Overview

The MSRA Salient Object Database, which originally provides salient object annotation in terms of bounding boxes provided by 3-9 users, is widely used in salient object detection and segmentation community. It contains pixel accurate salient object labeling for 5000 images from MSRA-B dataset.

Citation

@Article{WangDRFI2017,
    author="Wang, Jingdong and Jiang, Huaizu and Yuan, Zejian and Cheng, Ming-Ming and Hu,
Xiaowei and Zheng, Nanning",
    title="Salient Object Detection: A Discriminative Regional Feature Integration Approach",
    journal="International Journal of Computer Vision",
    year="2017",
    volume="123",
    number="2",
    pages="251--268",
    issn="1573-1405",
    doi="10.1007/s11263-016-0977-3"
}