- Full text PDF available (2)
- This year (2)
- Last five years (3)
In this paper, we propose an improved mechanism for saliency detection.
This paper proposes an unsupervised bottom-up saliency detection approach by aggregating complementary background template with refinement. Feature vectors are extracted from each superpixel to cover regional color, contrast and texture information. By using these features, a coarse detection for salient region is realized based on background template… (More)