Co-saliency detection based on region-level fusion and pixel-level refinement

Abstract : This paper addresses the problem of co-saliency detection, which aims to identify the common salient objects in a set of images and is important for many applications such as object co-segmentation and co-recognition. First, the segmentation driven low-rank matrix recovery model is used for intra saliency detection in each individual image of the image set, to highlight the regions whose features are sparse in each image. Then, a region-level fusion method, which exploits inter-region dissimilarities on color histograms and global consistency of regions over the image set, adjusts the intra saliency maps to obtain the region-level co-saliency maps, which can highlight co-salient object regions and suppress irrelevant regions. Finally, a pixel-level refinement method, which integrates color-spatial similarity between pixel and region with image border connectivity based object prior, generates the pixel-level co-saliency maps with better quality. Extensive experiments on two benchmark datasets demonstrate that the proposed co-saliency model consistently outperforms the state-of-the-art co-saliency models in both subjective and objective evaluation.
Document type :
Conference papers
Complete list of metadatas
Contributor : Zhi Liu <>
Submitted on : Tuesday, May 27, 2014 - 2:29:11 AM
Last modification on : Friday, November 16, 2018 - 1:32:18 AM


  • HAL Id : hal-00996799, version 1


Lina Li, Zhi Liu, Wenbin Zou, Xiang Zhang, Olivier Le Meur. Co-saliency detection based on region-level fusion and pixel-level refinement. International Conference on Multimedia Expo (ICME), Jul 2014, Chengdu, China. pp.1-6. ⟨hal-00996799⟩



Record views