RGB-D-based action recognition datasets: A survey
详细信息 查看全文
- 作者：Jing Zhanga ; jz960@uowmail.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Wanqing Lia ; wanqing@uow.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Philip O. Ogunbonaa ; philipo@uow.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Pichao Wanga ; pw212@uowmail.edu.au" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae ; Chang Tanga ; b ; tangchang@tju.edu.cn" class="auth_mail" title="E-mail the corresponding authorAuthor Vitae
- 关键词：Action recognition ; RGB-D dataset ; Evaluation protocol
- 刊名：Pattern Recognition
- 出版年：2016
- 出版时间：December 2016
- 年：2016
- 卷：60
- 期：Complete
- 页码：86-105
- 全文大小：1315 K
文摘
- class="listitem" id="list_li0005">
- class="label">•
A detailed review and in-depth analysis of 44 publicly available RGB-D-based action datasets.
- class="label">•
Recommendations on the selection of datasets and evaluation protocols for use in future research.
- class="label">•
Identification of some limitations of these datasets and evaluation protocols.
- class="label">•
Recommendations on future creation of datasets and use of evaluation protocols.