Lazy Random Walks for Superpixel Segmentation

By Jianbing Shen, Yunfan Du, Wenguan Wang, Xuelong Li. IEEE Transactions on Image Processing, 2014

341 citations recorded by the source corpus.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Stereo Video Object Segmentation Using Stereoscopic Foreground Trajectories (2019, methodology): “We first apply [28] to initialize a disparity map Dt of each frame pair {IL t , IR t } and oversegment both sides of the frame pair into superpixel sets {SL t , SR t } via [1] or [7], [10], [12].”
Video Salient Object Detection via Fully Convolutional Networks (2017, methodology): “We model the optical flow on superpixel level [39], [49] as the motion of similar adjacent pixels should present consistency.”
Deep Visual Attention Prediction (2017, background): “nd neuroscience. This modeling not only gives an insight into HVS, but also shows much potential in areas such as image cropping, object recognition [5], visual tracking [6], object segmentation [7], [31], [35], video understanding [2], [53], [54], [55], [45], to name a few. In the past few decades,”