• /  8
  • 下载费用: 19.90积分  

Valstar-2007-How to distinguish p

'Valstar-2007-How to distinguish p'
How to Distinguish Posed from Spontaneous Smiles using Geometric Features Michel F. Valstar Department of Computing Imperial College London michel.valstar@imperial.ac.uk Hatice Gunes Department of Computer Systems University of Technology, Sydney haticeg@it.uts.edu.au Maja Pantic Department of Computing/EEMCS Imperial College London, UK/Universiteit Twente, Netherlands m.pantic@imperial.ac.uk ABSTRACT Automatic distinction between posed and spontaneous ex- pressions is an unsolved problem. Previously cognitive sci- ences’ studies indicated that the automatic separation of posed from spontaneous expressions is possible using the face modality. However, little is known about the information from head and shoulder motion. In this work, we propose to (i) distinguish between posed and spontaneous smiles by fusing head, face, and shoulder modalities, (ii) investigate which modalities carry important information and how the modalities relate to each other, and (iii) to which extent the temporal dynamics of these signals attribute to solving the problem. A cylindrical head tracker is used to track head motion and two particle fi ltering techniques to track facial and shoulder motion. Classifi cation is performed by kernel methods combined with ensemble learning techniques. We investigated two aspects of multimodal fusion: the level of abstraction (i.e., early, mid-level, and late fusion) and the fusion rule used (i.e., sum, product and weight criteria). Ex- perimental results from 100 videos displaying posed smiles and 102 videos displaying spontaneous smiles are presented. Best results were obtained with late fusion of all modalities when 94.0% of the videos were classifi ed correctly. Categories and Subject Descriptors I.2.10 [Vision and scene understanding]: [Video analy- sis]; H.1.2 [User/Machine systems]: [Human information processing, Human Factors] General Terms Human Factors, Algorithms, Experimentation Keywords Human information processing, Deception detection, Multi- modal video processing Permission to make digital or hard copies of all or part of this work for personal or classroom use is granted without fee provided that copies are not made or distributed for profi t or commercial advantage and that copies bear this notice and the full citation on the fi rst page. To copy otherwise, to republish, to post on servers or to redistribute to lists, requires prior specifi c permission and/or a fee. ICMI’07, November 12-15, 2007, Nagoya, Aichi, Japan Copyright 2007 ACM 978-1-59593-817-6/07/0011 .$5.00. 1.INTRODUCTION Human-to-human interaction is multimodal. People natu- rally communicate multimodally by means of language, tone, facial expression, gesture and head movement, body move- ment and posture and possess a refi ned mechanism for the fusion of these data. To date, machines are not well able to emulate this ability. Psychological research fi ndings suggest that humans rely on the combined visual channels of face and body more than any other
关 键 词:
Valstar-2007-Howtodistinguishp
 天天文库所有资源均是用户自行上传分享,仅供网友学习交流,未经上传用户书面授权,请勿作他用。
关于本文
本文标题:Valstar-2007-How to distinguish p
链接地址: https://www.wenku365.com/p-40984916.html
关于我们 - 网站声明 - 网站地图 - 资源地图 - 友情链接 - 网站客服点击这里,给天天文库发消息,QQ:1290478887 - 联系我们

本站为“文档C2C交易模式”,即用户上传的文档直接卖给(下载)用户,本站只是中间服务平台,本站所有文档下载所得的收益归上传人(含作者)所有【成交的100%(原创)】。本站是网络服务平台方,若您的权利被侵害,侵权客服QQ:1290478887 欢迎举报。

1290478887@qq.com 2017-2027 https://www.wenku365.com 网站版权所有

粤ICP备19057495号 

收起
展开