講演抄録/キーワード |
講演名 |
2017-12-17 09:30
Action Sequence Recognition in Videos by Combining a CTC Network with a Statistical Language Model ○Mengxi Lin・Nakamasa Inoue・Koichi Shinoda(Tokyo Tech) PRMU2017-101 |
抄録 |
(和) |
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%. |
(英) |
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%. |
キーワード |
(和) |
connectionist temporal classification / action sequence recognition / statistical language model / weakly supervised learning / / / / |
(英) |
connectionist temporal classification / action sequence recognition / statistical language model / weakly supervised learning / / / / |
文献情報 |
信学技報, vol. 117, no. 362, PRMU2017-101, pp. 1-6, 2017年12月. |
資料番号 |
PRMU2017-101 |
発行日 |
2017-12-10 (PRMU) |
ISSN |
Print edition: ISSN 0913-5685 Online edition: ISSN 2432-6380 |
著作権に ついて |
技術研究報告に掲載された論文の著作権は電子情報通信学会に帰属します.(許諾番号:10GA0019/12GB0052/13GB0056/17GB0034/18GB0034) |
PDFダウンロード |
PRMU2017-101 |