Dynamic Visual Saliency Modeling for Video Semantics

In this work, we propose a novel approach for modeling dynamic visual attention based on spatiotemporal analysis. Our model first detects salient points in three-dimensional video volumes, and then uses them as seeds to search the extent of salient regions in a motion attention map. To determine the extent of attended regions, the maximum entropy in the spatial domain is used to analyze the dynamics obtained from spatiotemporal analysis. To annotate video semantics, the extent of attended regions is further recognized as two predefined categories by using orientation filters, cars and people. The experiment results show that the proposed dynamic visual attention model can effectively detect visual saliency through successive video volumes.