Section: New Results
Spatio-Temporal Grids for Daily Living Action Recognition
Participants : Srijan Das, Kaustubh Sakhalkar, Michal Koperski, Francois Brémond.
Keywords: Spatio-temporal, Grids, Multi-modal
This work addresses the recognition of short-term daily living actions from RGB-D videos. Most of the existing approaches ignore spatio-temporal contextual relationships in the action videos. So, we have proposed to explore the spatial layout to better model the appearance. In order to encode temporal information, we divided the action sequence into temporal grids. We address the challenge of subject invariance by applying clustering on the appearance features and velocity features to partition the temporal grids. We validated our approach on four public datasets. The results show that our method is competitive with the state-of-the-art. The proposed architecture has been published in ICVGIP 2018 [40].