Browsing by Author "Mahmood A."
Now showing items 1-5 of 5
-
Action recognition in poor-quality spectator crowd videos using head distribution-based person segmentation
Mahmood A.; Al-Maadeed S. ( Springer Verlag , 2019 , Article)Despite a big volume of research on action recognition, little attention has been given to individual action recognition in poor-quality spectator crowd scenes. It is an important scenario, because most of the surveillance ... -
An information fusion framework for person localization via body pose in spectator crowds
Shaban M.; Mahmood A.; Al-Maadeed S.A.; Rajpoot N. ( Elsevier B.V. , 2019 , Article)Person localization or segmentation in low resolution crowded scenes is important for person tracking and recognition, action detection and anomaly identification. Due to occlusion and lack of inter-person space, person ... -
Dynamic workload patterns prediction for proactive auto-scaling of web applications
Iqbal W.; Erradi A.; Mahmood A. ( Academic Press , 2018 , Article)Proactive auto-scaling methods dynamically manage the resources for an application according to the current and future load predictions to preserve the desired performance at a reduced cost. However, auto-scaling web ... -
Multi-Order Statistical Descriptors for Real-Time Face Recognition and Object Classification
Mahmood A.; Uzair M.; Al-Maadeed S. ( Institute of Electrical and Electronics Engineers Inc. , 2018 , Article)We propose novel multi-order statistical descriptors which can be used for high speed object classification or face recognition from videos or image sets. We represent each gallery set with a global second-order statistic ... -
Spatiotemporal Low-Rank Modeling for Complex Scene Background Initialization
Javed S.; Mahmood A.; Bouwmans T.; Jung S.K. ( Institute of Electrical and Electronics Engineers Inc. , 2018 , Article)Background modeling constitutes the building block of many computer-vision tasks. Traditional schemes model the background as a low rank matrix with corrupted entries. These schemes operate in batch mode and do not scale ...