Modelling salient visual dynamics in videos

Automatic video annotation is a critical step for content-based video retrieval and browsing. Detecting the focus of interest in video frames automatically can benefit the tedious manual labeling process. However, producing an appropriate extent of visually salient regions in video sequences is a challenging task. Therefore, 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 the points as seeds to search the extent of salient regions in a novel motion attention map. To determine the extent of attended regions, we use the maximum entropy in the spatial domain to analyze the dynamics derived by spatiotemporal analysis. Our experiment results show that the proposed dynamic visual attention model achieves high precision value of 70% and reveals its robustness in successive video volumes.