Multi-label sparse coding for automatic image annotation

Wang, Changhu; Yan, Shuicheng; Zhang, Lei; Zhang, Hong-Jiang

doi:10.1109/cvpr.2009.5206866

Cited by 155 publications

(109 citation statements)

References 17 publications

Supporting

Mentioning

108

Contrasting

Order By: Relevance

“…It becomes an important research topic in the image retrieval & management systems. Image annotation is viewed as multi-label learning problem in which a set of labels are associated with the images containing multiple objects [6]. Since, annotate the images manually is the most time consuming task, which creates yet more challenging to image annotation problem.…”

Section: Review Workmentioning

confidence: 99%

A Proposed Method for Semantic Annotation on Social Media Images

Ghosh¹,

Bandyopadhyay²

2017

IJECS

View full text Add to dashboard Cite

Semantic annotation attaches to various concepts (e.g. people, things, places, organizations etc) in any other content. A semantically annotated document is easy to interpret, combine and reuse by computers. In human history Web plays as the greatest information source. Many researchers believe semantic annotations can be inserted in web-based documents for information extraction and knowledge mining. These annotations use terms defined in an ontology. This paper uses the annotation process based on textual patterns for improving annotation. IntroductionImage databases are large and databases are used in public domain applications and domain-specific applications. Internet services such as social networks, photo sharing image and video monitoring are the specific examples. Specific-domain applications use medicine, aerial surveillance, audiovisual archiving and many more.

show abstract

Section: Review Workmentioning

confidence: 99%

A Proposed Method for Semantic Annotation on Social Media Images

Ghosh¹,

Bandyopadhyay²

2017

IJECS

View full text Add to dashboard Cite

show abstract

“…Therefore, this approach no longer suffers a sequence of independent binary tests. Afterwards, Wang et al [8] present a multi-label sparse coding (MSC) framework for feature extraction and classification within the context of automatic image annotation. This method propagates the multi-labels of the training images to the query image with the sparse ℓ1 reconstruction coefficients.…”

Section: Related Workmentioning

confidence: 99%

“…The first one is based on discriminative model. It defines auto-annotation as a traditional supervised classification problem [4][5][6][7][8], which treats each semantic concept as an independent class and creates different classifiers for different concepts. This approach computes similarity at the visual level and annotates a new image by propagating the corresponding words.…”

Section: Introductionmentioning

confidence: 99%

Combining Generative/Discriminative Learning for Automatic Image Annotation and Retrieval

Li¹,

Tang²,

Zhao³

et al. 2012

IJIS

View full text Add to dashboard Cite

In order to bridge the semantic gap exists in image retrieval, this paper propose an approach combining generative and discriminative learning to accomplish the task of automatic image annotation and retrieval. We firstly present continuous probabilistic latent semantic analysis (PLSA) to model continuous quantity. Furthermore, we propose a hybrid framework which employs continuous PLSA to model visual features of images in generative learning stage and uses ensembles of classifier chains to classify the multi-label data in discriminative learning stage. Since the framework combines the advantages of generative and discriminative learning, it can predict semantic annotation precisely for unseen images. Finally, we conduct a series of experiments on a standard Corel dataset. The experiment results show that our approach outperforms many state-of-the-art approaches.

show abstract

“…The SRC achieves robust single-labeling for face recognition. For the image annotation task, Wang et al [7] proposed multi-label sparse coding (MSC) in the same manner as the SRC together with linear embedding into a discriminative space learned from the training images and their sparse labels. Hsu et al [8] have exploited the sparsity of the classifier output by the compressed sensing technique [9][10][11][12][13] for reducing computational expense of multi-label classification with linear regression.…”

Section: Introductionmentioning

confidence: 99%

Multi-label Classification for Image Annotation via Sparse Similarity Voting

Sakai

Itoh

Imiya

2011

Computer Vision – ACCV 2010 Workshops

View full text Add to dashboard Cite

Abstract. We present a supervised multi-label classification method for automatic image annotation. Our method estimates the annotation labels for a test image by accumulating similarities between the test image and labeled training images. The similarities are measured on the basis of sparse representation of the test image by the training images, which avoids similarity votes for irrelevant classes. Besides, our sparse representation-based multi-label classification can estimate a suitable combination of labels even if the combination is unlearned. Experimental results using the PASCAL dataset suggest effectiveness for image annotation compared to the existing SVM-based multi-labeling methods. Nonlinear mapping of the image representation using the kernel trick is also shown to enhance the annotation performance.

show abstract

Multi-label sparse coding for automatic image annotation

Abstract: Abstract

Cited by 155 publications

References 17 publications

A Proposed Method for Semantic Annotation on Social Media Images

A Proposed Method for Semantic Annotation on Social Media Images

Combining Generative/Discriminative Learning for Automatic Image Annotation and Retrieval

Multi-label Classification for Image Annotation via Sparse Similarity Voting

Contact Info

Product

Resources

About