Title: Salient object detection of social images based on semantic tag context
Authors: Ye Liang; Congyan Lang; Jian Yu; Hongzhe Liu
Addresses: School of Computer and Information Technology, Beijing Jiaotong University, Beijing 100044, China; Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, China ' School of Computer and Information Technology, Beijing Jiaotong University, Beijing 10044, China ' School of Computer and Information Technology, Beijing Jiaotong University, Beijing 10044, China ' Beijing Key Laboratory of Information Service Engineering, Beijing Union University, Beijing 100101, China
Abstract: Salient object detection is an important process for machines to understand visual contents as humans. Typically, most previous studies on salient object detection infer salient map by only using the visual features. In this paper, we propose a new paradigm on salient object detection, which aims at producing more reliable results by mining the context information from user's annotated tags. To address this problem, we firstly construct a large scale salient object dataset, which includes 5429 images from the NUSWIDE dataset (a real world web image database from National University of Singapore) with tag information and accurate human-labeled masks. Moreover, a specialised conditional random field (CRF) model is also proposed which takes account of both tag contexts and appearance cues. Extensive experiments show the effectiveness and superiority of our model which can accurately locate the salient objects.
Keywords: saliency; salient object detection; social images; tags.
DOI: 10.1504/IJSNET.2017.083535
International Journal of Sensor Networks, 2017 Vol.23 No.4, pp.233 - 247
Received: 19 Sep 2016
Accepted: 28 Oct 2016
Published online: 09 Apr 2017 *