IEEE Computer Graphics and Applications最新文献_第2页

The UDV Card Deck: A Collaborative Design Framework to Facilitate Urban Visualization Conversations. UDV卡组：促进城市可视化对话的协作设计框架。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-31 DOI: 10.1109/MCG.2025.3556573

Damla Cay, Till Nagel, Sebastian Meier

引用次数: 0

What Data Does and Does Not Represent: Visualizing the Archive of Slavery. 数据能代表什么，不能代表什么：将奴隶制档案可视化。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-20 DOI: 10.1109/MCG.2025.3553412

Shiyao Li, Margy Adams, Tanvi Sharma, Jay Varner, Lauren Klein

引用次数: 0

2024 IEEE Scientific Visualization Contest Winner: PlumeViz: Interactive Exploration for Multi-Facet Features of Hydrothermal Plumes in Sonar Images. 2024年IEEE科学可视化竞赛冠军：PlumeViz：声纳图像中热液羽流多面特征的交互式探索。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-11 DOI: 10.1109/MCG.2025.3550365

Yiming Shao, Chengming Liu, Zhiyuan Meng, Shufan Qian, Peng Jiang, Yunhai Wang, Qiong Zeng

引用次数: 0

Towards Collective Storytelling: Investigating Audience Annotations in Data Visualizations. 走向集体叙事：调查数据可视化中的受众注释。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-04 DOI: 10.1109/MCG.2025.3547944

Tobias Kauer, Marian Dork, Benjamin Bach

引用次数: 0

Voting-Based Intervention Planning Using AI-Generated Images. 使用人工智能生成的图像进行基于投票的干预计划。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2025.3553620

Ioannis Kavouras, Ioannis Rallis, Emmanuel Sardis, Anastasios Doulamis, Nikolaos Doulamis

引用次数: 0

Reflections on the Use of Dashboards in the COVID-19 Pandemic. 关于在COVID-19大流行期间使用仪表板的思考。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2025.3538257

Alessio Arleo, Rita Borgo, Jorn Kohlhammer, Roy A Ruddle, H Scharlach, Xiaoru Yuan, Melanie Tory, Daniel Keefe

引用次数: 0

LossLens: Diagnostics for Machine Learning Through Loss Landscape Visual Analytics. LossLens：通过损失景观视觉分析进行机器学习诊断。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2024.3509374

Tiankai Xie, Jiaqing Chen, Yaoqing Yang, Caleb Geniesse, Ge Shi, Ajinkya Jeevan Chaudhari, John Kevin Cava, Michael W Mahoney, Talita Perciano, Gunther H Weber, Ross Maciejewski

{"title":"LossLens: Diagnostics for Machine Learning Through Loss Landscape Visual Analytics.","authors":"Tiankai Xie, Jiaqing Chen, Yaoqing Yang, Caleb Geniesse, Ge Shi, Ajinkya Jeevan Chaudhari, John Kevin Cava, Michael W Mahoney, Talita Perciano, Gunther H Weber, Ross Maciejewski","doi":"10.1109/MCG.2024.3509374","DOIUrl":"10.1109/MCG.2024.3509374","url":null,"abstract":"Modern machine learning often relies on optimizing a neural network's parameters using a loss function to learn complex features. Beyond training, examining the loss function with respect to a network's parameters (i.e., as a loss landscape) can reveal insights into the architecture and learning process. While the local structure of the loss landscape surrounding an individual solution can be characterized using a variety of approaches, the global structure of a loss landscape, which includes potentially many local minima corresponding to different solutions, remains far more difficult to conceptualize and visualize. To address this difficulty, we introduce LossLens, a visual analytics framework that explores loss landscapes at multiple scales. LossLens integrates metrics from global and local scales into a comprehensive visual representation, enhancing model diagnostics. We demonstrate LossLens through two case studies: visualizing how residual connections influence a ResNet-20, and visualizing how physical parameters influence a physics-informed neural network solving a simple convection problem.","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":"112-125"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143544540","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

HoloJig: Interactive Spoken Prompt Specified Generative AI Environments. HoloJig：交互式语音提示指定生成AI环境。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2025.3553780

Llogari Casas, Samantha Hannah, Kenny Mitchell

引用次数: 0

Should I Render or Should AI Generate? Crafting Synthetic Semantic Segmentation Datasets With Controlled Generation. 我应该渲染还是AI生成？合成语义分割数据集与控制生成。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2025.3553494

Omar A Mures, Manuel Silva, Manuel Lijo-Sanchez, Emilio J Padron, Jose A Iglesias-Guitian

{"title":"Should I Render or Should AI Generate? Crafting Synthetic Semantic Segmentation Datasets With Controlled Generation.","authors":"Omar A Mures, Manuel Silva, Manuel Lijo-Sanchez, Emilio J Padron, Jose A Iglesias-Guitian","doi":"10.1109/MCG.2025.3553494","DOIUrl":"10.1109/MCG.2025.3553494","url":null,"abstract":"This work explores the integration of generative AI models for automatically generating synthetic image-labeled data. Our approach leverages controllable diffusion models to generate synthetic variations of semantically labeled images. Synthetic datasets for semantic segmentation struggle to represent real-world subtleties, such as different weather conditions or fine details, typically relying on costly simulations and rendering. However, diffusion models can generate diverse images using input text prompts and guidance images, such as semantic masks. Our work introduces and tests a novel methodology for generating labeled synthetic images, with an initial focus on semantic segmentation, a demanding computer vision task. We showcase our approach in two distinct image segmentation domains, outperforming traditional computer graphics simulations in efficiently creating diverse datasets and training downstream models. We leverage generative models for crafting synthetically labeled images, posing the question: \"Should I render or should AI generate?\" Our results endorse a paradigm shift toward controlled generation models.","PeriodicalId":55026,"journal":{"name":"IEEE Computer Graphics and Applications","volume":"PP ","pages":"57-68"},"PeriodicalIF":1.7,"publicationDate":"2025-03-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143674963","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Unified Visual Comparison Framework for Human and AI Paintings Using Neural Embeddings and Computational Aesthetics. 使用神经嵌入和计算美学的人类和人工智能绘画的统一视觉比较框架。

IF 1.7 4区计算机科学

IEEE Computer Graphics and Applications Pub Date : 2025-03-01 DOI: 10.1109/MCG.2025.3555122

Yilin Ye, Rong Huang, Kang Zhang, Wei Zeng

引用次数: 0