Linear-time online action detection from 3D skeletal data using bags of gesturelets. Meshry, M., Hussein, M. E., & Torki, M. In 2016 IEEE Winter Conference on Applications of Computer Vision (WACV), pages 1–9, 2016.
doi  abstract   bibtex   
Sliding window is one direct way to extend a successful recognition system to handle the more challenging detection problem. While action recognition decides only whether or not an action is present in a pre-segmented video sequence, action detection identifies the time interval where the action occurred in an unsegmented video stream. Sliding window approaches can however be slow as they maximize a classifier score over all possible sub-intervals. Even though new schemes utilize dynamic programming to speed up the search for the optimal sub-interval, they require offline processing on the whole video sequence. In this paper, we propose a novel approach for online action detection based on 3D skeleton sequences extracted from depth data. It identifies the sub-interval with the maximum classifier score in linear time. Furthermore, it is suitable for real-time applications with low latency.
@inproceedings{meshry_linear-time_2016,
	title = {Linear-time online action detection from 3D skeletal data using bags of gesturelets},
	rights = {All rights reserved},
	doi = {10.1109/WACV.2016.7477587},
	abstract = {Sliding window is one direct way to extend a successful recognition system to handle the more challenging detection problem. While action recognition decides only whether or not an action is present in a pre-segmented video sequence, action detection identifies the time interval where the action occurred in an unsegmented video stream. Sliding window approaches can however be slow as they maximize a classifier score over all possible sub-intervals. Even though new schemes utilize dynamic programming to speed up the search for the optimal sub-interval, they require offline processing on the whole video sequence. In this paper, we propose a novel approach for online action detection based on 3D skeleton sequences extracted from depth data. It identifies the sub-interval with the maximum classifier score in linear time. Furthermore, it is suitable for real-time applications with low latency.},
	eventtitle = {2016 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})},
	pages = {1--9},
	booktitle = {2016 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})},
	author = {Meshry, M. and Hussein, M. E. and Torki, M.},
	year = {2016},
	keywords = {3D skeletal data, action recognition, bags of gesturelets, classifier, Feature extraction, gesture recognition, Histograms, image classification, image segmentation, image sequences, Indexes, Kinematics, linear-time online action detection, object detection, presegmented video sequence, real-time applications, real-time systems, Skeleton, sliding window, Three-dimensional displays, vectors, Video sequences, video signal processing},
	file = {IEEE Xplore Abstract Record:C\:\\Users\\Mohamed Hussein\\Zotero\\storage\\XGAJGHGI\\7477587.html:text/html;Submitted Version:C\:\\Users\\Mohamed Hussein\\Zotero\\storage\\EWPJSI35\\Meshry et al. - 2016 - Linear-time online action detection from 3D skelet.pdf:application/pdf}
}

Downloads: 0