Romero Morais — accepted AI-conference papers

2021

Learning Asynchronous and Sparse Human-Object Interaction in Videos

Romero Morais, Vuong Le, Svetha Venkatesh, Truyen Tran

CVPR 2021poster

Human activities can be learned from video. With effective modeling it is possible to discover not only the action labels but also the temporal structure of the activities, such as the progression of the sub-activities. Automatically recognizing such structure from raw video signal is a new capabili…

Cited by 47 PDF ↗Scholar ↗

2019

Learning Regularity in Skeleton Trajectories for Anomaly Detection in Videos

Romero Morais, Vuong Le, Truyen Tran, Budhaditya Saha, Moussa Mansour, Svetha Venkatesh

CVPR 2019poster

Appearance features have been widely used in video anomaly detection even though they contain complex entangled factors. We propose a new method to model the normal patterns of human movements in surveillance video for anomaly detection using dynamic skeleton features. We decompose the skeletal move…

Cited by 379 PDF ↗code ↗Scholar ↗