no code implementations • 11 Apr 2016 • Jubin Johnson, Ehsan Shahrian Varnousfaderani, Hisham Cholakkal, Deepu Rajan
In this paper, the matting problem is reinterpreted as a sparse coding of pixel features, wherein the sum of the codes gives the estimate of the alpha matte from a set of unpaired F and B samples.
no code implementations • 22 Apr 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
Although the role of the classifier is to support salient object detection, we evaluate its performance in image classification and also illustrate the utility of thresholded saliency maps for image segmentation.
no code implementations • CVPR 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
We propose a weakly supervised top-down saliency framework using only binary labels that indicate the presence/absence of an object in an image.
no code implementations • 16 Nov 2016 • Hisham Cholakkal, Jubin Johnson, Deepu Rajan
First, the probabilistic contribution of each image region to the confidence of a CNN-based image classifier is computed through a backtracking strategy to produce top-down saliency.
no code implementations • 9 Feb 2017 • Jubin Johnson, Hisham Cholakkal, Deepu Rajan
Sampling-based alpha matting methods have traditionally followed the compositing equation to estimate the alpha value at a pixel from a pair of foreground (F) and background (B) samples.
no code implementations • 27 Mar 2018 • Jubin Johnson, Shunsuke Yasugi, Yoichi Sugino, Sugiri Pranata, ShengMei Shen
Person re-identification (re-ID) aims to accurately re- trieve a person from a large-scale database of images cap- tured across multiple cameras.