Abstract

Human actions typically occur over a well localized extent in both space and time. Similarly, as typically captured in video, human actions have small spatiotemporal support in image space. This paper capitalizes on these observations by weighting feature pooling for action recognition over those areas within a video where actions are most likely to occur. To enable this operation, we defifine a novel measure of spacetime saliency. The measure relies on two observations regarding foreground motion of human actors: They typically exhibit motion that contrasts with that of their surrounding region and they are spatially compact. By using the resulting defifinition of saliency during feature pooling we show that action recognition performance achieves state-of-the-art levels on three widely considered action recognition datasets. Our saliency weighted pooling can be applied to essentially any locally defifined features and encodings thereof. Additionally, we demonstrate that inclusion of locally aggregated spatiotemporal energy features, which effificiently result as a by-product of the saliency computation, further boosts performance over reliance on standard action recognition features alone