User-Ranking Video Summarization With Multi-Stage Spatio–Temporal Representation

摘要

Video summarization is a challenging task, mainly due to the difficulties in learning complicated semantic structural relations between videos and summaries. In this paper, we present a novel supervised video summarization scheme based on three-stage deep neural networks. The scheme takes a divide-andconquer strategy to resolve the complicated task of 3D video summarization into a set of easy and flexible computational subtasks, and then to sequentially perform 2D CNNs, 1D CNNs, and long short-term memory to address the subtasks in an hierarchical fashion. The hierarchical modeling of spatio-temporal structure leads to high performance and efficiency. In addition, we propose a simple but effective user-ranking method to cope with the labeling subjectivity problem of user-created video summarization, leading to the labeling quality refinement for robust supervised learning. Experimental results show that our approach outperforms the state-of-the-art video summarization methods on two benchmark datasets.