Multimodal video classification with stacked contractive autoencoders

网站地图 | English | 公务邮箱

About the library

Background
History
Leadership
Organization

Opening Hours
Collections
Help Via Email

Electronic Information Resources

Multimodal video classification with stacked contractive autoencoders

详细信息查看全文

作者：Yanan Liu ; ^{liuyn@zju.edu.cn" class="auth_mail" title="E-mail the corresponding author} ; Xiaoqing Feng ^{fxq_snake@163.com" class="auth_mail" title="E-mail the corresponding author} ; Zhiguang Zhou ^{zhouzhiguang@zjucadcg.cn" class="auth_mail" title="E-mail the corresponding author}
关键词：Multimodal ; Video classification ; Deep learning ; Stacked contractive autoencoder
刊名：Signal Processing
出版年：2016
出版时间：March 2016
年：2016
卷：120
期：Complete
页码：761-766
全文大小：728 K

文摘

class="label">•: A two-stage framework for multimodal video classification is proposed.
class="label">•: The model is built based on stacked contractive autoencoders.
class="label">•: The first stage is single modal pre-training.
class="label">•: The second stage is multimodal fine-tuning.
class="label">•: The objective functions are optimized by stochastic gradient descent.

NGLC 2004-2010.National Geological Library of China All Rights Reserved.
Add:29 Xueyuan Rd,Haidian District,Beijing,PRC. Mail Add: 8324 mailbox 100083
For exchange or info please contact us via email.