extracted erroneously. To improve quality further, we engaged in a peer-search process for high-quality figures from early ieee visualization papers. With the resulting data, we also contribute VISImageNavigator (VIN, ***), a web-based tool that facilitates searching and exploring VIS30K by author names, paper keywords, title and abstract, and years.

关键词： Data visualization visualization conferences Metadata Tools Data mining Electronic mail visualization ieee VIS InfoVis SciVis VAST dataset bibliometrics images figures tables

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Optimizers for Breast Cancer Segmentation in Ultrasound Images Using U-Net

Comparative Analysis of Optimizers for Breast Cancer Segment...

引用

ieee SSD International Multi-conference on Systems, Signals and Devices

作者： Taissir Ferjani Ibtihel Nouira Ahmed Selmi Private Polytechnic School of Monastir Monastir Tunisia Technology and Medical Imaging Laboratory Faculty of Medicine Monastir University of Monastir Monastir Tunisia Faculty of Medicine Monastir University of Monastir Monastir Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

This paper presents a comparative study on the impact of various optimizers Adam, SGD, AdaGrad, and RMSprop on U-Net-based segmentation of breast cancer in ultrasound images. Using a synthetic dataset of breast ultrasound (BUS) images, generated via Data Expansion Network (DEN) and Probability Map Generator (PMG), the performance of each optimizer on segmentation metrics such as Dice coefficient, IoU, and accuracy are evaluated. Results demonstrate that the Adam optimizer yields the highest segmentation accuracy, while other optimizers exhibit specific strengths that may benefit different aspects of training stability and convergence.

关键词： Measurement Training Image segmentation visualization Ultrasonic imaging Accuracy Breast cancer Thermal stability Tumors Synthetic data

来源：评论

学校读者我要写书评

暂无评论

Investigating the Effects of Limited Field of View and Resolution in Optical See-Through Augmented Reality in the Context of Immersive Analytics

Investigating the Effects of Limited Field of View and Resol...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), ieee conference on

作者： Julia Hertel Jan Nicolai Synwold Frank Steinicke Human-Computer Interaction University of Hamburg

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

Currently, optical see-through augmented reality HMDs (OST AR HMDs) still have significant display limitations. This work presents a user study conducted with an OST AR HMD to investigate how two of these limitations-a small field of view and low resolution-affect task performance, user experience, workload, and simulator sickness in the context of immersive analytics. The Magic Leap 2 was used to simulate the display properties of other commonly used HMDs. The results suggest that a limited field of view negatively impacts user experience and workload, with the difference between the Magic Leap 2’s field of view and that of the two generations of the Microsoft HoloLens being particularly striking.

关键词： Human computer interaction visualization Three-dimensional displays conferences Resists User experience Augmented reality

来源：评论

学校读者我要写书评

暂无评论

Latency-Aware Heterogeneous Resource Allocation and Rendering Task Offloading for Metaverse

Latency-Aware Heterogeneous Resource Allocation and Renderin...

引用

ieee conference on Wireless Communications and Networking

作者： Pham Ngoc Hoa Te-Chuan Chiu Department of Computer Science National Tsing Hua University Taiwan

ISBN: (数字)9798350368369

ISBN: (纸本)9798350368376

To deliver immersive experiences with the Metaverse, rendering must be carefully orchestrated in high-resolution environments with minimal latency. To address this fundamental challenge and NP-hard problem, in this paper, we consider joint computation, communication, and caching optimization in rendering using Edge Computing. With our Latency-aware, Resolution-focused, and Cache-optimized (LaReCa) framework involving heterogeneous resource allocation and rendering task offloading, we achieve the desired minimization of computational requirements and 25–30 % reduction of service latency without losing visual immersion compared with the SOTA baseline. Importantly, our LaReCa framework ensures the quality of immersion by surpassing normal HD resolution, which represents a substantial contribution to the broad landscape Metaverse rendering service.

关键词： visualization Metaverse NP-hard problem Rendering (computer graphics) Minimization User experience Resource management Servers Optimization Edge computing

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：