Release Time:2019-03-10  Hits:

Indexed by: Conference Paper

Date of Publication: 2017-04-16

Included Journals: SCIE、CPCI-S、EI

Page Number: 230-237

Key Words: Co-saliency detection; co-salient seeds; partially absorbing random walk

Abstract: Co-saliency detection aims at finding the common salient objects in multiple images. In this paper, we introduce a new co-saliency detection model, which includes two main parts: co-salient seed selection using the inter-object recurrence cues from multiple images and saliency label propagation using partially absorbing random walk. With the guidance of cosalient seeds, salient objects are individually detected from each image through a semi-supervised label propagation process. Experimental results on two benchmark databases demonstrate that the proposed method achieves good performance.