Co-Saliency Detection via Co-Salient Object Discovery and Recovery
Authors:
- 20 July 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Signal Processing Letters
- Vol. 22 (11) , 2073-2077
Abstract
This letter proposes a novel co-saliency model to effectively discover and highlight co-salient objects in a set of images. Based on the gross similarity which combines color features and SIFT descriptors, some co-salient object regions are first discovered in each image as exemplars, which are exploited to generate the exemplar saliency maps with the use of single-image saliency model. Then both local recovery and global recovery of co-salient object regions are performed by propagating the exemplar saliency to the matched regions, and border connectivity is further exploited to generate the region-level co-saliency maps. Finally, the foci of attention area based pixel-level saliency derivation is used to generate the pixel-level co-saliency maps with even better quality. Experimental results on two benchmark datasets demonstrate that the proposed co-saliency model outperforms the state-of-the-art co-saliency models.Keywords
Funding Information
- National Natural Science Foundation of China (61171144, 61471230)
This publication has 30 references indexed in Scilit:
- Efficient Saliency-Model-Guided Visual Co-Saliency DetectionIEEE Signal Processing Letters, 2014
- Detecting Co-Salient Objects in Large Image SetsIEEE Signal Processing Letters, 2014
- Self-adaptively Weighted Co-saliency Detection via Rank ConstraintIEEE Transactions on Image Processing, 2014
- RIGOR: Reusing Inference in Graph Cuts for Generating Object Regions2014
- Detecting, segmenting and tracking unknown objects using multi-label MRF inferenceComputer Vision and Image Understanding, 2014
- Co-Salient Object Detection From Multiple ImagesIEEE Transactions on Multimedia, 2013
- Cluster-Based Co-Saliency DetectionIEEE Transactions on Image Processing, 2013
- From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model2011
- A Co-Saliency Model of Image PairsIEEE Transactions on Image Processing, 2011
- Efficient, high-quality image contour detection2009