In this paper

we propose a novel video key-frame extraction method based on visual attention model Firstly

the spatiotemporal saliency levels are generated and fused in a motion priority fashion to produce the overall attention degree Then

a new adaptive key-frame extraction algorithm using attention and the variation of attention is put forward For the shot level

the frames with higher attention value are selected as the candidates of the key-frames For the clip level

the key-frame number is generated by the attention variation in a shot Experimental results indicate the proposed method performs well in key-frame extraction with high efficiency