Home >

news Help

Publication Information


Title
Japanese: 
English:Action Sequence Recognition in Videos by Combining a CTC Network with a Statistical Language Model 
Author
Japanese: Lin Mengxi, 井上 中順, 篠田 浩一.  
English: Mengxi Lin, Nakamasa Inoue, Koichi Shinoda.  
Language English 
Journal/Book name
Japanese: 
English:Technical Reports of IEICE PRMU 
Volume, Number, Page vol. 117    no. 362    pp. 1-6
Published date Dec. 16, 2017 
Publisher
Japanese:電子情報通信学会 
English: 
Conference name
Japanese: 
English:Pattern Recognition and Media Understanding (PRMU) 2017-12 
Conference site
Japanese: 
English:慶應義塾大学 理工学部 矢上キャンパス 
File
Official URL http://www.ieice.org/ken/paper/20171217m1A7/
http://www.ieice.org/ken/program/index.php?tgs_regid=dcb3f5da17b46802a7ac54d2b097a59876c6cb3ce4786e95505fbc3a90fe24d9&tgid=IEICE-PRMU&lang=
 
Abstract Action sequence recognition aims to recognize what actions occur in a video and their temporal order. In this paper, we propose to combine an LSTM network trained with Connectionist Temporal Classification (CTC) with a statistical language model for action sequence recognition. The statistical language model captures the relations between action instances, which are hardly learned by the CTC network. Our experiments on the Breakfast dataset show that the statistical language model can significantly boost the recognition accuracy of the CTC network, from 37.0% to 43.4%.

©2007 Tokyo Institute of Technology All rights reserved.