检索结果-内蒙古大学图书馆

7th IEEE International Conference on Artificial Intelligence and eXtended and Virtual Reality, AIxVR 2025

作者： De Oliveira, Elisa Ayumi Masasi De Freitas Cintra, Luiza Martins Barbosa, Gustavo Higino Webster Sousa, Rafael Teixeira Filho, Arlindo Rodrigues Galvão Advanced Knowledge Center in Immersive Technology Akcit Goiânia Brazil Advanced Knowledge Center in Immersive Technology Akcit Recife Brazil Federal University of Mato Grosso Advanced Knowledge Center in Immersive Technology Akcit Barra do Garças Brazil

ISBN: (纸本)9798331521578

This paper explores the use of immersive technolo-gies and AI-driven virtual interactions to aid the social reintegration of incarcerated individuals. By integrating a ChatGPT-based AI within a virtual reality framework, the developed application offers interactive, realistic simulations aimed at fostering essential skills, such as effective communication and vocational abilities. Users interact with a lifelike avatar, designed to simulate scenarios like job interviews and interpersonal dialogues, promoting empathy, self-confidence, and behavioral adaptability. Initial assessments indicate that the application effectively supports engaging and empathetic interactions, which are crucial for preparing individuals for reintegration into society. The application will be open-access, allowing further refinement and adaptability by experts and developers, ultimately aiming to reduce recidivism and support a more humane approach to correctional rehabilitation through technological advancement. © 2025 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Focus360: Guiding User Attention in immersive Videos for VR

Focus360: Guiding User Attention in Immersive Videos for VR

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Silva, Paulo Vitor S. Neves, Lucas L. Goiás, Rafael A. Silva, Diogo F. C. Sousa, Rafael T. Filho, Arlindo R. Galvão Federal University of Goiás UFG Advanced Knowledge Center for Immersive Technologies Akcit Brazil

ISBN: (纸本)9798331514846

This demo introduces Focus360, a system designed to enhance user engagement in 360° VR videos by guiding attention to key elements within the scene. Using natural language descriptions, the system identifies important elements and applies a combination of visual effects to guide attention seamlessly. At the demonstration venue, participants can experience a 360° Safari Tour, showcasing the system's ability to improve user focus while maintaining an immersive experience. © 2025 IEEE.

关键词： 360° Videos Attention Guidance Deep Learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging immersive Reality and LLMs for Social Reintegration: AI-Driven Skill Development in Correctional Rehabilitation

Leveraging Immersive Reality and LLMs for Social Reintegrati...

引用

IEEE International Conference on Artificial Intelligence and Virtual Reality (AIVR)

作者： Elisa Ayumi Masasi De Oliveira Luiza Martins De Freitas Cintra Gustavo Higino Webster Barbosa Rafael Teixeira Sousa Arlindo Rodrigues Galvão Filho Advanced Knowledge Center in Immersive Technology AKCIT Goiânia Brazil Advanced Knowledge Center in Immersive Technology AKCIT Recife Brazil Advanced Knowledge Center in Immersive Technology AKCIT Federal University of Mato Grosso Barra do Garças Brazil

ISBN: (数字)9798331521578

ISBN: (纸本)9798331521585

关键词： Solid modeling Adaptation models Avatars Artificial intelligence Interviews

来源：评论

学校读者我要写书评

暂无评论

Transformative Technologies for Rehabilitation: Leveraging immersive and AI-Driven Solutions to Reduce Recidivism and Promote Decent Work

Transformative Technologies for Rehabilitation: Leveraging I...

引用

2025 IEEE Conference on Virtual Reality and 3D User Interfaces Abstracts and Workshops, VRW 2025

作者： Sousa, Rafael T. Oliveira, Elisa A. M. Cintra, Luiza M. F. Filho, Arlindo R. Galvão Federal University of Mato Grosso Advanced Knowledge Center in Immersive Technology Brazil Federal University of Goiás Advanced Knowledge Center in Immersive Technology Brazil

ISBN: (纸本)9798331514846

The reintegration of incarcerated individuals into society presents significant challenges, particularly in addressing barriers related to vocational training, social skill development, and emotional rehabilitation. immersive technologies, such as Virtual Reality and Augmented Reality, combined with generative Artificial Intelligence (AI) and Large Language Models, offer innovative opportunities to enhance these areas. These technologies create practical, controlled environments for skill acquisition and behavioral training, while generative AI enables dynamic, personalized, and adaptive experiences. This paper explores the broader potential of these integrated technologies in supporting rehabilitation, reducing recidivism, and fostering sustainable employment opportunities and these initiatives align with the overarching equity objective of ensuring Decent Work for All, reinforcing the commitment to inclusive and equitable progress across diverse communities, through the transformative potential of immersive and AI-driven systems in correctional systems. © 2025 IEEE.

关键词： Engineering education

来源：评论

学校读者我要写书评

暂无评论

Focus360: Guiding User Attention in immersive Videos for VR

Focus360: Guiding User Attention in Immersive Videos for VR

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Paulo Vitor S. Silva Lucas L. Neves Rafael A. Goiás Diogo F. C. Silva Rafael T. Sousa Arlindo R. Galvão Filho Advanced Knowledge Center for Immersive Technologies AKCIT Federal University of Goiás UFG

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

This demo introduces Focus360, a system designed to enhance user engagement in 360° VR videos by guiding attention to key elements within the scene. Using natural language descriptions, the system identifies important elements and applies a combination of visual effects to guide attention seamlessly. At the demonstration venue, participants can experience a 360° Safari Tour, showcasing the system’s ability to improve user focus while maintaining an immersive experience.

关键词： Deep learning Three-dimensional displays Conferences Natural languages immersive experience User interfaces Visual effects Videos

来源：评论

学校读者我要写书评

暂无评论

immersive Virtual Museums with Spatially-Aware Retrieval-Augmented Generation 25

Immersive Virtual Museums with Spatially-Aware Retrieval-Aug...

引用

Proceedings of the 2025 ACM International Conference on Interactive Media Experiences

作者： Elisa Ayumi Masasi de Oliveira Rafael Teixeira Sousa Andressa Araújo Bastos Luiza Martins de Freitas Cintra Arlindo Rodrigues Galvão Filho Federal University of Goiás Goiania Brazil Federal University of Mato Grosso Barra do Garças Brazil and Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia GO Brazil Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia GO Brazil Federal University of Goiás Goiânia GO Brazil and Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia GO Brazil Federal University of Goias Goiânia Goiás Brazil and Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia GO Brazil

来源：评论

学校读者我要写书评

暂无评论

See Through My Eyes: Using Multimodal Large Language Model for Describing Rendered Environments to Blind People 25

See Through My Eyes: Using Multimodal Large Language Model f...

引用

Proceedings of the 2025 ACM International Conference on Interactive Media Experiences

作者： Angelo Coronado Sergio T Carvalho Luciana Berretta Federal University of Goias (UFG) Goiania Brazil and Advanced Knowledge Center for Immersive Technologies (AKCIT) Goiania Brazil Federal University of Goiás (UFG) Goiânia Brazil and Advanced Knowledge Center for Immersive Technologies (AKCIT) Goiania Brazil Federal University of Goiás Goiânia Brazil and Advanced Knowledge Center for Immersive Technologies (AKCIT) Goiania Brazil

来源：评论

学校读者我要写书评

暂无评论

Transformative Technologies for Rehabilitation: Leveraging immersive and AI-Driven Solutions to Reduce Recidivism and Promote Decent Work

Transformative Technologies for Rehabilitation: Leveraging I...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Rafael T. Sousa Elisa A. M. Oliveira Luiza M. F. Cintra Arlindo R. Galvão Filho Advanced Knowledge Center in Immersive Technology Federal University of Mato Grosso Advanced Knowledge Center in Immersive Technology Federal University of Goiás

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

关键词： Technological innovation Three-dimensional displays Generative AI Large language models Employment Psychology User interfaces Vocational training Real-time systems Sustainable development

来源：评论

学校读者我要写书评

暂无评论

An LLM-Enhanced Framework for Bridging Simulators and Game Engines towards Realistic 3D Simulations 25

An LLM-Enhanced Framework for Bridging Simulators and Game E...

引用

Proceedings of the 2025 ACM International Conference on Interactive Media Experiences

作者： Luiza Martins de Freitas Cintra Elisa Ayumi Masasi de Oliveira Rafael Teixeira Sousa Valdemar Vicente Graciano, Neto Arlindo Galvão Gustavo Webster Sofia Larissa da Costa Paiva Federal University of Goiás Goiânia GO Brazil and Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia Brazil Advanced Knowledge Center in Immersive Technology - AKCIT Goiânia GO Brazil Federal University of Mato Grosso Barra do Garças Brazil Federal University of Goiás Goiânia Brazil Federal University of Goias Goiânia Goiás Brazil Advanced Knowledge Center in Immersive Technology Goiânia Brazil

来源：评论

学校读者我要写书评

暂无评论

INFOQUEST: EVALUATING MULTI-TURN DIALOGUE AGENTS FOR OPEN-ENDED CONVERSATIONS WITH HIDDEN CONTEXT

arXiv

引用

arXiv 2025年

作者： de Oliveira, Bryan L.M. Martins, Luana G.B. Brandão, Bruno Melo, Luckeciano C. Advanced Knowledge Center for Immersive Technologies AKCIT Brazil Institute of Informatics Federal University of Goiás Brazil OATML University of Oxford United Kingdom

Large language models excel at following explicit instructions, but they often struggle with ambiguous or incomplete user requests, defaulting to verbose, generic responses instead of seeking clarification. We introduce InfoQuest, a multi-turn chat benchmark designed to evaluate how dialogue agents handle hidden context in open-ended user requests. This benchmark presents intentionally ambiguous scenarios that require models to engage in information-seeking dialogue by asking clarifying questions before providing appropriate responses. Our evaluation of both open and closed models reveals that, while proprietary models generally perform better, all current assistants struggle to gather critical information effectively. They often require multiple turns to infer user intent and frequently default to generic responses without proper clarification. We provide a systematic methodology for generating diverse scenarios and evaluating models’ information-seeking capabilities, which can be leveraged to automatically generate data for self-improvement. We also offer insights into the current limitations of language models in handling ambiguous requests through multi-turn interactions. © 2025, CC BY.

关键词： Chatbots

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：