.png){kind=icon}
Return
A structured multi-feature representation for recognizing human action and interaction
.png){kind=icon}
OA
AI
DOI：10.1016/j.neucom.2018.08.066.png)
.png){kind=icon}
.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Active research has been carried out for human action recognition using 3D human skeleton joints with the release of cost-efficient RGB-D sensors. However, extracting discriminative features from noisy skeleton sequences to effectively distinguish various human action or interaction categories still remains challenging. This paper proposes a structured multi-feature representation for human action and interaction recognition. Specifically, a novel kernel enhanced bag of semantic words (BSW) is designed to represent the dynamic property of skeleton trajectories. By aggregating BSW with the geometric feature, a GBSW representation is constructed for human action recognition. For human interaction recognition where the cooperation of each subject matters, a GBSWC representation is proposed via combining the GBSW feature with a correlation feature which addresses the intrinsic relationship between interactive persons. Experimental results on several human action and interaction datasets demonstrate the superior performances of the proposed features over the state-of-the-art methods. (C) 2018 Elsevier B.V. All rights reserved.
Keywords:
Action recognition
Interaction recognition
RGB-D sensors
Skeleton joints
Multi-feature
Journal
IF:
6.5
Papers:
2.5W
Citations:
6.5W
Organization
Cited Papers
ShareSaveDepth Context: a new descriptor for human activity recognition by using sole depth sequences.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
ShareSave
ShareSaveEnhanced skeleton visualization for view invariant human action recognitionPATTERN RECOGNITION
PATTERN RECOGNITIONIF7.6
PREAI
ShareSave
View more