A Stacking Ensemble Approach for Supervised Video Summarization

Video summarization methods are usually classified into shot-level or frame-level methods, which are individually used in a general way. This paper investigates the underlying complementarity between the frame-level and shot-level methods, and a stacking ensemble approach is proposed for supervised video summarization. Firstly, we build up a stacking model to predict both the key frame probabilities and the temporal interest segments simultaneously. The two components are then combined via soft decision fusion to obtain the final scores of each frame in the video. A joint loss function is proposed here to train the model. The ablation experimental results show that the proposed method outperforms both the two corresponding individual method. Furthermore, extensive experiments and analysis on two benchmark datasets demonstrate the effectiveness of our method and its superior performance in comparison with the state-of-the-art methods.