Deep State-Space Model for Noise Tolerant Skeleton-Based Action Recognition
-
- KAWAMURA Kazuki
- Faculty of Engineering and the Graduate School of System Informatics, Kobe University
-
- MATSUBARA Takashi
- Faculty of Engineering and the Graduate School of System Informatics, Kobe University
-
- UEHARA Kuniaki
- Faculty of Engineering and the Graduate School of System Informatics, Kobe University
この論文をさがす
抄録
<p>Action recognition using skeleton data (3D coordinates of human joints) is an attractive topic due to its robustness to the actor's appearance, camera's viewpoint, illumination, and other environmental conditions. However, skeleton data must be measured by a depth sensor or extracted from video data using an estimation algorithm, and doing so risks extraction errors and noise. In this work, for robust skeleton-based action recognition, we propose a deep state-space model (DSSM). The DSSM is a deep generative model of the underlying dynamics of an observable sequence. We applied the proposed DSSM to skeleton data, and the results demonstrate that it improves the classification performance of a baseline method. Moreover, we confirm that feature extraction with the proposed DSSM renders subsequent classifications robust to noise and missing values. In such experimental settings, the proposed DSSM outperforms a state-of-the-art method.</p>
収録刊行物
-
- IEICE Transactions on Information and Systems
-
IEICE Transactions on Information and Systems E103.D (6), 1217-1225, 2020-06-01
一般社団法人 電子情報通信学会
- Tweet
詳細情報 詳細情報について
-
- CRID
- 1390285300161218944
-
- NII論文ID
- 130007850086
-
- NII書誌ID
- AA11510321
-
- ISSN
- 17451361
- 09168532
-
- HANDLE
- 20.500.14094/90007346
-
- 本文言語コード
- en
-
- データソース種別
-
- JaLC
- IRDB
- Crossref
- CiNii Articles
- KAKEN
-
- 抄録ライセンスフラグ
- 使用不可