A Top-Down Approach for Video Summarization
作者: Genliang GuanZhiyong WangShaohui MeiMax OttMingyi HeDavid Dagan Feng
刊名: ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM), 2014, Vol.11 (1), pp.1-21
来源数据库: Association for Computing Machinery Journal
DOI: 10.1145/2632267
关键词: Keyframe extractionclusteringkeypointlocal visual wordscene identification
原始语种摘要: While most existing video summarization approaches aim to identify important frames of a video from either a global or local perspective, we propose a top-down approach consisting of scene identification and scene summarization. For scene identification, we represent each frame with global features and utilize a scalable clustering method. We then formulate scene summarization as choosing those frames that best cover a set of local descriptors with minimal redundancy. In addition, we develop a visual word-based approach to make our approach more computationally scalable. Experimental results on two benchmark datasets demonstrate that our proposed approach clearly outperforms the state-of-the-art.
全文获取路径: ACM  (合作)

  • scene 景物
  • summarization 概括
  • scalable 修]可伸缩[缩放
  • frames 肋骨框架
  • propose 提议
  • benchmark 基准点
  • demonstrate 说明
  • existing 现行
  • video 影象
  • features 特征