PFI:AIR-TT: Video Collaboratory: A Platform for Active Viewing and Collaboration with Video Data

PFI:AIR-TT：视频协作：主动查看视频数据并进行协作的平台

• 批准号: 1500195
• 负责人: David Wilson
• 金额: $ 19.99万
• 依托单位: University of North Carolina at Charlotte
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2015
• 资助国家: 美国
• 起止时间: 2015-07-15 至 2017-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1500195&HistoricalAwards=false
• 关键词: PFI; AIR; TT; Video; Collaboratory

This PFI: AIR Technology Translation project focuses on translating an online software technology (The Video Collaboratory) to fill the need for innovative support in small group collaboration and discussion around video documents. The Video Collaboratory is important because increasingly huge amounts of video are being generated for business and personal use. And while there are currently ways to distribute / watch video, it is still not easy to drill into, analyze, and note important details from within the video as a means to an end, particularly when working with others. From corporate training to healthcare, education, and security, people need effective ways to privately converse about, mark up and brainstorm around videos that are linked directly into the video content itself. The project will result in a scaled-up and enhanced Video Collaboratory platform with the following unique features: new ways for precision interaction with video documents, direct connection of group discussions to the video timeline, and private social networking to support meaningful work with videos. These features provide the following advantages: enabling clearer, deeper discussion; reducing error and confusion; and increasing efficiency / saving time when compared to the leading competing technologies in this market space, such as YouTube and Vimeo, that focus on distribution rather than detailed analysis and use of video documents. This project will develop a market-ready technology platform for next-generation collaboration around video data.This project addresses the following technology gaps as it translates from research discovery toward commercial application: (1) social presence affordances and group analytics to enable group-guided viewing and synchronous interaction around video documents; (2) rich communication pathways to support multimedia annotations and video-centric filtering of commentary as part of video-anchored discussion; (3) responsive components for interface and video data to scale across platforms (particularly mobile) with smart video streaming that adapts to user network environments; and (4) elastic, scalable, and socially-aware metrics for group/project organization, access/privacy control, and content management for sharing. Significant contributions to the research and knowledge base are novel techniques designed to address these gaps, validated through user study testing. Contributions include techniques for synchronous interaction around video documents; social discussion threading (integrating context from annotated video segmentation, user interaction analytics, and discussion content); weighted adaptive video streaming to prioritize transfer of content by discussion activity; and a flexible, socially-aware model for access management and content sharing. In addition, personnel involved in this project, graduate students and post-docs, will receive technology translation and entrepreneurship experiences through research development and discovery toward commercial reality.

该PFI：AIR技术翻译项目的重点是翻译在线软件技术（视频协作），以满足围绕视频文档进行小组协作和讨论的创新支持需求。视频协作非常重要，因为越来越多的视频被生成用于商业和个人使用。虽然目前有一些方法可以分发/观看视频，但仍然不容易从视频中深入，分析和记录重要细节作为达到目的的手段，特别是在与他人合作时。从企业培训到医疗保健、教育和安全，人们需要有效的方式来私下匡威、标记和讨论直接链接到视频内容本身的视频。该项目将扩大和加强视频协作平台，具有以下独特功能：与视频文件进行精确互动的新方法，小组讨论与视频时间轴的直接联系，以及支持有意义的视频工作的私人社交网络。这些功能提供了以下优势：实现更清晰，更深入的讨论;减少错误和混乱;与该市场领域的领先竞争技术（如YouTube和Vimeo）相比，提高效率/节省时间，这些技术专注于分发而不是详细分析和使用视频文档。该项目将为下一代视频数据协作开发一个市场就绪的技术平台，解决从研究发现到商业应用的以下技术差距：（1）社交呈现可供性和群体分析，以实现围绕视频文档的群体引导观看和同步交互;（2）丰富的通信路径，以支持多媒体注释和以视频为中心的评论过滤，作为视频锚定讨论的一部分;（3）用于跨平台扩展的接口和视频数据的响应组件（特别是移动的）具有适应用户网络环境的智能视频流;以及（4）用于组/项目组织、访问/隐私控制和用于共享的内容管理的弹性、可扩展和社会感知的度量。对研究和知识库的重大贡献是旨在解决这些差距的新技术，通过用户研究测试进行了验证。其贡献包括围绕视频文档进行同步交互的技术;社交讨论线程（集成来自注释视频分割的上下文、用户交互分析和讨论内容）;加权自适应视频流以通过讨论活动优先传输内容;以及用于访问管理和内容共享的灵活的社交感知模型。此外，参与该项目的人员，研究生和博士后，将通过研究开发和商业现实的发现获得技术翻译和创业经验。