Learning Optimal Seeds for Diffusion-Based Salient Object Detection

Song, Lei; Mahadevan, Vijay; Vasconcelos, Nuno

doi:10.1109/cvpr.2014.357

Cited by 117 publications

(75 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…using an initial saliency estimate) and iteratively refining the saliency of regions to obtain the final saliency map has been used by numerous models in the literature [25,26]. This practice shares commonalities with the process of digital matting.…”

Section: Relation Between Salient Object Detection and Natural Imagementioning

confidence: 98%

Salient object detection via spectral matting

Naqvi

Browne

Hollitt

2016

Pattern Recognition

View full text Add to dashboard Cite

Section: Relation Between Salient Object Detection and Natural Imagementioning

confidence: 98%

Salient object detection via spectral matting

Naqvi

Browne

Hollitt

2016

Pattern Recognition

View full text Add to dashboard Cite

“…Liu et al [19] propose to learn the linear fusion weight of saliency features in a Conditional Random Field (CRF) framework. Recently, the large-margin framework was adopted to learn the weights in [60]. Due to the highly non-linear essence of the saliency mechanism, the linear mapping might not perfectly capture the characteristics of saliency.…”

Section: Supervised Approachesmentioning

confidence: 99%

Salient Object Detection: A Discriminative Regional Feature Integration Approach

et al. 2016

View full text Add to dashboard Cite

Abstract-Salient object detection has been attracting a lot of interest, and recently various heuristic computational models have been designed. In this paper, we formulate saliency map computation as a regression problem. Our method, which is based on multi-level image segmentation, utilizes the supervised learning approach to map the regional feature vector to a saliency score. Saliency scores across multiple layers are finally fused to produce the saliency map. The contributions lie in two-fold. One is that we propose a discriminate regional feature integration approach for salient object detection. Compared with existing heuristic models, our proposed method is able to automatically integrate high-dimensional regional saliency features and choose discriminative ones. The other is that by investigating standard generic region properties as well as two widely studied concepts for salient object detection, i.e., regional contrast and backgroundness, our approach significantly outperforms state-of-the-art methods on six benchmark datasets. Meanwhile, we demonstrate that our method runs as fast as most existing algorithms.

show abstract

“…However, many previous methods [1,11,41,30,25,6,54] only solve the task of foreground segmentation, i.e. generating a dense foreground mask (saliency map).…”

Section: Input Outputmentioning

confidence: 99%