Visual saliency detection: From space to frequency

作者：

Highlights：

• Some frequency-based saliency models can be transformed into the space domain.

• The frequency-based model derived from the transformation of multiple Gabor filters outperforms most of competing models.

• The SWE-based scale competition is a better scheme for scale combination.

• ARI is a better saliency metric than other AUC-based metrics.

摘要

Highlights•Some frequency-based saliency models can be transformed into the space domain.•The frequency-based model derived from the transformation of multiple Gabor filters outperforms most of competing models.•The SWE-based scale competition is a better scheme for scale combination.•ARI is a better saliency metric than other AUC-based metrics.

论文关键词：Saliency detection,Human fixation prediction,Gabor function,Fourier transform,Multi-scale saliency

论文评审过程：Received 15 July 2015, Revised 10 March 2016, Accepted 10 March 2016, Available online 12 March 2016, Version of Record 28 March 2016.

论文官网地址：https://doi.org/10.1016/j.image.2016.03.003