Learning to Detect a Salient Object

Abstract

In this paper, we study the salient object detection problem for images. We formulate this problem as a binary labeling task where we separate the salient object from the background. We propose a set of novel features, including multiscale contrast, center-surround histogram, and color spatial distribution, to describe a salient object locally, regionally, and globally. A conditional random field is learned to effectively combine these features for salient object detection. Further, we extend the proposed approach to detect a salient object from sequential images by introducing the dynamic salient features. We collected a large image database containing tens of thousands of carefully labeled images by multiple users and a video segment database, and conducted a set of experiments over them to demonstrate the effectiveness of the proposed approach.

DOI: 10.1109/TPAMI.2010.70
View Slides

Extracted Key Phrases

17 Figures and Tables

010020020072008200920102011201220132014201520162017
Citations per Year

1,577 Citations

Semantic Scholar estimates that this publication has 1,577 citations based on the available data.

See our FAQ for additional information.

Cite this paper

@article{Liu2007LearningTD, title={Learning to Detect a Salient Object}, author={Tie Liu and Zejian Yuan and Jian Sun and Jingdong Wang and Nanning Zheng and Xiaoou Tang and Harry Shum}, journal={IEEE Transactions on Pattern Analysis and Machine Intelligence}, year={2007}, volume={33}, pages={353-367} }