Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition
Date
2017
Authors
Qiao, R.
Liu, L.
Shen, C.
van den Hengel, A.
Editors
Advisors
Journal Title
Journal ISSN
Volume Title
Type:
Journal article
Citation
Pattern Recognition, 2017; 66:202-212
Statement of Responsibility
Ruizhi Qiao, Lingqiao Liu, Chunhua Shen, Anton van den Hengel
Conference Name
Abstract
Devising a representation suitable for characterizing human actions on the basis of a sequence of pose estimates generated by an RGBD sensor remains a research challenge. We here provide two insights into this challenge. First, we show that discriminate sequence of poses typically occur over a short time window, and thus we propose a simple-but-effective local descriptor called a trajectorylet to capture the static and kinematic information within this interval. Second, we show that state of the art recognition results can be achieved by encoding each trajectorylet using a discriminative trajectorylet detector set which is selected from a large number of candidate detectors trained through exemplar-SVMs. The action-level representation is obtained by pooling trajectorylet encodings. Evaluating on standard datasets acquired from the Kinect sensor, it is demonstrated that our method obtains superior results over existing approaches under various experimental setups.
School/Discipline
Dissertation Note
Provenance
Description
Access Status
Rights
© 2017 Elsevier Ltd. All rights reserved.