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
{"_id":"dThLgxNSLEx4feGW9","bibbaseid":"meshry-hussein-torki-lineartimeonlineactiondetectionfrom3dskeletaldatausingbagsofgesturelets-2016","author_short":["Meshry, M.","Hussein, M. E.","Torki, M."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","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":[{"propositions":[],"lastnames":["Meshry"],"firstnames":["M."],"suffixes":[]},{"propositions":[],"lastnames":["Hussein"],"firstnames":["M.","E."],"suffixes":[]},{"propositions":[],"lastnames":["Torki"],"firstnames":["M."],"suffixes":[]}],"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","bibtex":"@inproceedings{meshry_linear-time_2016,\n\ttitle = {Linear-time online action detection from 3D skeletal data using bags of gesturelets},\n\trights = {All rights reserved},\n\tdoi = {10.1109/WACV.2016.7477587},\n\tabstract = {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.},\n\teventtitle = {2016 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})},\n\tpages = {1--9},\n\tbooktitle = {2016 {IEEE} Winter Conference on Applications of Computer Vision ({WACV})},\n\tauthor = {Meshry, M. and Hussein, M. E. and Torki, M.},\n\tyear = {2016},\n\tkeywords = {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},\n\tfile = {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}\n}\n\n","author_short":["Meshry, M.","Hussein, M. E.","Torki, M."],"bibbaseid":"meshry-hussein-torki-lineartimeonlineactiondetectionfrom3dskeletaldatausingbagsofgesturelets-2016","role":"author","urls":{},"keyword":["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"],"metadata":{"authorlinks":{}}},"bibtype":"inproceedings","biburl":"https://bibbase.org/f/2bJzYjCLapWTtM86s/mehussein-2023.bib","dataSources":["kYvtZ54PgkXqjbteW","mhdykGczo2jDicE3X","havAjNnaG4BxhYWyb"],"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"],"search_terms":["linear","time","online","action","detection","skeletal","data","using","bags","gesturelets","meshry","hussein","torki"],"title":"Linear-time online action detection from 3D skeletal data using bags of gesturelets","year":2016}