From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model

Chang, Kai-Yueh; Liu, Tyng-Luh; Lai, Shang-Hong

doi:10.1109/cvpr.2011.5995415

Cited by 197 publications

(164 citation statements)

References 30 publications

(54 reference statements)

Supporting

Mentioning

164

Contrasting

Order By: Relevance

“…The saliency factor estimated for regions is fairly benefit for object co-segmentation [16], classification [17], retrieval [18] and object tracking [19]. A solution of color transfer by the mean and variance of colors [1] is enforced with saliency map in [20].…”

Section: Prior Workmentioning

confidence: 99%

Smooth Context based Color Transfer

Anh¹

2015

IJCA

View full text Add to dashboard Cite

Color transfer is an emerging framework for dealing with ubiquitous color manipulation in media such as documents and images. Despite the notable progress made in the field, there remains a need for designers that can represent the same information in personalization and corresponding to media context. This work presents adaptive color transfer method using cross-disciplinary interaction of semantic context and bilateral filters. Colors in the method are transferred softly in matching with saliency distributed context. Preliminary results show that the framework is highly keeping consistency and promising. Consequently in this work, a solution of tone mapping by color transfer is introduced. Experimental results are further showed pertaining for automatic handling colors and contrast.

show abstract

Section: Prior Workmentioning

confidence: 99%

Smooth Context based Color Transfer

Anh¹

2015

IJCA

View full text Add to dashboard Cite

show abstract

“…These methods aim at salient region extraction for individual images, while ignoring useful global information available from correlated image collections. Recently, co-saliency methods have been proposed to find common salient object(s) between pair of images [10,39] or among multiple images [8,52]. Such methods, however, require salient areas to contain parts of the foreground objects across most images.…”

Section: Related Workmentioning

confidence: 99%

“…We found that considering the largest appearance cluster [3] or top-ranked internet images [25] as an initial set to be unsatisfactory. In an interesting effort, Chang et al [8] use repeatedness among images as a global prior of multiple images and assume that most images contain at least parts of the foreground object, an assumption that is often violated in our setting. Further, since each image is compared with all others, the method cannot be used for large collections (e.g., they considered image sets of maximum size 30, while we handle a few 1000 s).…”

Section: Statistical Global Appearance Modelsmentioning

confidence: 99%

SalientShape: group saliency in image collections

et al. 2013

View full text Add to dashboard Cite

Efficiently identifying salient objects in large image collections is essential for many applications including image retrieval, surveillance, image annotation, and object recognition. We propose a simple, fast, and effective algorithm for locating and segmenting salient objects by analysing image collections. As a key novelty, we introduce group saliency to achieve superior unsupervised salient object segmentation by extracting salient objects (in collections of pre-filtered images) that maximize between-image similarities and within-image distinctness. To evaluate our method, we construct a large benchmark dataset consisting of 15 K images across multiple categories with 6000+ pixel-accurate ground truth annotations for salient object regions where applicable. In all our tests, group saliency consistently outperforms state-of-the-art single-image saliency algorithms, resulting in both higher precision and better recall. Our algorithm successfully handles image collections, of an order larger than any existing benchmark datasets, consisting of diverse and heterogeneous images from various internet sources.

show abstract

“…Considering the inter-image correspondence, researchers recently improve the saliency model in single image and propose the co-saliency model for multiple images [5,14,15]. Saliency and co-saliency models have been used in some co-segmentation methods [5,7,13].…”

Section: Intra-image Energy Termmentioning

confidence: 99%

“…Hochbaum and Singh [3] modify the global energy term using similarity between foreground histograms and then apply a max-flow solution like Graph Cuts [4] to efficiently optimize the energy function. Chang et al [5] formulate the global energy term by simultaneously considering foreground dissimilarity and dissimilarity between foreground and background. Rubio et al…”

Section: Introductionmentioning

confidence: 99%

Unsupervised co-segmentation based on a new global GMM constraint in MRF

Xian

2014

2014 IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

This paper proposes a new Markov Random Fields (MRF) optimization model for co-segmentation. The co-saliency model is incorporated into our model to make it fully unsupervised and work well for images with similar backgrounds. The Gaussian Mixture Model (GMM) based dissimilarity between foregrounds in each image and the common objects in the set is involved as a new global constraint (i.e., energy term) in our model. Finally, we introduce an alternative approximation to represent the energy function, which could be minimized by Graph Cuts iteratively. The experimental results on two datasets show that our algorithm achieves better or comparable accuracy when comparing with state-of-the-art algorithms.

show abstract

From co-saliency to co-segmentation: An efficient and fully unsupervised energy minimization model

Abstract: We address two key issues of co-segmentation over multiple images. The

Cited by 197 publications

References 30 publications

Smooth Context based Color Transfer

Smooth Context based Color Transfer

SalientShape: group saliency in image collections

Unsupervised co-segmentation based on a new global GMM constraint in MRF

Contact Info

Product

Resources

About