Embedding motion and structure features for action recognition

Zhen, Xiantong, Shao, Ling, Tao, Dacheng and Li, Xuelong (2013) Embedding motion and structure features for action recognition. IEEE Transactions on Circuits and Systems for Video Technology, 23 (7). pp. 1182-1190. ISSN 1051-8215

Full text not available from this repository.

Abstract

We propose a novel method to model human actions by explicitly coding motion and structure features that are separately extracted from video sequences. Firstly, the motion template (one feature map) is applied to encode the motion information and image planes (five feature maps) are extracted from the volume of differences of frames to capture the structure information. The Gaussian pyramid and center-surround operations are performed on each of the six obtained feature maps, decomposing each feature map into a set of subband maps. Biologically inspired features are then extracted by successively applying Gabor filtering and max pooling on each subband map. To make a compact representation, discriminative locality alignment is employed to embed the high-dimensional features into a low-dimensional manifold space. In contrast to sparse representations based on detected interest points, which suffer from the loss of structure information, the proposed model takes into account the motion and structure information simultaneously and integrates them in a unified framework; it therefore provides an informative and compact representation of human actions. The proposed method is evaluated on the KTH, the multiview IXMAS, and the challenging UCF sports datasets and outperforms state-of-the-art techniques on action recognition.

Item Type:	Article
Faculty \ School:	Faculty of Science > School of Computing Sciences
Depositing User:	Pure Connector
Date Deposited:	07 Feb 2017 02:39
Last Modified:	31 Oct 2022 12:31
URI:	https://ueaeprints.uea.ac.uk/id/eprint/62328
DOI:	10.1109/TCSVT.2013.2240916

Actions (login required)

View Item