Journal ArticleDOI
Co-saliency Detection with Graph Matching
Reads0
Chats0
TLDR
A novel graph-matching based model is proposed to integrate the visual appearance, saliency coherence, and spatial structural continuity for detecting co-saliency collaboratively and outperforms state-of-the-art baselines significantly.Abstract:
Recently, co-saliency detection, which aims to automatically discover common and salient objects appeared in several relevant images, has attracted increased interest in the computer vision community. In this article, we present a novel graph-matching based model for co-saliency detection in image pairs. A solution of graph matching is proposed to integrate the visual appearance, saliency coherence, and spatial structural continuity for detecting co-saliency collaboratively. Since the saliency and the visual similarity have been seamlessly integrated, such a joint inference schema is able to produce more accurate and reliable results. More concretely, the proposed model first computes the intra-saliency for each image by aggregating multiple saliency cues. The common and salient regions across multiple images are thus discovered via a graph matching procedure. Then, a graph reconstruction scheme is proposed to refine the intra-saliency iteratively. Compared to existing co-saliency detection methods that only utilize visual appearance cues, our proposed model can effectively exploit both visual appearance and structure information to better guide co-saliency detection. Extensive experiments on several challenging image pair databases demonstrate that our model outperforms state-of-the-art baselines significantly.read more
Citations
More filters
Proceedings ArticleDOI
Adaptive Graph Convolutional Network With Attention Graph Clustering for Co-Saliency Detection
TL;DR: Zhang et al. as mentioned in this paper proposed an adaptive graph convolutional network with attention graph clustering (GCAGC) to detect common and salient foregrounds from a group of relevant images.
Journal ArticleDOI
End-to-End Text-to-Image Synthesis with Spatial Constrains
TL;DR: This article proposes a novel end-to-end approach for text- to-image synthesis with spatial constraints by mining object spatial location and shape information by fusing text semantic and spatial information into a synthesis module and jointly fine-tuning them with multi-scale semantic layouts generated.
Journal ArticleDOI
GTAE: Graph Transformer–Based Auto-Encoders for Linguistic-Constrained Text Style Transfer
TL;DR: This work proposes a method called Graph Transformer based Auto Encoder (GTAE), which models a sentence as a linguistic graph and performs feature extraction and style transfer at the graph level, to maximally retain the content and the linguistic structure of original sentences.
Journal ArticleDOI
Re-Thinking the Relations in Co-Saliency Detection
TL;DR: A new concept of structural inter-saliency relations is proposed and solved to solve the CoSOD with deep reinforcement learning framework and achieves superior performance compared to the state-of-the-art methods.
Journal ArticleDOI
Superpixel Region Merging Based on Deep Network for Medical Image Segmentation
TL;DR: This work presents a new approach called "Smart Segmentation of pathological structures in medical images" (SCSI) that addresses the challenge of automatic and accurate semantic segmentation in the face of noisy disturbance, deformable shapes of pathology, and low contrast between soft and hard structures.
References
More filters
Journal ArticleDOI
Efficient Graph-Based Image Segmentation
TL;DR: An efficient segmentation algorithm is developed based on a predicate for measuring the evidence for a boundary between two regions using a graph-based representation of the image and it is shown that although this algorithm makes greedy decisions it produces segmentations that satisfy global properties.
Journal ArticleDOI
Algorithms for the Assignment and Transportation Problems
TL;DR: In this paper, algorithms for the solution of the general assignment and transportation problems are presen, and the algorithm is generalized to one for the transportation problem.
Proceedings ArticleDOI
Global contrast based salient region detection
TL;DR: This work proposes a regional contrast based saliency extraction algorithm, which simultaneously evaluates global contrast differences and spatial coherence, and consistently outperformed existing saliency detection methods.
Proceedings Article
Graph-Based Visual Saliency
TL;DR: A new bottom-up visual saliency model, Graph-Based Visual Saliency (GBVS), is proposed, which powerfully predicts human fixations on 749 variations of 108 natural images, achieving 98% of the ROC area of a human-based control, whereas the classical algorithms of Itti & Koch achieve only 84%.
Proceedings ArticleDOI
Saliency Detection via Graph-Based Manifold Ranking
TL;DR: This work considers both foreground and background cues in a different way and ranks the similarity of the image elements with foreground cues or background cues via graph-based manifold ranking, defined based on their relevances to the given seeds or queries.