Temporal segmentation and keyframe selection methods for user-generated video search-based annotation

作者：

Highlights：

• Video temporal segmentation and keyframe selection approaches for User Generated Video (UGV).

• Hierarchical Hidden Markov Models applied to camera motion analysis to detect motion patterns and temporally segment the video.

• Evaluation of the influence of camera motion over the performance of automatic UGV annotation systems.

• Two datasets for User Generated Video have been developed and made publicly available.

摘要

•Video temporal segmentation and keyframe selection approaches for User Generated Video (UGV).•Hierarchical Hidden Markov Models applied to camera motion analysis to detect motion patterns and temporally segment the video.•Evaluation of the influence of camera motion over the performance of automatic UGV annotation systems.•Two datasets for User Generated Video have been developed and made publicly available.

论文关键词：User Generated Video,Video annotation,Video temporal segmentation,Camera motion analysis,Keyframe selection

论文评审过程：Available online 16 August 2014.

论文官网地址：https://doi.org/10.1016/j.eswa.2014.08.001