Image annotation via graph learning

Liu, Jing; Li, Mingjing; Liu, Qingshan; Lu, Hanqing; Ma, Shugen

doi:10.1016/j.patcog.2008.04.012

Cited by 179 publications

(109 citation statements)

References 6 publications

Supporting

Mentioning

106

Contrasting

Unclassified

Order By: Relevance

“…Importantly, it also improves over state-of-the-art TagProp alone. Therefore, our method also improves over other works such as [9,13], which were outperformed by TagProp (see scores for MBRM or TGLM within [11]). …”

Section: Experimental Evaluationmentioning

confidence: 63%

See 1 more Smart Citation

Combining Image-Level and Segment-Level Models for Automatic Annotation

Kuettel

Guillaumin

Ferrari

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. For the task of assigning labels to an image to summarize its contents, many early attempts use segment-level information and try to determine which parts of the images correspond to which labels. Best performing methods use global image similarity and nearest neighbor techniques to transfer labels from training images to test images. However, global methods cannot localize the labels in the images, unlike segment-level methods. Also, they cannot take advantage of training images that are only locally similar to a test image. We propose several ways to combine recent image-level and segment-level techniques to predict both image and segment labels jointly. We cast our experimental study in an unified framework for both image-level and segment-level annotation tasks. On three challenging datasets, our joint prediction of image and segment labels outperforms either prediction alone on both tasks. This confirms that the two levels offer complementary information.

show abstract

Section: Experimental Evaluationmentioning

confidence: 63%

“…In recent years, automatic image annotation has received increasing attention [11,13,17,18]. In its basic version, which we call image-level annotation, the task is to assign a few semantic labels to a test image, roughly describing its contents ( fig.…”

Section: Introductionmentioning

confidence: 99%

Combining Image-Level and Segment-Level Models for Automatic Annotation

Kuettel

Guillaumin

Ferrari

2012

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…The random walk algorithm has also been studied in the domains of unsupervised image segmentation [19] and multi-class classification [43]. Finally, random walk algorithms have also been explored in the area of image retrieval [11,18,22,26,28,30,34,46], where the main advantages of such approaches are: 1) the ability to use visual and non-visual cues in the random walk procedure, 2) the potential to extend the method to large-scale databases, and 3) the relatively facility to adapt the method to dynamic problems, where new images and labels are continuously introduced into the database.…”

Section: Literature Reviewmentioning

confidence: 99%

“…Note that this assumption is important to uncover the aforementioned influence of art prints over other artistic productions (and also over other art prints). Specifically, we explore the following graph-based algorithms [6,35,50]: label propagation [18,28,34,46], random walk [11], stationary solution using a stochastic matrix [30], and combinatorial harmonic [19]. We adapt each of those techniques to a bag of visual words (BOV) approach, and we compare their performance with BOV approaches that use the following classifiers: support vector machines (SVM) [45], and random forests (RF) [7].…”

Section: Introductionmentioning

confidence: 99%

Graph-based methods for the automatic annotation and retrieval of art prints

Carneiro

2011

Proceedings of the 1st ACM International Conference on Multimedia Retrieval

View full text Add to dashboard Cite

The analysis of images taken from cultural heritage artifacts is an emerging area of research in the field of information retrieval. Current methodologies are focused on the analysis of digital images of paintings for the tasks of forgery detection and style recognition. In this paper, we introduce a graph-based method for the automatic annotation and retrieval of digital images of art prints. Such method can help art historians analyze printed art works using an annotated database of digital images of art prints. The main challenge lies in the fact that art prints generally have limited visual information. The results show that our approach produces better results in a weakly annotated database of art prints in terms of annotation and retrieval performance compared to state-of-the-art approaches based on bag of visual words.H.3.3Information storage and retrievalInformation search and retrieval|Retrieval models I.4.8Image Processing and Computer VisionScene Analysis|Object Recognition G.3Probability and StatisticsProbabilistic Algorithms General TermsAlgorithms, Measurement, Experimentation Keywords Content-based image retrieval and annotation, Art image annotation and retrieval, Graph-based Learning methods

show abstract

“…Being aware of this, we propose an improved graph learning framework to resolve such issue. Graph-based methods [4] have achieved much success in the field of image retrieval [5] and automatic image annotation [8], which formulated the image retrieval task as a semi-supervised learning problem. Specifically, [5] take the user's query image as a labeled data and the images in the dataset as the unlabeled data, then the labels are propagated from the labeled data to the unlabeled data along their underlying manifold by analyzing their relationship in Euclidean space.…”

Section: An Improved Graph Learning Algorithmmentioning

confidence: 99%

A Novel Saliency-Based Graph Learning Framework with Application to CBIR

Bao

Feng

et al. 2011

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

SUMMARYLocalized content-based image retrieval (LCBIR) has emerged as a hot topic more recently because in the scenario of CBIR, the user is interested in a portion of the image and the rest of the image is irrelevant. In this paper, we propose a novel region-level relevance feedback method to solve the LCBIR problem. Firstly, the visual attention model is employed to measure the regional saliency of each image in the feedback image set provided by the user. Secondly, the regions in the image set are constructed to form an affinity matrix and a novel propagation energy function is defined which takes both low-level visual features and regional significance into consideration. After the iteration, regions in the positive images with high confident scores are selected as the candidate query set to conduct the next-round retrieval task until the retrieval results are satisfactory. Experimental results conducted on the SIVAL dataset demonstrate the effectiveness of the proposed approach.

show abstract

Image annotation via graph learning

Cited by 179 publications

References 6 publications

Combining Image-Level and Segment-Level Models for Automatic Annotation

Combining Image-Level and Segment-Level Models for Automatic Annotation

Graph-based methods for the automatic annotation and retrieval of art prints

A Novel Saliency-Based Graph Learning Framework with Application to CBIR

Contact Info

Product

Resources

About