Key-frame extraction and key-frame rate determination using human attention modeling

This paper presents a novel key-frame detection method that combines the visual saliency-based attention features with the contextual game status information for sports videos. First, it describes the approach of extracting the object oriented visual attention map and illustrates the algorithm for determining the contextual excitement curve. Semantic contextual inference is used to simulate how the video content attracts the subscribers. Second, it presents the fusion methodology of visual and contextual attention analysis based on the characteristics of human excitement. Finally, the experimental results demonstrate the efficiency and the robustness of our system by means of some baseball game videos.