“…To integrate the center bias into the saliency mapping framework, we utilize the object‐biased Gaussian refinement process [
18, 41, 42] to generate the center prior. To each pixel z whose coordinate is
, we denote the salient mapping of the center prior as:
where σ x , σ y are set as
the image's height and width and x obj , y obj are the object centers, defined as:
where,
is the weight, which are defined by the reconstruction error on pixel level
in ():
…”