Deep attentive and semantic preserving video summarization

作     者：Ji, Zhong Jiao, Fang Pang, Yanwei Shao, Ling 

作者机构：Tianjin Univ Sch Elect & Informat Engn Tianjin Peoples R China Incept Inst Artificial Intelligence Abu Dhabi U Arab Emirates 

出 版 物：《NEUROCOMPUTING》 (神经计算)

年 卷 期：2020年第405卷

页      面：200-207页

核心收录：

学科分类：08[工学] 0812[工学-计算机科学与技术（可授工学、理学学位）] 

基　　金：National Natural Science Foundation of China [61771329  61472273  61632018] 

主　　题：Video summarization Encoder-decoder Attention mechanism Semantic preserving 

摘      要：Video summarization shortens a lengthy video into a succinct version, whose challenges mainly originate from the difficulties of discovering the inherent relations between the original video and its summary, meanwhile minimizing the semantic information loss. Supervised approaches, especially those in deep learning framework, have demonstrated their effectiveness in video summarization. However, these approaches mainly focus on one of the challenges, and seldom pay close attention to both challenges simultaneously. To this end, we propose to pay close attention to this deficiency by incorporating the ideas of both the encoder-decoder attention and semantic preserving loss in a deep Seq2Seq framework for video summarization. Moreover, we also introduce Huber loss to replace the popular mean square error loss to enhance the robustness of the model to outliers. Extensive experiments on two benchmark video summarization datasets demonstrate that the proposed approach consistently outperforms the state-of-the-art ones.