Fusing appearance and distribution information of interest points for action recognition
Most of the existing action recognition methods represent actions as bags of space-time
interest points. Specifically, space-time interest points are detected from the video and …
interest points. Specifically, space-time interest points are detected from the video and …
Hierarchical relaxed partitioning system for activity recognition
F Azhar, CT Li - IEEE transactions on cybernetics, 2016 - ieeexplore.ieee.org
A hierarchical relaxed partitioning system (HRPS) is proposed for recognizing similar
activities which has a feature space with multiple overlaps. Two feature descriptors are built …
activities which has a feature space with multiple overlaps. Two feature descriptors are built …
Unusual event detection in real-world surveillance applications
J Kuklyte - 2014 - doras.dcu.ie
Given the near-ubiquity of CCTV, there is significant ongoing research effort to apply image
and video analysis methods together with machine learning techniques towards …
and video analysis methods together with machine learning techniques towards …
Action recognition in videos using geometrical representation and kernel logistic regression with feature relevance
O Ouyed - 2018 - di.uqo.ca
Human activity recognition in videos is a very important problem in computer vision. The
main challenge in this area is how to develop algorithms capable of analyzing automatically …
main challenge in this area is how to develop algorithms capable of analyzing automatically …
An action recognition framework for uncontrolled video capture based on a spatio-temporal video graph
I Jargalsaikhan - 2017 - doras.dcu.ie
The task of automatic categorization and localization of human action in video sequences is
valuable for a variety of applications such as detecting relevant activities in surveillance …
valuable for a variety of applications such as detecting relevant activities in surveillance …