Supervised Learning of Semantic Classes for Image Annotation and Retrieval

Carneiro, Gustavo; Chan, Antoni B.; Moreno, Pedro J.; Vasconcelos, Nuno

doi:10.1109/tpami.2007.61

Cited by 767 publications

(583 citation statements)

References 37 publications

(71 reference statements)

Supporting

Mentioning

578

Contrasting

Unclassified

Order By: Relevance

“…This method received much attention and since its introduction several modifications and extensions have been proposed [22,12,4,5]; furthermore, the data used by Duygulu et al have become a benchmark for comparing image annotation methods [18,15,14]. Several successful semi-supervised methods have been proposed 1 [6,1,2,4,11,16,5], some of which outperform the previous work [11]. The intuitive idea in most of these methods is to introduce latent variables for modeling the joint (or conditional) probability of words and regions.…”

Section: Automatic Image Annotationmentioning

confidence: 99%

“…Hidden Markov models and Markov random fields have been introduced for consideration of dependencies between regions [4,13]. From the supervised learning community some approaches have been proposed for image labeling [17,6,7]. A work close in spirit to ours is that due to Li et al [17], where a probabilistic support vector machine classifier is used for ranking labels for each region.…”

Section: Automatic Image Annotationmentioning

confidence: 99%

“…Since words that tend to co-occur in the captions are very likely to be visually related, as they are used to describe the same image. We performed experiments on three subsets of the benchmark Corel data set ( [18,15,6,11,14]), using a k−nearest neighbors (knn) [19] method as our annotation strategy. Experimental results show that knn combined with our approach can result in significant improvements over knn alone and over other soft-annotation methods as well.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Improving Automatic Image Annotation Based on Word Co-occurrence

Montes

Sucar

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

Abstract. Accuracy of current automatic image labeling methods is under the requirements of annotation-based image retrieval systems. The performance of most of these labeling methods is poor if we just consider the most relevant label for a given region. However, if we look within the set of the top−k candidate labels for a given region, accuracy of most of these systems is improved. In this paper we take advantage of this fact and propose a method (NBI ) based on word co-occurrences that uses the naïve Bayes formulation for improving automatic image annotation methods. Our approach utilizes co-occurrence information of the candidate labels for a region with those candidate labels for the other surrounding regions, within the same image, for selecting the correct label. Co-occurrence information is obtained from an external collection of manually annotated images: the IAPR-TC12 benchmark. Experimental results using a k−nearest neighbors method as our annotation system, give evidence of significant improvements after applying the NBI method. NBI is efficient since the co-occurrence information was obtained off-line. Furthermore, our method can be applied to any other annotation system that ranks labels by their relevance.

show abstract

Section: Automatic Image Annotationmentioning

confidence: 99%

Section: Automatic Image Annotationmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Improving Automatic Image Annotation Based on Word Co-occurrence

Montes

Sucar

2008

Lecture Notes in Computer Science

View full text Add to dashboard Cite

show abstract

“…None of this information describes what is in the image or what the image is. Automatic image annotation [2][3][4][5] or tagging is an active research area of computer vision and pattern recognition, machine learning, and content-based image retrieval in computer science. It focuses on identifying the content of a raster image and assigning a limited number of unstructured semantic labels or text keywords to an image.…”

Section: Introductionmentioning

confidence: 99%

The National Cancer Informatics Program (NCIP) Annotation and Image Markup (AIM) Foundation Model

Mongkolwat¹,

Kleper²,

Talbot³

et al. 2014

J Digit Imaging

View full text Add to dashboard Cite

“…This has applications in several tasks such as image retrieval, object recognition, robot navigation, etc. Hence this has emerged as an important research area during the last decade [2,5,6,8,11,19,23]. In annotation datasets with large vocabularies of few hundred or more labels, there exist three practical issues: (a) Incomplete-labeling: The training samples are not exhaustively tagged with all relevant labels from vocabulary.…”

Section: Introductionmentioning

confidence: 99%

Exploring SVM for Image Annotation in Presence of Confusing Labels

Verma¹,

Jawahar²

2013

Procedings of the British Machine Vision Conference 2013

View full text Add to dashboard Cite

We address the problem of automatic image annotation in large vocabulary datasets. In such datasets, for a given label, there could be several other labels that act as its confusing labels. Three possible factors for this are (i) incomplete-labeling ("cars" vs. "vehicle"), (ii) label-ambiguity ("flowers" vs. "blooms"), and (iii) structural-overlap ("lion" vs. "tiger"). While previous studies in this domain have mostly focused on nearest-neighbour based models, we show that even the conventional one-vs-rest SVM significantly outperforms several benchmark models. We also demonstrate that with a simple modification in the hinge-loss of SVM, it is possible to significantly improve its performance. In particular, we introduce a tolerance-parameter in the hinge-loss. This makes the new model more tolerant against the errors in the classification of samples tagged with confusing labels as compared to other samples. This tolerance parameter is automatically determined using visual similarity and dataset statistics. Experimental evaluations demonstrate that our method (referred to as SVM with Variable Tolerance or SVM-VT) shows promising results on the task of image annotation on three challenging datasets, and establishes a baseline for such models in this domain.

show abstract

Supervised Learning of Semantic Classes for Image Annotation and Retrieval

Cited by 767 publications

References 37 publications

Improving Automatic Image Annotation Based on Word Co-occurrence

Improving Automatic Image Annotation Based on Word Co-occurrence

The National Cancer Informatics Program (NCIP) Annotation and Image Markup (AIM) Foundation Model

Exploring SVM for Image Annotation in Presence of Confusing Labels

Contact Info

Product

Resources

About