政大機構典藏:Item 140.119/111901

政大機構典藏

Menu Search
查询小技巧：
  • 您可在西文检索词汇前后加上"双引号"，以获取较精准的检索结果
  • 若欲以作者姓名搜寻，建议至进阶搜寻限定作者字段，可获得较完整数据
    •  进阶搜寻
    政大機構典藏 > 資訊學院 > 資訊科學系 > 會議論文 >  Item 140.119/111901


    请使用永久网址来引用或连结此文件: https://nccur.lib.nccu.edu.tw/handle/140.119/111901


    题名: Estimation and evaluation of body language in a presentation scenario using RGBD data
    作者: 廖文宏
    Wu, Yi Chieh
    Liao, Wenhung
    贡献者: 資訊科學系
    关键词: Animation;Classification (of information);Computational linguistics;Intelligent systems;Personnel training;Audio processing;Body language;Evaluation results;Facial Expressions;Kinect sensors;performance evaluation;Presentation style;Skeletal joints;Intelligent control
    日期: 2015
    上传时间: 2017-08-10 15:16:38 (UTC+8)
    摘要: In this research, we capture body movements, facial expressions, and voice data of subjects in the presentation scenario using RGBD-capable Kinect sensor. The acquired videos were accessed by a group of reviewers to indicate their preferences/aversions to the presentation style. We denote the two classes of ruling as Period of Like (POL) and Period of Dislike (POD), respectively. We then employ three types of image features, namely, animation units (AU), skeletal joints, and 3D face vertices to analyze the consistency of the evaluation result, as well as the ability to classify unseen footage based on the training data supplied by 35 evaluators. Finally, we develop a prototype program to help users to identify their strength/weakness during their presentation so that they can improve their skills accordingly. © 2015 The authors and IOS Press. All rights reserved.
    關聯: Frontiers in Artificial Intelligence and Applications, 274, 1213-1222
    International Computer Symposium, ICS 2014; Taichung; Taiwan; 12 December 2014 到 14 December 2014; 代碼 111725
    数据类型: conference
    DOI 連結: http://dx.doi.org/10.3233/978-1-61499-484-8-1213
    DOI: 10.3233/978-1-61499-484-8-1213
    显示于类别:[資訊科學系] 會議論文

    文件中的档案:

    档案 描述 大小格式浏览次数
    index.html0KbHTML21014检视/开启


    在政大典藏中所有的数据项都受到原著作权保护.


    社群 sharing
    DSpace Software Copyright © 2002-2004  MIT &  HP  /   Enhanced by   NTU Library IR team Copyright ©   - 回馈