Issue No. 02 - February (2011 vol. 33)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TPAMI.2010.70
Tie Liu , Xi'an Jiaotong University, Xi'an and IBM Research-China, Beijing
Zejian Yuan , Xi'an Jiaotong Uinversity, Xi'an
Jian Sun , Microsoft Research Asia, Beijing
Jingdong Wang , Microsoft Research Aisa, Beijing
Nanning Zheng , Xi'an Jiaotong Uinversity, Xi'an
Xiaoou Tang , Chinese University of Hong Kong, Hong Kong
Heung-Yeung Shum , Microsoft, Redmond
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.
Salient object detection, conditional random field, visual attention, saliency map.
Tie Liu, Zejian Yuan, Jian Sun, Jingdong Wang, Nanning Zheng, Xiaoou Tang, Heung-Yeung Shum, "Learning to Detect a Salient Object", IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 33, no. , pp. 353-367, February 2011, doi:10.1109/TPAMI.2010.70