You-Do, I-Learn: Egocentric unsupervised discovery of objects and their modes of interaction towards video-based guidance
详细信息 查看全文
- 作者：Dima Damen ; dima.damen@bristol.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Teesid Leelasawassuk csztl@bristol.ac.uk" class="auth_mail" title="E-mail the corresponding author ; Walterio Mayol-Cuevas walterio.mayol-cuevas@bristol.ac.uk" class="auth_mail" title="E-mail the corresponding author
- 关键词：Video guidance ; Real-time computer vision ; Assistive computing ; Object discovery ; Object usage
- 刊名：Computer Vision and Image Understanding
- 出版年：2016
- 出版时间：August 2016
- 年：2016
- 卷：149
- 期：Complete
- 页码：98-112
- 全文大小：5540 K
文摘
- •
Discovering task-relevant objects from egocentric video sequences of multiple users, using appearance, position, motion and attention features.
- •
Distinguishing different ways in which a task-relevant object has been used.
- •
Automatically extracting usage snippets, to be used for video-based guidance.
- •
Tested on a variety of daily tasks such as initialising a printer, preparing a coffee and setting up a gym machine.