Journal ArticleDOI
Learning graph affinities for spectral graph-based salient object detection
Reads0
Chats0
TLDR
The proposed method for learning graph affinities for salient object detection has an insignificant computational burden on, but significantly outperforms the baseline EQCut and achieves a comparable performance level with the state-of-the-art in some performance measures.About:
This article is published in Pattern Recognition.The article was published on 2017-04-01. It has received 20 citations till now. The article focuses on the topics: Graph (abstract data type) & Spectral graph theory.read more
Citations
More filters
Journal ArticleDOI
Sparse graphs with smoothness constraints: Application to dimensionality reduction and semi-supervised classification
TL;DR: A new sparse graph construction method that integrates manifold constraints on the unknown sparse codes as a graph regularizer that can out-perform many state-of-the-art methods for the tasks of label propagation, nonlinear and linear embedding.
Journal ArticleDOI
Saliency detection based on background seeds by object proposals and extended random walk
Muwei Jian,Muwei Jian,Runxia Zhao,Xin Sun,Hanjiang Luo,Wenyin Zhang,Huaxiang Zhang,Junyu Dong,Yilong Yin,Kin-Man Lam +9 more
TL;DR: A novel bottom-up saliency-detection algorithm is proposed to tackle and overcome the issue of undesired errors and retrieval outputs when the boundaries of the salient objects concerned touch, or connect with, the image’s border.
Posted Content
On differentiating eigenvalues and eigenvectors
TL;DR: In this paper, the conditions under which unique differentiable functions λ(X) and u(X), respectively, exist in a neighborhood of a square matrix (complex or otherwise) satisfying the equations Xu = λu, λO, and Xu = ǫ.
Journal ArticleDOI
Point set registration with mixture framework and variational inference
TL;DR: A three-phase registration strategy (TRS) is proposed to automatically process point set registration problem in different cases and shows favorable performances in most scenarios.
Journal ArticleDOI
DevsNet: Deep Video Saliency Network using Short-term and Long-term Cues
TL;DR: A novel deep learning framework of saliency detection for video sequences, namely Deep Video Saliency Network (DevsNet), which mainly consists of two components: 3D Convolutional Network (3D-ConvNet) and Bidirectional convolutional Long-Short Term Memory Network (B-ConVLSTM).
References
More filters
Journal ArticleDOI
Normalized cuts and image segmentation
Jianbo Shi,Jitendra Malik +1 more
TL;DR: This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.
Proceedings ArticleDOI
Normalized cuts and image segmentation
Jianbo Shi,Jitendra Malik +1 more
TL;DR: This work treats image segmentation as a graph partitioning problem and proposes a novel global criterion, the normalized cut, for segmenting the graph, which measures both the total dissimilarity between the different groups as well as the total similarity within the groups.
Journal ArticleDOI
Fast approximate energy minimization via graph cuts
TL;DR: This work presents two algorithms based on graph cuts that efficiently find a local minimum with respect to two types of large moves, namely expansion moves and swap moves that allow important cases of discontinuity preserving energies.
Proceedings ArticleDOI
A database of human segmented natural images and its application to evaluating segmentation algorithms and measuring ecological statistics
TL;DR: In this paper, the authors present a database containing ground truth segmentations produced by humans for images of a wide variety of natural scenes, and define an error measure which quantifies the consistency between segmentations of differing granularities.
Journal ArticleDOI
Objective Criteria for the Evaluation of Clustering Methods
TL;DR: This article proposes several criteria which isolate specific aspects of the performance of a method, such as its retrieval of inherent structure, its sensitivity to resampling and the stability of its results in the light of new data.