A spatiotemporal weighted dissimilarity-based method for video saliency detection

作者：

Highlights：

• We proposed a new video saliency detection method to allow for motion conspicuity.

• Spatial dissimilarity and preference difference are used as spatial conspicuity.

• The motion features are differences of motion vectors between adjacent frames.

• Experiments on ORIG-CRCNS, MTV and DIEM datasets.

摘要

Highlights•We proposed a new video saliency detection method to allow for motion conspicuity.•Spatial dissimilarity and preference difference are used as spatial conspicuity.•The motion features are differences of motion vectors between adjacent frames.•Experiments on ORIG-CRCNS, MTV and DIEM datasets.

论文关键词：Saliency detection,Video,Visual attention

论文评审过程：Available online 19 August 2015, Version of Record 18 November 2015.

论文官网地址：https://doi.org/10.1016/j.image.2015.08.005