A survey of recent interactive image segmentation methods
Image segmentation is one of the most basic tasks in computer vision and remains an initial
step of many applications. In this paper, we focus on interactive image segmentation (IIS) …
step of many applications. In this paper, we focus on interactive image segmentation (IIS) …
Segment-based disparity refinement with occlusion handling for stereo matching
T Yan, Y Gan, Z **a, Q Zhao - IEEE Transactions on Image …, 2019 - ieeexplore.ieee.org
In this paper, we propose a disparity refinement method that directly refines the winner-take-
all (WTA) disparity map by exploring its statistical significance. According to the primary …
all (WTA) disparity map by exploring its statistical significance. According to the primary …
Mercer features for efficient combinatorial Bayesian optimization
Bayesian optimization (BO) is an efficient framework for solving black-box optimization
problems with expensive function evaluations. This paper addresses the BO problem setting …
problems with expensive function evaluations. This paper addresses the BO problem setting …
Higher order energies for image segmentation
A novel energy minimization method for general higher order binary energy functions is
proposed in this paper. We first relax a discrete higher order function to a continuous one …
proposed in this paper. We first relax a discrete higher order function to a continuous one …
Kernel Cuts: Kernel and Spectral Clustering Meet Regularization
This work bridges the gap between two popular methodologies for data partitioning: kernel
clustering and regularization-based segmentation. While addressing closely related …
clustering and regularization-based segmentation. While addressing closely related …
Interactive image segmentation using constrained dominant sets
We propose a new approach to interactive image segmentation based on some properties
of a family of quadratic optimization problems related to dominant sets, a well-known graph …
of a family of quadratic optimization problems related to dominant sets, a well-known graph …
Large-scale price optimization via network flow
S Ito, R Fujimaki - Advances in Neural Information …, 2016 - proceedings.neurips.cc
This paper deals with price optimization, which is to find the best pricing strategy that
maximizes revenue or profit, on the basis of demand forecasting models. Though recent …
maximizes revenue or profit, on the basis of demand forecasting models. Though recent …
Loosecut: Interactive image segmentation with loosely bounded boxes
One popular approach to interactively segment an object of interest from an image is to
annotate a bounding box that covers the object, followed by a binary labeling. However, the …
annotate a bounding box that covers the object, followed by a binary labeling. However, the …
Secrets of grabcut and kernel k-means
The log-likelihood energy term in popular model-fitting segmentation methods, eg
Zhu&Yuille, Chan-Vese, GrabCut, is presented as a generalized" probabilistic K-means" …
Zhu&Yuille, Chan-Vese, GrabCut, is presented as a generalized" probabilistic K-means" …
Neutro-connectedness cut
Interactive image segmentation is a challenging task and receives increasing attention
recently; however, two major drawbacks exist in interactive segmentation approaches. First …
recently; however, two major drawbacks exist in interactive segmentation approaches. First …