1. "Object Segmentation using Superpixel-based Region Merging" by Zhang, Z., et al. (2015)

The paper proposes a novel approach for object segmentation using superpixel-based region merging. The proposed method consists of three main stages: superpixel segmentation, initial region merging, and final region merging. In the first stage, an image is segmented into superpixels using the SLIC algorithm. In the second stage, neighboring superpixels are merged if they have similar color and texture features. The third stage refines the segmentation by considering the object boundaries and the contrast between regions.

The proposed method is evaluated on two datasets: the Berkeley Segmentation Dataset and the Pascal VOC 2012 Segmentation Challenge. The experimental results show that the proposed method outperforms several state-of-the-art methods in terms of segmentation accuracy and computational efficiency.

Overall, the paper presents a promising approach for object segmentation using superpixel-based region merging. The proposed method is simple, efficient, and achieves state-of-the-art results on benchmark datasets.